CN113901621A - SVM power distribution network topology identification method based on artificial fish swarm algorithm optimization - Google Patents
SVM power distribution network topology identification method based on artificial fish swarm algorithm optimization Download PDFInfo
- Publication number
- CN113901621A CN113901621A CN202111208168.8A CN202111208168A CN113901621A CN 113901621 A CN113901621 A CN 113901621A CN 202111208168 A CN202111208168 A CN 202111208168A CN 113901621 A CN113901621 A CN 113901621A
- Authority
- CN
- China
- Prior art keywords
- svm
- artificial fish
- distribution network
- power distribution
- swarm algorithm
- 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.)
- Withdrawn
Links
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 52
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000005457 optimization Methods 0.000 title claims abstract description 22
- 238000012706 support-vector machine Methods 0.000 claims abstract description 54
- 238000005259 measurement Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000012544 monitoring process Methods 0.000 claims abstract description 5
- 230000000007 visual effect Effects 0.000 claims description 14
- 238000010606 normalization Methods 0.000 claims description 9
- 230000002431 foraging effect Effects 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 23
- 239000013598 vector Substances 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power distribution network topology identification method based on an SVM (support vector machine) optimized by an artificial fish swarm algorithm, which comprises the following steps of: collecting section voltage amplitude measurement data of various load levels of observation nodes under different topological structures and corresponding topological labels by using an SCADA system, and carrying out standardized preprocessing; obtaining a training data set after standardized preprocessing; establishing a power distribution network topology identification model of an SVM (support vector machine) based on artificial fish swarm algorithm optimization; and (4) acquiring section voltage amplitude measurement data of the observation node from the monitoring node, carrying out standardization preprocessing, substituting the data obtained in the third step into a power distribution network topology identification model of the SVM (support vector machine) based on artificial fish swarm algorithm optimization, and obtaining a circuit topology structure of the observation node. The method and the device can reduce the time for identifying the topology of the power distribution network and improve the identification precision.
Description
Technical Field
The invention relates to the technical field of power distribution network topology identification, in particular to a power distribution network topology identification method based on an SVM (support vector machine) optimized by an artificial fish swarm algorithm.
Background
The task of power grid topology identification is to convert a physical model described by nodes into a mathematical model described by buses and convert original physical nodes into topology nodes considering the state of a switch aiming at the change of given switch information.
The power grid is divided into a transmission grid and a distribution grid. The data acquisition and monitoring configuration of the power transmission network are quite complete, and scheduling personnel can conveniently acquire the topological structure of the power transmission network and can identify topological errors through methods such as state estimation. The power distribution network is usually designed in a closed loop mode and operates in an open loop mode, radiation is kept during normal operation, when faults occur or optimal control is carried out, the section switch and the connection line act, the topological structure of the power distribution network is changed, and the trend direction of partial branches is changed. Under the current distribution automation level, no distribution automation terminal is arranged at the section switch of the distribution network, and after the switches are operated, the remote signaling and remote measuring functions do not exist, so that the network topology stored in the system cannot be updated in time due to the manual inspection and report, and the safe and economic operation of the distribution network is influenced. Meanwhile, with the massive access of the distributed power supply, the traditional one-way power flow is changed into two-way interactive power flow, and if the power flow direction cannot be determined, the misoperation of the relay protection device is easily caused. In recent years, the economic benefit of a power grid company is seriously affected by obtaining an accurate topological structure by additionally installing measuring equipment or investing more labor cost, so that the topological identification of a power distribution network is paid more and more attention by researchers.
The topology identification method of the power distribution network mainly has two categories. The first type is a numerical optimization method based on the network parameters and the structure of the power distribution network. For example, a power distribution network topology identification method based on Mixed Integer Quadratic Programming (MIQP) is only applicable to radial power distribution networks by taking the weighted square sum of the minimized measurement residuals as an objective function of a topology identification model. For example, a Micro-synchronous Phasor Measurement Unit (μ PMU) is used to obtain multiple sampling values of node injection power, calculate a variance of voltage deviation based on node injection power Measurement, use the variance as a weight of a line, and construct a minimum spanning tree with the minimum variance by using a Kruskal algorithm, where the corresponding structure is an operation topology of the power distribution network, and the search efficiency is low. The second category is data-driven based methods. For example, correlation analysis is performed on a voltage curve measured by the smart meter, and the topological connection relation of the power distribution network is determined by combining the comparison of the voltage amplitudes. For example, a trend vector is constructed by using a plurality of continuous voltage measurements of the distribution feeder, and the trend vector is compared with a pre-constructed trend vector library corresponding to various topology changes to judge the switch with the changed state. For example, a Light Gradient Boosting Machine (LightGBM) is adopted to screen out the most effective measurement features for power distribution network topology identification, a Deep Neural Network (DNN) is adopted to perform power distribution network topology identification, the correlation among the selected features is not considered in the feature selection method, redundant features can be selected, and the super-parameters of the DNN are determined by grid search, so that the search efficiency is low.
Disclosure of Invention
1. The technical problem to be solved is as follows:
aiming at the technical problems, the invention provides the SVM-based power distribution network topology identification method based on artificial fish swarm algorithm optimization, which can reduce the time for identifying the power distribution network topology and improve the identification precision.
2. The technical scheme is as follows:
a power distribution network topology identification method based on SVM optimized by artificial fish swarm algorithm is characterized in that: the method comprises the following steps:
the method comprises the following steps: collecting section voltage amplitude measurement data of various load levels of observation nodes under different topological structures and corresponding topological labels by using an SCADA system, and carrying out standardized preprocessing; and obtaining a training data set after standardized preprocessing.
Step two: establishing a power distribution network topology identification model of an SVM (support vector machine) based on artificial fish swarm algorithm optimization; the method specifically comprises the following steps:
step 21: initializing an artificial fish school, and setting an artificial fish Visual field Visual, a Step length parameter Step, a maximum foraging trial number try _ number, a crowding factor delta, a maximum iteration number MAXGEN and a billboard value number;
step 22: respectively taking the preprocessed node voltage data as input and output of the SVM, selecting a punishment factor C and a kernel function parameter sigma of the SVM model as parameters to be optimized, and taking a root mean square error of training data as a fitness target function of a fish swarm algorithm;
step 23: each artificial fish self-adaptively adjusts the step length to execute the clustering behavior and the rear-end collision behavior, compares the behavior results and judges whether clustering or rear-end collision or visual field adjustment is carried out for foraging;
step 24: after one round, calculating the adaptive value of each artificial fish, and storing the optimal value in the bulletin board compared with the bulletin board;
step 25: judging whether the maximum iteration time termination condition or the set elimination mechanism termination condition is met, if so, outputting an optimal parameter value, otherwise, returning to the step 23;
step 26: after the optimization is finished, the kernel function parameters and the punishment parameters which are output optimally are used as the optimal parameters of the SVM, namely, a power distribution network topology identification model of the SVM based on the artificial fish swarm optimization is established;
step three: and acquiring section voltage amplitude measurement data of the observation node from the monitoring node, and performing standardized preprocessing.
Step four: and (4) substituting the data obtained in the third step into a power distribution network topology identification model of the SVM based on the artificial fish swarm algorithm optimization to obtain a circuit topology structure of the observation node.
Further, the normalization pretreatment in the step one is normalization treatment, and is specifically treated by adopting a formula (1);
in the formula (1), ViAnd Vi normVoltage amplitudes before and after normalization of node i, V, respectivelyi maxAnd Vi minThe maximum value and the minimum value of the voltage amplitude of the node i in the training data set are respectively.
Further, in step 22, the kernel function parameter σ of the SVM model adopts the kernel function determined according to equation (2):
ψ(hi,hj)＝exp(-σ||hi-hj||2) (2)
(2) in the formula, hi is a sample corresponding to the node i;
the fitness objective function of the fish swarm algorithm is as follows:
(3) wherein n is the sample number of the node i, yrThe output value of the SVM for the r-th sample,
is the actual value of the r-th sample, fRMSEThe root mean square error of the SVM output and the min.
3. Has the advantages that:
according to the scheme, the SCADA is utilized to collect section voltage amplitude measurement data of various load levels under different topological structures and corresponding topological labels to form a training data set. And then, carrying out normalization processing on the training data set, simultaneously carrying out feature selection and SVM parameter optimization by using AFSA, screening out partial node voltage amplitude measurement which is most effective for power distribution network topology identification, forming an optimal feature subset by the node voltage amplitude measurement, and constructing an optimal topology identification model by the optimized SVM parameter. And inputting the section voltage amplitude measurement data of the observation point to be identified, namely realizing the topology identification of the observation point.
Drawings
FIG. 1 is an overall flow chart of a power distribution network topology identification method based on SVM optimized by artificial fish swarm algorithm;
FIG. 2 is a flow chart of establishing an SVM power distribution network topology identification model based on artificial fish swarm algorithm optimization;
fig. 3 is a schematic diagram of an artificial fish model.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings.
Support Vector Machines (SVMs) are well known as an effective data analysis and pattern recognition technique. Unlike conventional statistical theory, SVM solves the classification and regression problems using Vapnik-Chervonenkis dimension theory and the structural risk minimization principle. The basic concept of SVM is to create an optimal hyperplane by maximizing the separation between support vectors. A kernel function is introduced in the solving process. The kernel function is a linear function, a polynomial function, a Sigmoid function, a gaussian function, etc., wherein the gaussian kernel function is most commonly used because it only needs to determine one parameter and has a good classification capability for non-linear problems. Therefore, a gaussian kernel is used as follows:
ψ(hi,hj)＝exp(-σ||hi-hj||2)
in the formula: σ denotes a kernel function parameter. In addition to the kernel function parameters, for the nonlinear classification problem, a penalty parameter C is required for trading off structural and empirical risks. The classification performance of SVM is significantly affected by the kernel function parameter and the penalty parameter C, and therefore needs to be optimized.
Artificial Fish Swarm Algorithm optimization (AFSA) optimizes by a bottom-up optimization mode and realizes the search of the optimal solution of the problem by individual competition and cooperation among populations.
In fig. 3, the current position of an artificial fish is denoted as X (X ═ X)1,x2,x33xn) Visual length of which is Visual, maximum distance of action per time is Step, Xi(i-1, 2,33) represents other artificial fish. Human beingThe worker fish randomly searches in the visual field range,
indicating the position of the artificial fish viewpoint at a certain moment, if VnextIs greater than the food concentration at the X position, the artificial fish moves to V next stepnextIs moved in the vector direction, and the position after the movement is marked as Xnext。VnextAnd XnextThe calculation formulas (3) and (4). Wherein r is [ -1,1 [ ]]Random number of intervals.
The artificial fish swarm algorithm mainly comprises 4 actions of foraging, herding, rear-end collision and random. The parameters of the artificial fish swarm algorithm comprise: the scale N of the artificial fish school, the Visual field perception distance Visual of the artificial fish school, the Step length Step of the artificial fish, the crowding factor delta and the trial times try _ number.
As shown in the attached figure 1, the method for identifying the power distribution network topology based on the SVM optimized by the artificial fish swarm algorithm is characterized in that: the method comprises the following steps:
the method comprises the following steps: collecting section voltage amplitude measurement data of various load levels of observation nodes under different topological structures and corresponding topological labels by using an SCADA system, and carrying out standardized preprocessing; and obtaining a training data set after standardized preprocessing.
Step two: establishing a power distribution network topology identification model of an SVM (support vector machine) based on artificial fish swarm algorithm optimization; the method specifically comprises the following steps:
step 21: initializing an artificial fish school, and setting an artificial fish Visual field Visual, a Step length parameter Step, a maximum foraging trial number try _ number, a crowding factor delta, a maximum iteration number MAXGEN and a billboard value number;
step 22: respectively taking the preprocessed node voltage data as input and output of the SVM, selecting a punishment factor C and a kernel function parameter sigma of the SVM model as parameters to be optimized, and taking a root mean square error of training data as a fitness target function of a fish swarm algorithm;
step 23: each artificial fish self-adaptively adjusts the step length to execute the clustering behavior and the rear-end collision behavior, compares the behavior results and judges whether clustering or rear-end collision or visual field adjustment is carried out for foraging;
step 24: after one round, calculating the adaptive value of each artificial fish, and storing the optimal value in the bulletin board compared with the bulletin board;
step 25: judging whether the maximum iteration time termination condition or the set elimination mechanism termination condition is met, if so, outputting an optimal parameter value, otherwise, returning to the step 23;
step 26: after the optimization is finished, the kernel function parameters and the punishment parameters which are output optimally are used as the optimal parameters of the SVM, namely, a power distribution network topology identification model of the SVM based on the artificial fish swarm optimization is established;
step three: and acquiring section voltage amplitude measurement data of the observation node from the monitoring node, and performing standardized preprocessing.
Step four: and (4) substituting the data obtained in the third step into a power distribution network topology identification model of the SVM based on the artificial fish swarm algorithm optimization to obtain a circuit topology structure of the observation node.
Further, the normalization pretreatment in the step one is normalization treatment, and is specifically treated by adopting a formula (1);
in the formula (1), ViAnd Vi normVoltage amplitudes before and after normalization of node i, V, respectivelyi maxAnd Vi minThe maximum value and the minimum value of the voltage amplitude of the node i in the training data set are respectively.
Further, in step 22, the kernel function parameter σ of the SVM model adopts the kernel function determined according to equation (2):
ψ(hi,hj)＝exp(-σ||hi-hj||2) (2)
(2) in the formula, hi is a sample corresponding to the node i;
the fitness objective function of the fish swarm algorithm is as follows:
(3) wherein n is the sample number of the node i, yrThe output value of the SVM for the r-th sample,
is the actual value of the r-th sample, fRMSEThe root mean square error of the SVM output and the min.
Although the present invention has been described with reference to the preferred embodiments, it should be understood that various changes and modifications can be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (3)
1. A power distribution network topology identification method based on SVM optimized by artificial fish swarm algorithm is characterized in that: the method comprises the following steps:
the method comprises the following steps: collecting section voltage amplitude measurement data of various load levels of observation nodes under different topological structures and corresponding topological labels by using an SCADA system, and carrying out standardized preprocessing; obtaining a training data set after standardized preprocessing;
step two: establishing a power distribution network topology identification model of an SVM (support vector machine) based on artificial fish swarm algorithm optimization; the method specifically comprises the following steps:
step 21: initializing an artificial fish school, and setting an artificial fish Visual field Visual, a Step length parameter Step, a maximum foraging trial number try _ number, a crowding factor delta, a maximum iteration number MAXGEN and a billboard value number;
step 22: respectively taking the preprocessed node voltage data as input and output of the SVM, selecting a punishment factor C and a kernel function parameter sigma of the SVM model as parameters to be optimized, and taking a root mean square error of training data as a fitness target function of a fish swarm algorithm;
step 23: each artificial fish self-adaptively adjusts the step length to execute the clustering behavior and the rear-end collision behavior, compares the behavior results and judges whether clustering or rear-end collision or visual field adjustment is carried out for foraging;
step 24: after one round, calculating the adaptive value of each artificial fish, and storing the optimal value in the bulletin board compared with the bulletin board;
step 25: judging whether the maximum iteration time termination condition or the set elimination mechanism termination condition is met, if so, outputting an optimal parameter value, otherwise, returning to the step 23;
step 26: after the optimization is finished, the kernel function parameters and the punishment parameters which are output optimally are used as the optimal parameters of the SVM, namely, a power distribution network topology identification model of the SVM based on the artificial fish swarm optimization is established;
step three: acquiring section voltage amplitude measurement data of an observation node from the monitoring node, and performing standardized preprocessing;
step four: and (4) substituting the data obtained in the third step into a power distribution network topology identification model of the SVM based on the artificial fish swarm algorithm optimization to obtain a circuit topology structure of the observation node.
2. The method for identifying the power distribution network topology based on the SVM optimized by the artificial fish swarm algorithm according to claim 1, characterized in that: the standardization pretreatment in the step one is normalization treatment, and is specifically treated by adopting a formula (1);
in the formula (1), ViAnd Vi normVoltage amplitudes before and after normalization of node i, V, respectivelyi maxAnd Vi minThe maximum value and the minimum value of the voltage amplitude of the node i in the training data set are respectively.
3. The method for identifying the power distribution network topology based on the SVM optimized by the artificial fish swarm algorithm according to claim 1, characterized in that: in step 22, the kernel function parameter σ of the SVM model adopts the kernel function determined according to the formula (2):
ψ(hi,hj)＝exp(-σ||hi-hj||2) (2)
(2) in the formula, hi is a sample corresponding to the node i;
the fitness objective function of the fish swarm algorithm is as follows:
(3) wherein n is the sample number of the node i, yrThe output value of the SVM for the r-th sample,
is the actual value of the r-th sample, fRMSEThe root mean square error of the SVM output and the min.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111208168.8A CN113901621A (en) | 2021-10-18 | 2021-10-18 | SVM power distribution network topology identification method based on artificial fish swarm algorithm optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111208168.8A CN113901621A (en) | 2021-10-18 | 2021-10-18 | SVM power distribution network topology identification method based on artificial fish swarm algorithm optimization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113901621A true CN113901621A (en) | 2022-01-07 |
Family
ID=79192514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111208168.8A Withdrawn CN113901621A (en) | 2021-10-18 | 2021-10-18 | SVM power distribution network topology identification method based on artificial fish swarm algorithm optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113901621A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113688488A (en) * | 2021-08-17 | 2021-11-23 | 南京信息工程大学 | Power grid line planning method based on improved artificial fish swarm algorithm |
| CN115224728A (en) * | 2022-07-19 | 2022-10-21 | 贵州大学 | Wind power generation system model identification method and system |
-
2021
- 2021-10-18 CN CN202111208168.8A patent/CN113901621A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113688488A (en) * | 2021-08-17 | 2021-11-23 | 南京信息工程大学 | Power grid line planning method based on improved artificial fish swarm algorithm |
| CN113688488B (en) * | 2021-08-17 | 2023-05-30 | 南京信息工程大学 | Power grid line planning method based on improved artificial fish swarm algorithm |
| CN115224728A (en) * | 2022-07-19 | 2022-10-21 | 贵州大学 | Wind power generation system model identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113901621A (en) | SVM power distribution network topology identification method based on artificial fish swarm algorithm optimization | |
| CN102183621A (en) | Aquaculture dissolved oxygen concentration online forecasting method and system | |
| CN109670676A (en) | Distributing net platform region method for prewarning risk and system based on Support Vector data description | |
| CN109490814A (en) | Metering automation terminal fault diagnostic method based on deep learning and Support Vector data description | |
| CN111754020A (en) | Intelligent power plant equipment inspection system and method based on data analysis | |
| CN110321940A (en) | The feature extraction of aircraft telemetry and classification method and device | |
| CN111880044A (en) | Online fault positioning method for power distribution network with distributed power supply | |
| CN110659672B (en) | Method and device for predicting step-by-step uncertainty of output of wind turbine generator | |
| CN101738998A (en) | System and method for monitoring industrial process based on local discriminatory analysis | |
| CN113901623A (en) | SVM power distribution network topology identification method based on cuckoo search algorithm | |
| CN114386538A (en) | Method for marking wave band characteristics of KPI (Key performance indicator) curve of monitoring index | |
| CN113901622A (en) | Genetic algorithm optimization-based SVM power distribution network topology identification method | |
| CN110096723B (en) | High-voltage switch cabinet insulation state analysis method based on operation and maintenance detection big data | |
| Dai et al. | Fault diagnosis of data‐driven photovoltaic power generation system based on deep reinforcement learning | |
| CN112836876B (en) | Power distribution network line load prediction method based on deep learning | |
| CN117674421A (en) | Digital twin power grid data transmission system | |
| CN111965442A (en) | Energy internet fault diagnosis method and device under digital twin environment | |
| CN116125199A (en) | Low-voltage distribution network line fault early warning method and system | |
| CN113762591B (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM countermeasure learning | |
| CN115864644A (en) | Relay protection device state evaluation method, system, equipment and medium | |
| Zheng et al. | Application based on artificial intelligence in substation operation and maintenance management | |
| Zhang et al. | Transfer learning featured combining short-term load forecast with small-sample conditions | |
| CN114066068A (en) | Short-term power load prediction method, device, equipment and storage medium | |
| CN113935413A (en) | Distribution network wave recording file waveform identification method based on convolutional neural network | |
| CN117592870B (en) | Comprehensive analysis system based on water environment monitoring information |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220107 |
|
| WW01 | Invention patent application withdrawn after publication |