CN114705947A - Island detection model training method, device, equipment and medium - Google Patents
Island detection model training method, device, equipment and medium Download PDFInfo
- Publication number
- CN114705947A CN114705947A CN202210277435.5A CN202210277435A CN114705947A CN 114705947 A CN114705947 A CN 114705947A CN 202210277435 A CN202210277435 A CN 202210277435A CN 114705947 A CN114705947 A CN 114705947A
- Authority
- CN
- China
- Prior art keywords
- detection model
- support vector
- vector machine
- island
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 174
- 238000012549 training Methods 0.000 title claims abstract description 119
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000012706 support-vector machine Methods 0.000 claims abstract description 125
- 238000004088 simulation Methods 0.000 claims abstract description 56
- 238000012360 testing method Methods 0.000 claims description 66
- 238000004590 computer program Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 11
- 230000006735 deficit Effects 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000005070 sampling Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 238000010248 power generation Methods 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000002347 injection Methods 0.000 description 2
- 239000007924 injection Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/381—Dispersed generators
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/388—Islanding, i.e. disconnection of local power supply from the network
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses an island detection model training method, device, equipment and medium, wherein the method comprises the following steps: acquiring three-phase instantaneous voltages in N states in a simulation island power grid and in M states in a simulation non-island power grid; calculating the root mean square value of each group of three-phase instantaneous voltages according to each group of three-phase instantaneous voltages to form a data set consisting of the root mean square values of the three-phase instantaneous voltages, wherein the data set comprises a training set; training an island detection model based on a support vector machine by taking a training set as input of the island detection model based on the support vector machine to obtain model parameters of the island detection model based on the support vector machine; and obtaining an island detection model based on the support vector machine based on the model parameters. Therefore, by calculating the root mean square value of each group of three-phase instantaneous voltages, the single voltage feature in each group of three-phase instantaneous voltages is amplified, and therefore the island detection model based on the support vector machine is higher in accuracy.
Description
Technical Field
The invention relates to the technical field of power equipment, in particular to an island detection model training method, device, equipment and medium.
Background
Whether the distributed power supply can quickly and accurately judge the self island operation state is a necessary condition for ensuring the safety of people and equipment in the operation process of the micro-grid, the accuracy and the detection efficiency of island detection are improved, the distributed power supply, the distribution network main station and the substation system can accurately judge the change of the operation mode according to a preset strategy, the potential safety hazards of the people and the equipment caused by unknown island operation state can be eliminated in time, and the reliable power supply of the power grid is ensured.
The existing island detection method comprises active injection and a passive threshold, wherein the active injection can bring the influence of electric energy quality deterioration to a power grid, the detection accuracy and the detection time of the passive threshold are relatively poor, the island state of a distributed power supply cannot be detected timely and accurately, and the defects of large detection blind area, long detection time and the like exist.
Disclosure of Invention
The invention provides an island detection model training method, device, equipment and medium, which are used for solving the problems of long island detection time, large detection blind area, low detection accuracy and the like in a power grid in the prior art.
In order to solve the above problem, an embodiment of a first aspect of the present invention provides an islanding detection model training method based on a support vector machine, including the following steps:
acquiring three-phase instantaneous voltages in N states in a simulation island power grid and in M states in a simulation non-island power grid, wherein N and M are positive integers;
calculating the root mean square value of each group of the three-phase instantaneous voltages according to each group of the three-phase instantaneous voltages to form a data set consisting of the root mean square values of the three-phase instantaneous voltages, wherein the data set comprises a training set;
taking the training set as the input of an isolated island detection model based on a support vector machine, training the isolated island detection model based on the support vector machine, and obtaining model parameters of the isolated island detection model based on the support vector machine;
and obtaining the support vector machine-based island detection model based on the model parameters.
According to one embodiment of the invention, the data set further comprises a test set;
after the islanding detection model based on the support vector machine is obtained, the method further comprises the following steps:
and taking the test set as the input of the support vector machine-based island detection model, and testing the support vector machine-based island detection model to obtain a test score.
According to an embodiment of the invention, after forming the data set consisting of the root mean square values of the three-phase instantaneous voltages, the following steps are further included:
dividing the data set into a plurality of parts, wherein one part is used as the test set, and the rest parts are used as the training set;
taking the 1 st part as the test set and the 2 nd to the last part as the training set, so as to obtain a first model parameter and a first test score of the support vector machine-based island detection model;
taking the I part as the test set, and taking the 1 st part, the.. 1 st part, the. +1 st part to the last part as the training set, and obtaining an I model parameter and an I test score of the support vector machine-based island detection model;
by analogy, the last part is used as the test set, the 1 st to the second last part is used as the training set, and the last model parameter and the last test score of the support vector machine-based island detection model can be obtained;
and comparing the first test score with the last test score, and taking the model parameter corresponding to the highest test score as the final model parameter of the support vector machine-based island detection model.
According to an embodiment of the invention, the N states in the simulation islanded grid include:
any two groups of numerical values in the active power mismatch condition and the reactive power mismatch condition are combined to form N states.
According to one embodiment of the invention, the active power mismatch condition satisfies the following condition:
where Δ P represents the active power deficit, PDGRepresenting distributed generation active power output;
and, the reactive power mismatch condition satisfies the following condition:
where Δ Q represents the reactive power deficit, QDGRepresenting distributed generation reactive power output.
According to an embodiment of the invention, the simulating M states in the non-islanded grid includes:
the total value of the simulation times of one or more of the normal operation condition, the fault condition, the load switching condition or the capacitance switching condition in the non-isolated island power grid is M states formed by M.
According to one embodiment of the invention, the fault condition comprises: one or more of a single-phase ground fault condition, a phase-to-phase fault condition, a two-phase ground fault condition, a three-phase fault condition, or a three-phase ground fault condition;
wherein, in the trouble process, the resistance of trouble transition resistance satisfies the condition: rf＝1～2kΩ。
According to one embodiment of the invention, when the value of the total simulation times of multiple situations in a normal operation situation, a fault situation, a load switching situation or a capacitance switching situation in a non-island power grid is M states formed by M, the simulation times of each situation in the multiple situations are divided into M.
According to one embodiment of the invention, N of the N states in the simulated islanded grid is equal to M of the M states in the simulated non-islanded grid.
According to an embodiment of the present invention, after obtaining the islanding detection model based on the support vector machine, the method further includes:
placing the support vector machine-based island detection model in an actual operation working condition for island detection;
judging whether the actual operation working condition is in an island state or not according to a preset frequency threshold;
when the actual operation working condition is judged to be in an island state according to the preset frequency threshold value, and the result output by the island detection model based on the support vector machine is still in a non-island state, acquiring three-phase instantaneous voltage within preset time before a judgment point for judging that the actual operation working condition is in the island state according to the preset frequency threshold value;
calculating the root mean square value of the three-phase instantaneous voltage according to each group of three-phase instantaneous voltages to form a correction training set consisting of the root mean square values of the three-phase instantaneous voltages;
updating the training set according to the corrected training set, and retraining the support vector machine-based island detection model to obtain the updating parameters of the support vector machine-based island detection model;
and obtaining the corrected island detection model based on the support vector machine according to the updated parameters.
In order to solve the above problem, an embodiment of a second aspect of the present invention provides an islanding detection model training apparatus based on a support vector machine, including:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring three-phase instantaneous voltages in N states in a simulation island power grid and in M states in a simulation non-island power grid, wherein N and M are positive integers;
the data set forming module is used for calculating the root mean square value of each group of three-phase instantaneous voltages according to each group of three-phase instantaneous voltages to form a data set consisting of the root mean square values of the three-phase instantaneous voltages, wherein the data set comprises a training set;
the training module is used for taking the training set as the input of an isolated island detection model based on a support vector machine, training the isolated island detection model based on the support vector machine and obtaining model parameters of the isolated island detection model based on the support vector machine;
and the model acquisition module is used for acquiring the support vector machine-based island detection model based on the model parameters.
To solve the above problem, a third aspect of the present invention provides an electronic apparatus, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the islanding detection model training method based on support vector machine according to any of the embodiments of the present invention.
To solve the above problem, a fourth aspect of the present invention provides a computer-readable storage medium storing computer instructions for causing a processor to implement the islanding detection model training method based on a support vector machine according to any embodiment of the present invention when the computer instructions are executed.
The island detection model training method provided by the embodiment of the invention comprises the following steps: acquiring three-phase instantaneous voltages in N states in a simulation island power grid and in M states in a simulation non-island power grid, wherein N and M are positive integers; calculating the root mean square value of each group of three-phase instantaneous voltages according to each group of three-phase instantaneous voltages to form a data set consisting of the root mean square values of the three-phase instantaneous voltages, wherein the data set comprises a training set; training an island detection model based on a support vector machine by taking a training set as input of the island detection model based on the support vector machine to obtain model parameters of the island detection model based on the support vector machine; and obtaining an island detection model based on the support vector machine based on the model parameters. Therefore, by sampling the three-phase instantaneous voltages of the simulation island power grid and the simulation non-island power grid in different states and calculating the root mean square value of each group of three-phase instantaneous voltages, the single voltage characteristic in each group of three-phase instantaneous voltages is amplified, and the accuracy of the support vector machine-based island detection model trained by the training set consisting of the root mean square values of the three-phase instantaneous voltages is higher. In addition, the island detection model based on the support vector machine has the advantages of shorter detection time, small detection blind area and higher detection accuracy.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of an island detection model training method proposed by an embodiment of the present invention;
FIG. 2 is a flow chart of a method for training an island detection model according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method for training an island detection model according to another embodiment of the present invention;
FIG. 4 is a flow chart of a method for training an island detection model according to another embodiment of the present invention;
FIG. 5 is a schematic diagram of frequency acquisition in an island detection model training method according to an embodiment of the present invention;
FIG. 6 is a block diagram of an islanding detection model training apparatus according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device implementing the islanding detection model training method according to the embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Fig. 1 is a flowchart of an island detection model training method according to an embodiment of the present invention. As shown in fig. 1, the training method includes the following steps:
s101, three-phase instantaneous voltages in N states in a simulation island power grid and in M states in a simulation non-island power grid are obtained, wherein N and M are positive integers;
it can be understood that many hundreds or even thousands of states exist under the simulated island power grid, N states are simulated under the island power grid, and also many hundreds or even thousands of states exist under the simulated non-island power grid, and M states are simulated under the non-island power grid. The simulation software may be RTDS simulation software (Real Time Digital Simulator), that is, islanded power grids and non-islanded power grids in different states may be set up through RTDS simulation.
The isolated island power grid is a local power grid constructed by mutually combining multiple groups of small power generation systems, the power generation systems and loads of the power generation systems form an isolated grid system capable of operating by self, isolated islands are not enough due to limitation of various frequency modulation means and reactive compensation control means, static stability and dynamic stability are poor, power generation adjustment can be recovered after a long time when active imbalance occurs, even frequency breakdown and voltage breakdown phenomena occur, therefore, the isolated island power grid is generally used in a grid-connected mode with other power grids, namely, a non-isolated island power grid is formed, when the non-isolated island power grid operates, whether the isolated island phenomenon occurs needs to be detected in real time, so that workers can overhaul the power grid in time, and danger caused by the formation of the isolated island power grid is avoided.
Because when the island electric wire netting appeared, the three-phase instantaneous voltage of whole electric wire netting can change, and then, trains island detection model through acquireing three-phase instantaneous voltage.
The method comprises the steps of obtaining three-phase instantaneous voltages in N states under a simulation island power grid, namely obtaining N groups of three-phase instantaneous voltages; and obtaining three-phase instantaneous voltages of M states under the simulation non-island power grid, namely obtaining M groups of three-phase instantaneous voltages. The values of N and M may be set according to actual conditions (server performance for training, accuracy of the desired model, etc.), and the present invention is not limited thereto.
S102, calculating the root mean square value of each group of three-phase instantaneous voltages according to each group of three-phase instantaneous voltages to form a data set consisting of the root mean square values of the three-phase instantaneous voltages, wherein the data set comprises a training set;
note that, in step S101, the root mean square value of each of the N groups of three-phase instantaneous voltages and the M groups of three-phase instantaneous voltages is calculated, for example, the three-phase instantaneous voltages are denoted as ua、ub、ucThen the root mean square value is
Simulating the obtained data sets in the N states and the M states, and performingAfter the quantity conversion, can be recorded as phi ═ x1,...,xi,...,xn)TWhere i ∈ [1, n ]]Representing simulation serial number, xiAnd representing the root mean square value of the three-phase instantaneous voltage collected in the simulation process, wherein the three-phase instantaneous voltage can be sampled once per simulation, N is the number of times of the collected three-phase instantaneous voltage, and N can be the sum of N and M. It is also possible to simulate that the total duration of one sampling is preferably 40 ms and the sampling frequency is preferably 500Hz, which increases the number of data sets. It can be understood that after the three-phase instantaneous voltage is processed by the root mean square, one value of the root mean square can reflect the three-phase instantaneous voltage at the same time, and further the change of the three-phase instantaneous voltage and the single-phase voltage is amplified, so that the accuracy of the trained model is higher.
S103, taking the training set as the input of an island detection model based on a support vector machine, training the island detection model based on the support vector machine, and obtaining model parameters of the island detection model based on the support vector machine;
preferably, the support vector machine-based island detection model explicit expression is as follows:
where m represents the number of support vectors, ksCoefficients representing the corresponding support vector, γ ∈ (0, + ∞) is the kernel parameter of the support vector machine, xiRepresenting the input vector, xsRepresenting the support vector and b representing the hyperplane bias.
Therefore, the training set obtained in the step S102 is placed into an island detection model based on a support vector machine to train the model, and k is finally obtaineds、xsAnd b model parameters.
And S104, obtaining an island detection model based on the support vector machine based on the model parameters.
According to one embodiment of the invention, as shown in FIG. 2, the data set further includes a test set;
after obtaining the islanding detection model based on the support vector machine, the method further comprises the following steps:
and S105, taking the test set as the input of the support vector machine-based island detection model, and testing the support vector machine-based island detection model to obtain a test score. That is, the islanding detection model is tested through the test set to determine whether the parameters obtained in step S103 are optimal.
Therefore, through the steps S101 to S105, an island detection model based on a support vector machine is obtained through training, the model can be placed in an actual working condition for use, the root mean square of the three-phase instantaneous voltage is used as input in the actual use process, the model can output whether the current working condition is in an island operation state, the frequency for collecting the three-phase instantaneous voltage is preferably 500Hz (shown in figure 5) in the actual use process, the time for judging whether the three-phase instantaneous voltage is in an island is greatly shortened, the detection time is shortened, the root mean square of the three-phase instantaneous voltage is used as input, the detection accuracy is higher, and the detection accuracy is favorably improved.
According to an embodiment of the present invention, as shown in fig. 3, after forming a data set consisting of root mean square values of three-phase instantaneous voltages, the following steps are further included:
s201, dividing the data set into a plurality of parts, wherein one part is used as a test set, and the rest parts are used as training sets;
for example, the data set may be divided equally into three portions, a first portion, a second portion, and a third portion;
s202, taking the 1 st part as a test set and the 2 nd to the last part as a training set, and obtaining a first model parameter and a first test score of the island detection model based on the support vector machine;
that is, the second part and the third part are used as training sets to obtain the first model parameters, and the first part is used as a test set to obtain the first test score.
S203, taking the I part as a test set, and taking the 1 st, the I +1 st to the last part as a training set, and obtaining an I model parameter and an I test score of the island detection model based on the support vector machine, wherein I is a positive integer;
and obtaining a second test score by taking the first part and the third part as training sets to obtain second model parameters and taking the second part as a test set.
S204, by analogy, the last part is used as a test set, the 1 st to the second last part is used as a training set, and the last model parameter and the last test score of the island detection model based on the support vector machine can be obtained;
that is, the first part and the second part are used as training sets to obtain third model parameters, and the third part is used as a test set to obtain a third test score.
And S205, comparing the first test score with the last test score, and taking the model parameter corresponding to the highest test score as the final model parameter of the support vector machine-based island detection model.
And selecting the model parameters trained by the training set corresponding to the test set with the highest test score as final model parameters of the support vector machine-based island detection model, and judging the actual working conditions by using the model in actual use. Therefore, when the data set amount is small, the training times can be increased by the method, and further, a better model can be finally obtained.
According to one embodiment of the invention, simulating N states in an island grid comprises:
and any two groups of numerical values in the active power mismatch condition and the reactive power mismatch condition are combined to form N states.
Preferably, the active power mismatch condition satisfies the following condition:
where Δ P represents the active power deficit, PDGRepresenting distributed generation active power output;
and, the reactive power mismatch condition satisfies the following condition:
where Δ Q represents the reactive power deficit, QDGRepresenting distributed generation reactive power output.
It can be understood that the values of the active power mismatch and the reactive power mismatch may be the same, such as-0.1, 0, 0.1, and the like, or may be different, such as the active power mismatch is 0, the reactive power mismatch is 0.1, or the active power mismatch is 0.1, and the reactive power mismatch is 0, in which case, the value of N may be determined according to the performance parameters of the training server itself and the simulation difficulty level, the values of the active power mismatch and the reactive power mismatch are all within the above-mentioned limited range, the larger the value of N, the more the amount of data sets, the better the final trained model.
It should be noted that when the islanding condition is simulated for N times, N three-phase instantaneous voltages can be obtained.
According to one embodiment of the invention, simulating M states in a non-islanded grid comprises:
the total value of the simulation times of one or more of the normal operation condition, the fault condition, the load switching condition or the capacitance switching condition in the non-isolated island power grid is M states formed by M.
It can be understood that a non-isolated island power grid generally has four conditions, namely a normal operation condition, a fault condition, a load switching condition or a capacitance switching condition, and during actual simulation, only one or more conditions can be simulated according to the difficulty of the actual simulation. For example, when only one condition is simulated, the normal operation condition is simulated for M times when the normal operation condition is simulated. When only the fault condition is simulated, the fault condition is simulated for M times. The other two cases are the same, and are not described in detail herein. For example, when two cases, namely a normal operation case and a fault case, are simulated, in the two cases, the number of times of simulation for the two cases, namely the normal operation case and the fault case, should be M times in total. For example, when two cases of the normal operation condition, the fault condition and the load switching condition are simulated, in the three cases, the number of times of simulation for the normal operation condition, the fault condition and the load switching condition should be M times in total. The more cases of simulation, the larger the value setting of M, the larger the amount of data set, and the better the final trained model.
It should be noted that, when the simulation condition is the normal operation condition, the power grid parameters of the normal operation condition may be changed, the simulation times are simulated for M times, and finally M three-phase instantaneous voltages are obtained. For other cases, refer to the above explanations and are not described in detail here.
According to one embodiment of the invention, the fault condition comprises: one or more of a single-phase ground fault condition, a phase-to-phase fault condition, a two-phase ground fault condition, a three-phase fault condition, or a three-phase ground fault condition;
wherein, in the trouble process, the resistance of trouble transition resistance satisfies the condition: rf＝1～2kΩ。
It can be understood that there are five cases of the fault conditions, and one of the five cases may be simulated during simulation, or multiple fault conditions may be simulated, for example, if only the fault condition is simulated, the number of simulated fault conditions is M, and if two of the fault conditions are simulated, the sum of the number of simulated fault conditions is M. For example, when two cases, namely a normal operation case and a fault case (two cases are used for the fault case), are simulated, the number of times of simulation in the three cases should be M times in total.
According to one embodiment of the invention, when the value of the total simulation times of multiple conditions in a normal operation condition, a fault condition, a load switching condition or a capacitance switching condition in a non-isolated island power grid is M states formed by M, the simulation times of each condition in the multiple conditions are divided into M.
That is, for example, when two cases, namely a normal operation case and a fault case, are simulated, in the two cases, the total simulation times should be M times, then the simulation times for the normal operation case should be M/2 times, and the simulation times for the fault case should be M/2 times. If there are two kinds of fault conditions, the simulation times of the normal operation condition should be M/3 times, and the simulation times of the other two kinds of fault conditions should be M/3 times respectively. The finally obtained three-phase instantaneous voltage times are equally divided, so that the obtained data set is more uniformly distributed, and the accuracy of model training is improved.
According to one embodiment of the invention, N of N states in the simulated island power grid is equal to M of M states in the simulated non-island power grid.
That is to say, N is equal to M, and the total number of times of the simulation islanded grid is equal to the total number of times of the simulation non-islanded grid, so that the acquired data set is distributed more uniformly, and the accuracy of model training is improved.
In a word, the more the simulation, the more the three-phase instantaneous voltage is collected, the more accurate the model of final training is, but too many simulation times and the more the three-phase instantaneous voltage is collected, the larger the calculation amount is, the more complicated is, if too little, the model is rough again, it is not accurate enough, and then it is more important to select suitable N and M according to actual conditions, preferably, N is 300 ~ 1000.
According to an embodiment of the present invention, as shown in fig. 4, after obtaining the islanding detection model based on the support vector machine, the method further includes:
s301, placing an island detection model based on a support vector machine in an actual operation working condition for island detection;
when the islanding detection model based on the support vector machine is placed in an actual operation working condition, three-phase instantaneous voltage can be collected at a sampling frequency of 500Hz (shown in figure 5), the root mean square of the three-phase instantaneous voltage is calculated, the model outputs the actual operation working condition state to be an islanding state or a non-islanding state through the root mean square of the three-phase instantaneous voltage, and one of a normal condition, a fault condition, a load switching condition or a capacitance switching condition in the non-islanding state can be output if the model is trained comprehensively.
S302, judging whether the actual operation working condition is in an island state or not according to a preset frequency threshold;
wherein the predetermined frequency threshold may be fsmp＜49.5Hz∨fsmp> 50.5Hz, the frequency of the detection frequency can beIs 0.1Hz, and when the collected frequency is less than 49.5Hz or more than 50.5Hz, the current actual working condition is in an island state.
The order of step S301 and step S302 may not be limited.
S303, when the actual operation working condition is judged to be in an island state according to a preset frequency threshold value and the result output by the island detection model based on the support vector machine is still in a non-island state, acquiring three-phase instantaneous voltage within preset time before a judgment point for judging that the actual operation working condition is in the island state according to the preset frequency threshold value;
it can be understood that when the actual operation condition is judged to be in the island state through the preset frequency threshold, it is shown that the actual operation condition is in the island state at this time, but if the result output by the island detection model based on the support vector machine is still in the non-island state, it is shown that the island detection model obtained by the previous training has a misjudgment and needs to be corrected. At this time, three-phase instantaneous voltages within a preset time before a judgment point for judging that the actual operation condition is in the island state according to a preset frequency threshold are obtained, the preset time can be 1s, for example, if the actual operation condition judged at the current moment is in the island state, 1s is counted from this moment onward, and a plurality of groups of three-phase instantaneous voltages within 1s are stored.
In other embodiments, preferably, the time when the monitored frequency of the sampling point is firstly lower than 49.9Hz or higher than 50.1Hz within 1 second is taken as a starting point, and three-phase voltage instantaneous value data within 60ms after the starting point is stored.
S304, calculating the root mean square value of the three-phase instantaneous voltage according to each group of three-phase instantaneous voltages to form a correction training set consisting of the root mean square values of the three-phase instantaneous voltages;
wherein, the correction training set may be xg，xg＝(rmsu1,...,rmsu30)。
S305, updating the training set according to the corrected training set, and retraining the support vector machine-based island detection model to obtain the updating parameters of the support vector machine-based island detection model;
the previous training set is Φ ═ x1,...,xi,...,xn)TAccording to xg＝(rmsu1,...,rmsu30) To update the training set to phig＝(x1,...,xi,...,xn，xg)T. And further through the updated phigAnd retraining the support vector machine-based island detection model to obtain the updated parameters of the support vector machine-based island detection model, so that the model is corrected.
And S306, obtaining the corrected island detection model based on the support vector machine according to the updated parameters.
Therefore, the island detection model based on the support vector machine after correction is put into the actual working condition again for island detection, and the accuracy rate of the detection model is higher.
After the corrected island detection model based on the support vector machine is obtained, the island detection model can be tested and put into use after being tested.
In summary, the island detection model training method provided by the embodiment of the invention includes the following steps: acquiring three-phase instantaneous voltages in N states in a simulation island power grid and in M states in a simulation non-island power grid, wherein N and M are positive integers; calculating the root mean square value of each group of three-phase instantaneous voltages according to each group of three-phase instantaneous voltages to form a data set consisting of the root mean square values of the three-phase instantaneous voltages, wherein the data set comprises a training set; training an island detection model based on a support vector machine by taking a training set as input of the island detection model based on the support vector machine to obtain model parameters of the island detection model based on the support vector machine; and obtaining an island detection model based on the support vector machine based on the model parameters. From this, through sampling the three-phase instantaneous voltage that emulation isolated island electric wire netting to and emulation non-isolated island electric wire netting are in under different states, and calculate the root mean square value of every group three-phase instantaneous voltage, make the single voltage characteristic in every group three-phase instantaneous voltage amplified, thereby make the island detection model accuracy rate based on support vector machine of the training set training of being constituteed by three-phase instantaneous voltage's root mean square value higher. In addition, the island detection model based on the support vector machine has the advantages of short detection time, small detection blind area and high detection accuracy.
Fig. 6 is a schematic block diagram of an islanding detection model training apparatus according to an embodiment of the present invention. As shown in fig. 6, the apparatus includes:
the acquiring module 101 is configured to acquire three-phase instantaneous voltages in N states in a simulated island power grid and M states in a simulated non-island power grid, where N and M are positive integers;
the data set forming module 102 is configured to calculate a root mean square value of each group of three-phase instantaneous voltages according to each group of three-phase instantaneous voltages, and form a data set composed of the root mean square values of the three-phase instantaneous voltages, where the data set includes a training set;
the training module 103 is configured to train the support vector machine-based islanding detection model by using the training set as an input of the support vector machine-based islanding detection model, and obtain model parameters of the support vector machine-based islanding detection model;
and the model obtaining module 104 is configured to obtain an island detection model based on a support vector machine based on the model parameters.
According to one embodiment of the invention, the data set further comprises a test set; the device also includes:
and the test module is used for taking the test set as the input of the support vector machine-based island detection model, testing the support vector machine-based island detection model and obtaining a test score.
According to an embodiment of the invention, the apparatus further comprises:
the data set dividing module is used for dividing the data set into a plurality of parts, wherein one part is used as a test set, and the rest parts are used as training sets;
the training module is used for taking the 1 st part as a test set and taking the 2 nd to the last part as a training set, and can obtain a first model parameter and a first test score of the island detection model based on the support vector machine;
taking the I part as a test set, and taking the 1 st part, the.. 1 st part, the I +1 st part and the last part as training sets, and obtaining an I model parameter and an I test score of the island detection model based on the support vector machine, wherein I is a positive integer;
by analogy, the last part is used as a test set, the 1 st to the second last part is used as a training set, and the last model parameter and the last test score of the island detection model based on the support vector machine can be obtained;
and the comparison module is used for comparing the first test score with the last test score, and obtaining the model parameter corresponding to the highest test score as the final model parameter of the support vector machine-based island detection model.
According to one embodiment of the invention, simulating N states in an island grid comprises:
and any two groups of numerical values in the active power mismatch condition and the reactive power mismatch condition are combined to form N states.
According to one embodiment of the invention, the active power mismatch condition satisfies the following condition:
where Δ P represents the active power deficit, PDGRepresenting distributed generation active power output;
and, the reactive power mismatch condition satisfies the following condition:
where Δ Q represents the reactive power deficit, QDGRepresenting distributed generation reactive power output.
According to one embodiment of the invention, simulating M states in a non-islanded grid comprises:
the total value of the simulation times of one or more of the normal operation condition, the fault condition, the load switching condition or the capacitance switching condition in the non-isolated island power grid is M states formed by M.
According to one embodiment of the invention, the fault condition comprises: one or more of a single-phase ground fault condition, a phase-to-phase fault condition, a two-phase ground fault condition, a three-phase fault condition, or a three-phase ground fault condition;
wherein, in the trouble process, the resistance of trouble transition resistance satisfies the condition: rf＝1～2kΩ。
According to one embodiment of the invention, when the value of the total simulation times of multiple situations in a normal operation situation, a fault situation, a load switching situation or a capacitance switching situation in a non-island power grid is M states formed by M, the simulation times of each situation in the multiple situations are divided into M.
According to one embodiment of the invention, N of N states in the simulated island power grid is equal to M of M states in the simulated non-island power grid.
According to an embodiment of the invention, the apparatus further comprises:
the model detection module is used for placing an island detection model based on the support vector machine in an actual operation working condition for island detection;
the frequency difference detection module is used for judging whether the actual operation working condition is in an island state or not according to a preset frequency threshold;
the obtaining module is further used for obtaining three-phase instantaneous voltage within preset time before a judging point for judging that the actual operation condition is in the island state according to the preset frequency threshold when the actual operation condition is judged to be in the island state according to the preset frequency threshold and the result output by the island detection model based on the support vector machine is still in a non-island state;
the data set forming module is also used for calculating the root mean square value of the three-phase instantaneous voltage according to each group of three-phase instantaneous voltages to form a correction training set consisting of the root mean square values of the three-phase instantaneous voltages;
the updating and correcting module is used for updating the training set according to the corrected training set and retraining the support vector machine-based island detection model to obtain the updating parameters of the support vector machine-based island detection model;
the model obtaining module is further used for obtaining the corrected island detection model based on the support vector machine according to the updated parameters.
The training device for the island detection model provided by the embodiment of the invention can execute the training method for the island detection model provided by any embodiment of the invention, has the corresponding functional modules and beneficial effects of the execution method, and is not repeated here.
FIG. 7 shows a schematic diagram of an electronic device that may be used to implement an embodiment of the invention.
The electronic device 10 includes:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform a method for support vector machine based islanding detection model training according to any of the embodiments of the present invention.
In an embodiment of a fourth aspect of the present invention, a computer-readable storage medium is provided, where computer instructions are stored, and the computer instructions are configured to, when executed, enable a processor to implement the islanding detection model training method based on a support vector machine according to any embodiment of the present invention.
Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 7, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM)12, a Random Access Memory (RAM)13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM)12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as a support vector machine-based islanding detection model training method.
In some embodiments, the support vector machine-based islanding detection model training method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the above described support vector machine based islanding detection model training method may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the support vector machine-based islanding detection model training method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), blockchain networks, and the Internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (13)
1. An island detection model training method based on a support vector machine is characterized by comprising the following steps:
acquiring three-phase instantaneous voltages in N states in a simulation island power grid and in M states in a simulation non-island power grid, wherein N and M are positive integers;
calculating the root mean square value of each group of the three-phase instantaneous voltages according to each group of the three-phase instantaneous voltages to form a data set consisting of the root mean square values of the three-phase instantaneous voltages, wherein the data set comprises a training set;
taking the training set as the input of an isolated island detection model based on a support vector machine, training the isolated island detection model based on the support vector machine, and obtaining model parameters of the isolated island detection model based on the support vector machine;
and obtaining the support vector machine-based island detection model based on the model parameters.
2. The method for islanding detection model training based on support vector machine according to claim 1, wherein the data set further comprises a test set;
after the islanding detection model based on the support vector machine is obtained, the method further comprises the following steps:
and taking the test set as the input of the support vector machine-based island detection model, and testing the support vector machine-based island detection model to obtain a test score.
3. A support vector machine-based islanding detection model training method according to claim 2, characterized by further comprising the following steps after forming a data set consisting of root mean square values of the three-phase instantaneous voltages:
dividing the data set into a plurality of parts, wherein one part is used as the test set, and the rest parts are used as the training set;
taking the 1 st part as the test set and the 2 nd to the last part as the training set, so as to obtain a first model parameter and a first test score of the support vector machine-based island detection model;
taking the I part as the test set, and taking the 1 st, the.. 1, the.. 1 +1 to the last part as the training set, and obtaining an I model parameter and an I test score of the support vector machine-based island detection model, wherein I is a positive integer;
by analogy, the last part is used as the test set, the 1 st to the second last part is used as the training set, and the last model parameter and the last test score of the support vector machine-based island detection model can be obtained;
and comparing the first test score with the last test score, and taking the model parameter corresponding to the highest test score as the final model parameter of the support vector machine-based island detection model.
4. The islanding detection model training method based on the support vector machine according to claim 1, wherein the simulating N states in the islanding grid comprises:
and any two groups of numerical values in the active power mismatch condition and the reactive power mismatch condition are combined to form N states.
5. The islanding detection model training method based on support vector machine according to claim 4,
the active power mismatch condition satisfies the following condition:
where Δ P represents the active power deficit, PDGRepresenting distributed generation active power output;
and, the reactive power mismatch condition satisfies the following condition:
where Δ Q represents the reactive power deficit, QDGRepresenting distributed generation reactive power output.
6. The islanding detection model training method based on the support vector machine according to claim 1, wherein simulating M states in a non-islanding power grid comprises:
the total value of the simulation times of one or more of the normal operation condition, the fault condition, the load switching condition or the capacitance switching condition in the non-isolated island power grid is M states formed by M.
7. The islanding detection model training method based on support vector machine according to claim 6,
the fault condition includes: one or more of a single-phase ground fault condition, a phase-to-phase fault condition, a two-phase ground fault condition, a three-phase fault condition, or a three-phase ground fault condition;
wherein, in the trouble process, the resistance of trouble transition resistance satisfies the condition: rf＝1～2kΩ。
8. The islanding detection model training method based on support vector machine according to claim 6,
when the value of the total number of simulation times of multiple situations in a normal operation situation, a fault situation, a load switching situation or a capacitance switching situation in a non-isolated island power grid is M states formed by M, the number of simulation times of each situation in the multiple situations is divided into M equally.
9. The islanding detection model training method based on the support vector machine according to claim 1, wherein N of the N states in the simulated islanding grid is equal to M of the M states in the simulated non-islanding grid.
10. A support vector machine-based island detection model training method according to any one of claims 1-9, further comprising, after obtaining the support vector machine-based island detection model:
placing the support vector machine-based island detection model in an actual operation working condition for island detection;
judging whether the actual operation working condition is in an island state or not according to a preset frequency threshold;
when the actual operation working condition is judged to be in an island state according to the preset frequency threshold value, and the result output by the island detection model based on the support vector machine is still in a non-island state, acquiring three-phase instantaneous voltage within preset time before a judgment point for judging that the actual operation working condition is in the island state according to the preset frequency threshold value;
calculating the root mean square value of the three-phase instantaneous voltage according to each three-phase instantaneous voltage to form a correction training set consisting of the root mean square values of the three-phase instantaneous voltages;
updating the training set according to the corrected training set, and retraining the support vector machine-based island detection model to obtain the updating parameters of the support vector machine-based island detection model;
and obtaining the corrected island detection model based on the support vector machine according to the updated parameters.
11. An island detection model training device based on a support vector machine is characterized by comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring three-phase instantaneous voltages in N states in a simulation island power grid and in M states in a simulation non-island power grid, wherein N and M are positive integers;
the data set forming module is used for calculating the root mean square value of each group of three-phase instantaneous voltages according to each group of three-phase instantaneous voltages to form a data set consisting of the root mean square values of the three-phase instantaneous voltages, wherein the data set comprises a training set;
the training module is used for taking the training set as the input of an isolated island detection model based on a support vector machine, training the isolated island detection model based on the support vector machine and obtaining model parameters of the isolated island detection model based on the support vector machine;
and the model acquisition module is used for acquiring the support vector machine-based island detection model based on the model parameters.
12. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the support vector machine-based islanding detection model training method of any of claims 1-10.
13. A computer-readable storage medium storing computer instructions for causing a processor to implement the method for support vector machine-based islanding detection model training according to any one of claims 1-10 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210277435.5A CN114705947A (en) | 2022-03-16 | 2022-03-16 | Island detection model training method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210277435.5A CN114705947A (en) | 2022-03-16 | 2022-03-16 | Island detection model training method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114705947A true CN114705947A (en) | 2022-07-05 |
Family
ID=82168658
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210277435.5A Pending CN114705947A (en) | 2022-03-16 | 2022-03-16 | Island detection model training method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114705947A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024108686A1 (en) * | 2022-11-22 | 2024-05-30 | 中通服创发科技有限责任公司 | Method and device for creating iptables-based secure enclave under linux and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103778470A (en) * | 2014-02-13 | 2014-05-07 | 上海交通大学 | Distributed generation island detection method with on-line self-learning ability |
| WO2016023579A1 (en) * | 2014-08-12 | 2016-02-18 | Siemens Aktiengesellschaft | Method for estimating status of ac networks and subsequent adaptive control |
| WO2016054842A1 (en) * | 2014-10-09 | 2016-04-14 | 湖南大学 | Combined islanding detection method |
| US20160124031A1 (en) * | 2014-11-04 | 2016-05-05 | Walid G. Morsi Ibrahim | Smart multi-purpose monitoring system using wavelet design and machine learning for smart grid applications |
| CN109861278A (en) * | 2019-01-23 | 2019-06-07 | 华北电力大学 | The intelligent passive type island detection method of photovoltaic generating system |
| CN110866366A (en) * | 2019-11-26 | 2020-03-06 | 南京工程学院 | XGboost algorithm-based island detection method for photovoltaic microgrid containing PHEV |
| CN111160386A (en) * | 2019-11-28 | 2020-05-15 | 南京航空航天大学 | Data-driven power island detection method based on active reactive power disturbance |
| CN113222067A (en) * | 2021-06-01 | 2021-08-06 | 华北电力大学 | Intelligent island detection method based on SVM-Adaboost algorithm |
-
2022
- 2022-03-16 CN CN202210277435.5A patent/CN114705947A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103778470A (en) * | 2014-02-13 | 2014-05-07 | 上海交通大学 | Distributed generation island detection method with on-line self-learning ability |
| WO2016023579A1 (en) * | 2014-08-12 | 2016-02-18 | Siemens Aktiengesellschaft | Method for estimating status of ac networks and subsequent adaptive control |
| WO2016054842A1 (en) * | 2014-10-09 | 2016-04-14 | 湖南大学 | Combined islanding detection method |
| US20160124031A1 (en) * | 2014-11-04 | 2016-05-05 | Walid G. Morsi Ibrahim | Smart multi-purpose monitoring system using wavelet design and machine learning for smart grid applications |
| CN109861278A (en) * | 2019-01-23 | 2019-06-07 | 华北电力大学 | The intelligent passive type island detection method of photovoltaic generating system |
| CN110866366A (en) * | 2019-11-26 | 2020-03-06 | 南京工程学院 | XGboost algorithm-based island detection method for photovoltaic microgrid containing PHEV |
| CN111160386A (en) * | 2019-11-28 | 2020-05-15 | 南京航空航天大学 | Data-driven power island detection method based on active reactive power disturbance |
| CN113222067A (en) * | 2021-06-01 | 2021-08-06 | 华北电力大学 | Intelligent island detection method based on SVM-Adaboost algorithm |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024108686A1 (en) * | 2022-11-22 | 2024-05-30 | 中通服创发科技有限责任公司 | Method and device for creating iptables-based secure enclave under linux and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khoshkhoo et al. | On-line dynamic voltage instability prediction based on decision tree supported by a wide-area measurement system | |
| CN111368449B (en) | Cascading failure evolution path online identification method considering alternating current and direct current influences | |
| CN108695862B (en) | Power grid inertia characteristic online evaluation method based on PMU measured data | |
| CN110570122A (en) | Offshore wind power plant reliability assessment method considering wind speed seasonal characteristics and current collection system element faults | |
| JPWO2017126260A1 (en) | Power system model analysis apparatus and method | |
| CN113852083A (en) | Automatic searching and early warning method, device and equipment for power grid cascading failure | |
| Carmona-Delgado et al. | Probabilistic load flow with versatile non-Gaussian power injections | |
| CN114705947A (en) | Island detection model training method, device, equipment and medium | |
| CN114565058A (en) | Training method, device, equipment and medium for island detection model | |
| CN106022590B (en) | Voltage quality evaluation method and device for active power distribution network | |
| CN117473384A (en) | Power grid line safety constraint identification method, device, equipment and storage medium | |
| US11379091B2 (en) | Operation support device and operation support method | |
| CN116484554A (en) | Topology identification method, device, equipment and medium for power distribution network | |
| CN115441458A (en) | Active defense method, device and system for cascading failures of power system | |
| CN114936612A (en) | Short circuit type identification method and device, electronic equipment and storage medium | |
| CN115276081A (en) | Microgrid island division method and device, electronic equipment and storage medium | |
| CN110797906B (en) | Method and device for determining maximum installed capacity of wind power base and storage medium | |
| Brinkmann et al. | An observability index for distribution networks using information entropy | |
| CN109088413B (en) | Dynamic reactive power planning and site selection method and device for direct-current receiving-end power grid | |
| CN117422260A (en) | State estimation method, device, equipment and medium based on graph neural network | |
| CN115483699A (en) | On-grid and off-grid switching method and device, electronic equipment and storage medium | |
| CN116027197A (en) | Method, device, equipment and storage medium for evaluating self-discharge consistency of battery | |
| Bu et al. | Probabilistic analysis of small-signal stability of power systems—A survey | |
| Abasi et al. | Diagnosis of Voltage Instability Using BSDC Index in the Presence of Voltage Dependent Loads | |
| CN115408854A (en) | Power transmission and distribution system BESS scheduling model construction method, device, equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220705 |