CN113162037B - Power system transient voltage stability self-adaptive evaluation method and system - Google Patents
Power system transient voltage stability self-adaptive evaluation method and system Download PDFInfo
- Publication number
- CN113162037B CN113162037B CN202110444126.8A CN202110444126A CN113162037B CN 113162037 B CN113162037 B CN 113162037B CN 202110444126 A CN202110444126 A CN 202110444126A CN 113162037 B CN113162037 B CN 113162037B
- Authority
- CN
- China
- Prior art keywords
- time
- power system
- time step
- transient voltage
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- 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]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
Abstract
The invention provides a power system transient voltage stability self-adaptive evaluation method and system, wherein the evaluation method comprises the following steps: when a power system fails, acquiring a time sequence track of each time step after the failure in real time; calculating the distance between the time sequence track of each time step and the multidimensional shape corresponding to the time step; outputting a transient voltage stability evaluation result of the power system corresponding to the time step based on a comparison result of the distance and the split point corresponding to the time step; and training the multi-dimensional shape and the split point based on time sequence track sample data and a predetermined stable state label to obtain the multi-dimensional shape and the split point. The embodiment of the invention can adaptively evaluate the transient voltage stability, adapts to the actual acquisition condition of time sequence track data after a fault, can give an evaluation result in real time, can accurately and timely judge the current state of the power system, and has interpretability.
Description
Technical Field
The invention relates to the field of power system stability analysis and evaluation, in particular to a power system transient voltage stability self-adaptive evaluation method and system.
Background
With the rapid increase of loads in power systems and the push of the power market, the proportion of dynamic loads such as induction motors and the like is continuously increased, and transient voltage instability becomes a serious threat in the area of heavy load bearing areas. Transient voltage instability or collapse can cause major power failure accidents, thereby causing a great amount of economic loss and serious social impact. Therefore, timely judging the transient voltage stability of the power system has important significance for preventing voltage instability and even major power failure accidents. At present, engineering criteria based on a fixed threshold value are widely adopted in engineering to evaluate the transient voltage stability of a power system, when the duration that any node voltage is lower than the fixed threshold value in the transient process after fault clearing exceeds preset time, the system is regarded as instable, but the setting of the threshold value and the duration mainly depends on actual operation experience or regulations, and the reliability and the adaptability are difficult to guarantee.
With the popularization of a wide area measurement system, most of over 500KV substations and part of 220KV substations of a modern power system are mostly provided with Phasor Measurement Units (PMUs), and the transient voltage stability evaluation of the power system can be rapidly and accurately realized by utilizing synchronous PMU data. At present, three main methods are used for realizing transient voltage stability evaluation of a power system: firstly, judging the transient voltage stability of a system by adopting electromechanical transient simulation software of a power system according to time section data obtained by monitoring; secondly, judging the transient voltage stability of the system by adopting a theoretical method, such as a direct method and a bifurcation analysis method; and thirdly, judging the transient voltage stability of the system by using the ideas of data mining and machine learning. The first method is time-consuming, cannot meet the requirements of early and fast transient voltage stability evaluation, and requires accurate modeling of an actual power grid, but in practice, it is difficult to obtain accurate load parameters of the power system. The second theoretical method is applicable only to a small system, and is hardly applicable to a large system which is actually complicated, and therefore, much research is focused on the third method. However, the current method for performing transient voltage stability evaluation by machine learning/data mining lacks interpretability, does not consider spatial correlation among variables, and does not balance accuracy and rapidity of transient voltage stability evaluation.
Disclosure of Invention
The invention provides a self-adaptive evaluation method and a self-adaptive evaluation system for transient voltage stability of a power system, which are used for solving the technical defects in the prior art, and the method comprises the following steps:
when a power system fails, acquiring a time sequence track of each time step after the failure in real time;
calculating the distance between the time sequence track of the time step and the multi-dimensional shape corresponding to the time step;
outputting a transient voltage stability evaluation result of the power system corresponding to the time step based on a comparison result of the distance and the split point corresponding to the time step;
and the multi-dimensional shape and the split point are obtained by training based on time sequence track sample data and a predetermined stable state label.
According to the adaptive evaluation method for the transient voltage stability of the power system, the method further comprises the following steps:
testing the multi-dimensional shape and the split point by adopting time sequence track sample data and a predetermined stable state label;
if the accuracy of the test is greater than a preset threshold value, storing the corresponding multidimensional shape and split points for evaluating the transient voltage stability of the power system;
and if the accuracy of the test is not greater than the preset threshold, adding time sequence track sample data and a predetermined stable state label for training or adjusting the hyper-parameters in the multi-dimensional shape extraction process.
According to the transient voltage stability self-adaptive evaluation method of the power system, the time sequence track sample data of a plurality of time steps and a predetermined stable state label are both from a simulation sample set, and the generation method of the simulation sample set comprises the following steps: and performing simulation to generate the simulation sample set based on different fault positions and fault clearing time set by the power system and parameter sets consisting of different dynamic-static load ratios set by the load of the power system.
According to the transient voltage stability self-adaptive evaluation method of the power system provided by the invention, the extracting of the corresponding multidimensional shape and the splitting point based on the time sequence track sample data of a plurality of time steps and the predetermined stable state label comprises the following steps:
and selecting the corresponding multidimensional subsequence with the maximum information gain as the multidimensional shape obtained by extracting the initial time step, and storing the corresponding split point.
According to the adaptive evaluation method for transient voltage stability of the power system provided by the invention, after the multidimensional subsequence with the maximum corresponding information gain is selected as the multidimensional shape extracted at the initial time step and the corresponding split point is stored, the method further comprises the following steps:
after the length of the time sequence track is increased, selecting a corresponding sequence with the largest information gain from the newly added multi-dimensional candidate subsequence set as a newly added multi-dimensional candidate subsequence;
judging whether the information gain of the newly-added multi-dimensional candidate subsequence is larger than the information gain of the multi-dimensional shape at the previous time step, if so, taking the newly-added multi-dimensional candidate subsequence as the multi-dimensional shape extracted at the current time step;
and if not, taking the multi-dimensional shape of the previous time step as the multi-dimensional shape obtained by extraction of the current time step.
According to the adaptive evaluation method for transient voltage stability of the power system provided by the invention, the multidimensional shape extracted by selecting the corresponding multidimensional subsequence with the largest information gain as the initial time step comprises the following steps:
setting the time sequence track length of the candidate multi-dimensional shape at L min And L max In between, the time window is set to L en (L min ≤L en ≤L max ) (ii) a From an initial time step t 1 The composed training sample set is D t1 At initial time step voltage amplitude V t1 Applying a time window on each time sequence simultaneously to obtain a multi-dimensional candidate subsequence sc with a dimension of n × L en (ii) a For each sample in the sample set D1, sliding a time window to obtain a multi-dimensional candidate subsequence set according to different time window lengths;
calculating a sample set D formed from a multi-dimensional candidate subsequence sc to an initial time step t1 The distance therebetween; let ds be the sample set D t1 In this case, the distance between the multi-dimensional candidate subsequences sc and ds, denoted as D (sc, ds), is calculated according to the following formula:
wherein, can L Is a set of L-length subsequences extracted from a multi-dimensional time series ds L Is a subsequence set can L One subsequence thereof, euc (sc) i ,ds Li ) Refers to the sequence sc i And ds Li Euclidean distance between;
after the distance is calculated, the sample set D t1 Into a vector D consisting of distance values v Comparing the vector value with the split point sp according to the split point sp, and dividing the vector D by the magnitude v Divided into two subsets D L And D R Then, the calculation formula of the information gain of the multidimensional subsequence sc at the split point sp is as follows:
Info(D t1 )＝-(p 1 log 2 (p 1 )+p 2 log 2 (p 2 ))
IG sp (D t1 )＝Info(S)-Info sp (D t1 )
wherein, info (D) t1 ) Is a data set D t1 In the entire data set D, the stable and unstable samples t1 Has a ratio of p 1 ,p 2 ，Info sp (D t1 ) Is additional desired information when the split point is sp,
and
respectively represent D L And D R In the data set D t1 Middle ratio, IG sp (D t1 ) Is a data set D t1 Information gain at the split point sp;
traversal vector D v Calculating corresponding information gain of all possible split points, and selecting the largest information gain as the capability measure of distinguishing different categories of the candidate multi-dimensional subsequence sc;
traversing multi-dimensional candidate subsequences of the multi-dimensional candidate subsequence set, wherein a corresponding sequence with the largest information gain is used as a sample set D consisting of initial time steps t1 And extracting the obtained multi-dimensional shape and storing the corresponding splitting point.
The invention also provides a power system transient voltage stability self-adaptive evaluation system, which comprises:
the time sequence track acquisition module is used for acquiring the time sequence track of each time step after the fault in real time when the power system has the fault;
the distance determining module is used for calculating the distance between the time sequence track of the time step and the multi-dimensional shape corresponding to the time step;
the voltage stability evaluation module is used for outputting a transient voltage stability evaluation result of the power system corresponding to the time step based on a comparison result of the distance and the split point corresponding to the time step;
and the multi-dimensional shape and the split point are obtained by training based on time sequence track sample data and a predetermined stable state label.
The invention further provides an electronic device, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the adaptive evaluation method for transient voltage stability of the power system as described in any one of the above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when being executed by a processor, implements the steps of the power system transient voltage stability adaptive evaluation method according to any one of the above.
The invention provides a self-adaptive evaluation method for transient voltage stability of a power system based on a multi-dimensional shield, which takes the correlation among variables into consideration by utilizing the extraction of the multi-dimensional shield, and the extracted multi-dimensional shield is a multi-dimensional subsequence with the strongest region classification capability, has interpretability, is favorable for improving the evaluation accuracy, can be evaluated in a self-adaptive manner to adapt to the actual acquisition condition after a fault, and can give an evaluation result in real time.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a transient voltage stability adaptive evaluation method of a power system according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a power system transient voltage stability adaptive evaluation method according to another embodiment of the present invention;
FIG. 3 is a schematic diagram of an adaptive transient voltage stability evaluation system for a power system according to an embodiment of the invention;
fig. 4 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
The embodiment of the invention discloses a self-adaptive evaluation method for transient voltage stability of a power system, which comprises the following steps of:
s1: when a power system fails, acquiring a time sequence track of each time step after the failure in real time;
the transient voltage stabilization process is gradually developed, the time sequence track is also gradually obtained after the fault, and the length of the time sequence track is gradually increased on the basis of the initial time step, so that the transient voltage stability of the power system is evaluated aiming at each time step to realize the self-adaptive evaluation of the transient voltage stability, and therefore, the time sequence track of the real-time step needs to be obtained during the evaluation.
S2: calculating the distance between the time sequence track of the time step and the multi-dimensional shape corresponding to the time step;
and calculating the distance between the time sequence track and the multidimensional shapelet corresponding to the time step, and comparing the obtained distance with the corresponding split point to obtain a stable evaluation result.
S3: outputting a transient voltage stability evaluation result of the power system corresponding to the time step based on a comparison result of the distance and the split point corresponding to the time step;
the actual acquisition condition of PMU measurement after the fault is adaptively evaluated and adapted, and an evaluation result can be given in an early stage. And aiming at each time step, obtaining a corresponding post-fault voltage amplitude time sequence track, calculating the distance between the tracks and the multidimensional shape extracted in the time step, and comparing the distance with the corresponding split point to obtain a stable evaluation result. At each new time step, the obtained evaluation result covers the previous evaluation result.
And the multi-dimensional shape and the split point are obtained by training based on time sequence track sample data and a predetermined stable state label.
The extraction of the multidimensional shape takes the correlation relation among variables into consideration, and the evaluation accuracy is improved. The multidimensional shape extracted based on the simulation sample set is the extracted multidimensional subsequence with the strongest distinguishing and classifying capability, has interpretability, and is beneficial to a dispatcher to understand. The multidimensional shape extracted for each time step can be used for online transient voltage stability self-adaptive evaluation.
According to the self-adaptive evaluation method for the transient voltage stability of the power system, the time sequence track sample data and the predetermined stable state label are both derived from a simulation sample set, and the generation method of the simulation sample set comprises the following steps: collecting typical operation modes of a monitored power system to form an operation mode set, setting different fault positions and fault clearing time to form a fault set, and setting different dynamic-static load ratio forming parameter sets aiming at the load of the power system; and performing K-time domain simulation on the monitored power system under the conditions of different operation modes, fault settings and parameters by adopting electromechanical transient simulation software according to the obtained operation mode set, fault set and parameter set. In each simulation, a voltage amplitude time sequence track V of a transformer substation of the monitored power system within delta t after the fault is cleared needs to be recorded, a final voltage stable state C of the corresponding power system is recorded, and the information (V, C) is formed into a simulation sample. If the monitored power system includes N nodes, and the length of the fault-cleared timing trace for adaptive evaluation is N, the dimension of the fault-cleared voltage amplitude timing trace V of a single simulation sample is N × N. And performing time domain simulation for K times to obtain K simulation samples to form a simulation sample set for learning and testing. The obtained simulation sample set composed of K samples is randomly divided into two parts, namely a sample set D1 and a sample set D2. And selecting a sample set D1 to extract the multi-dimensional shape needed by the evaluation model, and testing the trained model by using a sample set D2.
According to the adaptive evaluation method for the transient voltage stability of the power system, provided by the invention, the method further comprises the following steps:
and extracting the multi-dimensional shape for the adaptive evaluation of the transient voltage stability by using the sample set D1. The multidimensional shape is the multidimensional sub-trajectory that is most relevant to the transient voltage stabilization condition C of the monitored power system. Because the voltage measurement value after the fault is gradually obtained along with the time, the corresponding multidimensional shape is extracted for each time step so as to realize the self-adaptive evaluation of the transient voltage stability and balance the requirements of the early and accurate evaluation of the transient voltage stability. Further, the training based on the time-series trajectory sample data and the predetermined steady-state label includes:
and selecting the sequence with the maximum corresponding information gain as the multi-dimensional shape extracted at the initial time step, and storing the corresponding split point.
At an initial time step t 1 The step of extracting the multi-dimensional shape is as follows:
setting the time sequence track length of the candidate multi-dimensional shape at L min And L max In between, the time window is set to L en (L min ≤L en ≤L max ) (ii) a From an initial time step t 1 The composed training sample set is D t1 At initial time step voltage amplitude V t1 Obtaining a multi-dimensional candidate subsequence sc by simultaneously adopting a time window on each time sequence, wherein the dimension of the sc is n × L en (ii) a For each sample in the sample set D1, sliding the time window for different time window lengths results in a multi-dimensional candidateA set of subsequences;
calculating a sample set D formed from a multi-dimensional candidate subsequence sc to an initial time step t1 The distance between them; let ds be the sample set D t1 In this case, the distance between the multi-dimensional candidate subsequences sc and ds, denoted as D (sc, ds), is calculated according to the following formula:
wherein, can L Is a set of L-length subsequences extracted from a multi-dimensional time series ds L Is a set of subsequences can L One subsequence thereof, euc (sc) i ,ds Li ) Refers to the sequence sc i And ds Li Euclidean distance between;
after the distance is calculated, the sample set D t1 Into a vector D consisting of distance values v Comparing the vector value with the split point sp according to the split point sp, and dividing the vector D by the magnitude v Divided into two subsets D L And D R The calculation formula of the information gain is as follows:
Info(D t1 )＝-(p 1 log 2 (p 1 )+p 2 log 2 (p 2 ))
IG sp (D t1 )＝Info(S)-Info sp (D t1 )
wherein, info (D) t1 ) Is a data set D t1 In the entire data set D, the stable and unstable samples t1 Has a ratio of p 1 ,p 2 ，Info sp (D t1 ) Is the additional desired information when the split point is sp,
and
respectively represent D L And D R In the data set D t1 Middle ratio, IG sp (D t1 ) Is a data set D t1 Information gain at the split point sp;
traversal vector D v Calculating corresponding information gain of all possible split points, and selecting the largest information gain as the capability measure of distinguishing different categories of the candidate multi-dimensional subsequence sc;
traversing multi-dimensional candidate subsequences of the multi-dimensional candidate subsequence set, wherein a corresponding sequence with the largest information gain is used as a sample set D consisting of initial time steps t1 And extracting the obtained multi-dimensional shape and storing the corresponding splitting point.
According to the adaptive evaluation method for transient voltage stability of the power system provided by the invention, after the sequence with the maximum corresponding information gain is selected as the multidimensional shape extracted at the initial time step and the corresponding split point is stored, the method further comprises the following steps:
because the transient voltage stabilization process is gradually developed and the time sequence track is gradually obtained after the fault, the length of the time sequence track is gradually increased on the basis of the initial time step, and therefore the corresponding shape is extracted at each subsequent time step on the basis of the initial time step. After the length of the time sequence track is increased, selecting a corresponding sequence with the largest information gain in the newly increased multi-dimensional candidate subsequence set as a newly increased multi-dimensional candidate subsequence;
judging whether the information gain of the newly added multi-dimensional candidate subsequence is larger than the information gain of the multi-dimensional shape at the previous time step, if so, taking the newly added multi-dimensional candidate subsequence as the multi-dimensional shape obtained by extracting the current time step;
and if not, taking the multi-dimensional shape of the previous time step as the multi-dimensional shape obtained by extracting the current time step.
Testing the multi-dimensional shape and the split point by adopting time sequence track sample data in the sample set D2 and a predetermined stable state label;
if the accuracy of the test is greater than a preset threshold value, storing the corresponding multidimensional shape and split points for evaluating the transient voltage stability of the power system;
and if the accuracy of the test is not greater than the preset threshold, adding time sequence track sample data and a predetermined stable state label for training or adjusting the hyper-parameters in the multi-dimensional shape extraction process. The preset threshold may be set according to actual needs, for example, may be set to 95% or 98%, etc.
The multidimensional shield in the transient voltage stabilization self-adaptive evaluation method based on the multidimensional shield has interpretability, useful information related to transient voltage stabilization/instability can be provided, and the multidimensional shield most having the capability of distinguishing the stabilization/instability types can be changed along with the time based on the dynamic knowledge after the transient voltage stabilization fault, so that the method is also matched with the development process of the transient voltage stabilization.
To further illustrate the multidimensional shield-based power system transient voltage stability adaptive evaluation method of the present invention, another embodiment of the method is provided as follows, as shown in fig. 2, the method includes:
s101, when a power system fails, acquiring a time sequence track of a current time step after the failure in real time;
s102, calculating the distance between the time sequence track of the current time step and the multi-dimensional shape corresponding to the time step;
s103, outputting a transient voltage stability evaluation result of the power system corresponding to the time step based on a comparison result of the distance and the split point corresponding to the time step;
s104, judging whether the current time step is smaller than a preset maximum time step or not; if not, executing S105; if the time is less than the preset maximum time step, S106 is executed.
S105, finishing transient voltage stability evaluation;
and S106, continuing to return to the time step next to the current time step, and re-executing the steps from S101 to S104.
That is to say: outputting the transient voltage stability evaluation result of the power system corresponding to the time step until the current time step is larger than a preset maximum time step; and the transient voltage stability evaluation result of the power system corresponding to each time step can be output in a circulating manner.
And training the multi-dimensional shape and the split points of the multiple time steps based on the time sequence track sample data of the multiple time steps and a predetermined stable state label to obtain the multi-dimensional shape and the split points of the multiple time steps. And training the multidimensional shape and the split point of each time step by respectively adopting the time sequence track sample data of the corresponding time step and a predetermined stable state label to obtain the multidimensional shape and the split point of each time step.
The invention provides a self-adaptive evaluation method for transient voltage stability of a power system based on a multi-dimensional shield, which takes the correlation among variables into consideration by utilizing the extraction of the multi-dimensional shield, and the extracted multi-dimensional shield is a multi-dimensional subsequence with the strongest region classification capability, has interpretability, is favorable for improving the evaluation accuracy, can be evaluated in a self-adaptive manner to adapt to the actual acquisition condition after a fault, and can give an evaluation result in real time.
The embodiment of the invention discloses a transient voltage stability self-adaptive evaluation system of a power system, which is shown in figure 3 and comprises the following components:
the time sequence track acquisition module 10 is used for acquiring the time sequence track of each time step after the fault in real time when the power system fails;
a distance determining module 20, configured to calculate a distance between the time sequence trajectory of the time step and the multidimensional shape corresponding to the time step;
the voltage stability evaluation module 30 is configured to output a transient voltage stability evaluation result of the power system corresponding to the time step based on a comparison result of the distance and the split point corresponding to the time step;
and the multi-dimensional shape and the split point are obtained by training based on time sequence track sample data and a predetermined stable state label.
Fig. 4 illustrates a physical structure diagram of an electronic device, which may include: a processor (processor) 310, a communication Interface (communication Interface) 320, a memory (memory) 330 and a communication bus 340, wherein the processor 310, the communication Interface 320 and the memory 330 communicate with each other via the communication bus 340. The processor 310 may invoke logic instructions in the memory 330 to perform the power system transient voltage stability adaptive evaluation method.
In addition, the logic instructions in the memory may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, which when executed by a computer, the computer is capable of executing the above power system transient voltage stabilization adaptive evaluation method.
In yet another aspect, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the above power system transient voltage stability adaptive evaluation method.
The above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A power system transient voltage stability self-adaptive evaluation method is characterized by comprising the following steps:
when a power system breaks down, acquiring a time sequence track of each time step after the failure in real time;
calculating the distance between the time sequence track of the time step and the multi-dimensional shape corresponding to the time step;
outputting a transient voltage stability evaluation result of the power system corresponding to the time step based on a comparison result of the distance and the split point corresponding to the time step;
the multidimensional shape and the split point are obtained by training based on time sequence track sample data and a predetermined stable state label;
the time sequence track sample data of the time steps and the predetermined stable state label are all derived from a simulation sample set, and the generation method of the simulation sample set comprises the following steps: collecting typical operation modes of a monitored power system to form an operation mode set, setting different fault positions and fault clearing time to form a fault set, and setting different dynamic-static load ratio forming parameter sets aiming at the load of the power system; performing K-time domain simulation on the monitored power system under the conditions of different operation modes, fault settings and parameters by adopting electromechanical transient simulation software according to the obtained operation mode set, fault set and parameter set; recording a voltage amplitude timing sequence track V of a transformer substation of the monitored power system in delta t time after fault clearing in each simulation, recording a final voltage stable state C of the corresponding power system, and forming a simulation sample by information (V, C); if the monitored power system comprises N nodes, and the length of the time sequence track after fault clearing for self-adaptive evaluation is N, the dimension of the voltage amplitude time sequence track V after fault of a single simulation sample is N x N; and performing time domain simulation for K times to obtain K simulation samples to form a simulation sample set.
2. The power system transient voltage stability adaptive evaluation method according to claim 1, further comprising:
testing the multi-dimensional shape and the split point by adopting time sequence track sample data and a predetermined stable state label;
if the accuracy of the test is greater than a preset threshold value, storing the corresponding multidimensional shape and split points for evaluating the transient voltage stability of the power system;
and if the accuracy of the test is not greater than the preset threshold, adding time sequence track sample data and a predetermined stable state label for training or adjusting the hyper-parameters in the multi-dimensional shape extraction process.
3. The adaptive evaluation method for transient voltage stability of a power system according to claim 1, wherein extracting corresponding multidimensional shapelets and split points based on time series trace sample data of the plurality of time steps and a predetermined steady state label comprises:
and selecting the corresponding multidimensional subsequence with the maximum information gain as the multidimensional shape obtained by extracting the initial time step, and storing the corresponding split point.
4. The adaptive evaluation method for transient voltage stability of a power system according to claim 3, wherein after the selecting the corresponding multidimensional subsequence with the largest information gain as the multidimensional shape extracted at the initial time step and storing the corresponding split point, the method further comprises:
after the length of the time sequence track is increased, selecting a corresponding sequence with the largest information gain from the newly added multi-dimensional candidate subsequence set as a newly added multi-dimensional candidate subsequence;
judging whether the information gain of the newly added multi-dimensional candidate subsequence is larger than the information gain of the multi-dimensional shape at the previous time step, if so, taking the newly added multi-dimensional candidate subsequence as the multi-dimensional shape obtained by extracting the current time step;
and if not, taking the multi-dimensional shape of the previous time step as the multi-dimensional shape obtained by extracting the current time step.
5. The adaptive evaluation method for transient voltage stability of the power system according to claim 3 or 4, wherein the selecting the multidimensional subsequence with the largest corresponding information gain as the multidimensional shape extracted at the initial time step comprises:
setting the time sequence track length of the candidate multi-dimensional shape at L min And L max In between, the time window is set to L en (L min ≤L en ≤L max ) (ii) a From an initial time step t 1 The formed training sample set is D t1 At initial time step voltage amplitude V t1 Applying a time window on each time sequence simultaneously to obtain a multi-dimensional candidate subsequence sc with a dimension of n × L en (ii) a For each sample in the sample set D1, sliding a time window to obtain a multi-dimensional candidate subsequence set according to different time window lengths;
calculating a sample set D formed from a multi-dimensional candidate subsequence sc to an initial time step t1 The distance between them; let ds be the sample set D t1 In this case, the distance between the multi-dimensional candidate subsequences sc and ds, denoted as D (sc, ds), is calculated according to the following formula:
wherein, can L Is a set of L-length subsequences extracted from a multi-dimensional time series ds L Is a set of subsequences can L One subsequence thereof, euc (sc) i ,ds Li ) Refers to the sequence sc i And ds Li Euclidean distance between;
after the distance is calculated, the sample set D t1 Into a vector D consisting of distance values v Comparing the vector value with the split point sp according to the split point sp, and dividing the vector D by the magnitude v Divided into two subsets D L And D R Then, the calculation formula of the information gain of the multidimensional subsequence sc at the split point sp is as follows:
Info(D t1 )＝-(p 1 log 2 (p 1 )+p 2 log 2 (p 2 ))
IG sp (D t1 )＝Info(S)-Info sp (D t1 )
wherein, info (D) t1 ) Is a data set D t1 In the entire data set D, the stable and unstable samples t1 Has a ratio of p 1 ,p 2 ，Info sp (D t1 ) Is additional desired information when the split point is sp,
and
respectively represent D L And D R In the data set D t1 Middle ratio, IG sp (D t1 ) Is a data set D t1 Information gain at the split point sp;
traversal vector D v Calculating corresponding information gain of all possible split points, and selecting the largest information gain as the capability measure of distinguishing different categories of the candidate multi-dimensional subsequence sc;
traversing multi-dimensional candidate subsequences of the multi-dimensional candidate subsequence set, wherein a corresponding sequence with the largest information gain is used as a sample set D consisting of initial time steps t1 And extracting the obtained multi-dimensional shape and storing the corresponding splitting point.
6. An adaptive evaluation system for transient voltage stability of a power system, comprising:
the time sequence track acquisition module is used for acquiring the time sequence track of each time step after the fault in real time when the power system has the fault;
the distance determining module is used for calculating the distance between the time sequence track of the time step and the multi-dimensional shape corresponding to the time step;
the voltage stability evaluation module is used for outputting a transient voltage stability evaluation result of the power system corresponding to the time step based on a comparison result of the distance and the split point corresponding to the time step;
the multidimensional shape and the split point are obtained by training based on time sequence track sample data and a predetermined stable state label;
the time sequence track sample data of the time steps and the predetermined stable state label are all derived from a simulation sample set, and the generation method of the simulation sample set comprises the following steps: collecting typical operation modes of a monitored power system to form an operation mode set, setting different fault positions and fault clearing time to form a fault set, and setting different dynamic-static load ratio forming parameter sets aiming at the load of the power system; performing K-time domain simulation on the monitored power system under different operation modes, fault settings and parameters by adopting electromechanical transient simulation software according to the obtained operation mode set, fault set and parameter set; recording a voltage amplitude time sequence track V of a transformer substation of the monitored power system in delta t time after fault clearing in each simulation, recording a final voltage stable state C of the corresponding power system, and forming information (V and C) into a simulation sample; if the monitored power system comprises N nodes, and the length of the time sequence track after fault clearing for self-adaptive evaluation is N, the dimension of the voltage amplitude time sequence track V after fault of a single simulation sample is N x N; and performing time domain simulation for K times to obtain K simulation samples to form a simulation sample set.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the power system transient voltage stability adaptive evaluation method according to any one of claims 1 to 5 when executing the program.
8. A non-transitory computer readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the power system transient voltage stability adaptive evaluation method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110444126.8A CN113162037B (en) | 2021-04-23 | 2021-04-23 | Power system transient voltage stability self-adaptive evaluation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110444126.8A CN113162037B (en) | 2021-04-23 | 2021-04-23 | Power system transient voltage stability self-adaptive evaluation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113162037A CN113162037A (en) | 2021-07-23 |
| CN113162037B true CN113162037B (en) | 2023-02-03 |
Family
ID=76870026
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110444126.8A Active CN113162037B (en) | 2021-04-23 | 2021-04-23 | Power system transient voltage stability self-adaptive evaluation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113162037B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113608146B (en) * | 2021-08-06 | 2023-12-19 | 云南电网有限责任公司昆明供电局 | Fault line selection method suitable for forest fire under high-resistance grounding condition |
| CN114091705A (en) * | 2021-11-26 | 2022-02-25 | 国网四川省电力公司电力科学研究院 | Power system instability analysis method and device, electronic equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107482621A (en) * | 2017-08-02 | 2017-12-15 | 清华大学 | A kind of Transient Voltage Stability in Electric Power System appraisal procedure based on voltage sequential track |
-
2021
- 2021-04-23 CN CN202110444126.8A patent/CN113162037B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107482621A (en) * | 2017-08-02 | 2017-12-15 | 清华大学 | A kind of Transient Voltage Stability in Electric Power System appraisal procedure based on voltage sequential track |
Non-Patent Citations (5)
| Title |
|---|
| "Online Long-term Voltage Stability Assessment Based on Time Series Shapelet Extraction";Sicong Xie 等;《2018 IEEE Innovative Smart Grid Technologies - Asia (ISGT Asia)》;20180920;第1-6页 * |
| 基于广域时序数据挖掘策略的暂态电压稳定评估;朱利鹏等;《电网技术》;20160105;第40卷(第01期);第180-185页 * |
| 基于改进shapelet挖掘的风电并网系统暂态功角稳定评估;梁咪咪等;《能源工程》;20191220(第06期);第37-43页 * |
| 基于时序轨迹特征学习的暂态电压稳定评估;朱利鹏等;《电网技术》;20190429;第43卷(第06期);第1922-1930页 * |
| 朱利鹏等.基于时序轨迹特征学习的暂态电压稳定评估.《电网技术》.2019,第43卷(第06期),第1922-1930页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113162037A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113162037B (en) | Power system transient voltage stability self-adaptive evaluation method and system | |
| CN106154163A (en) | Battery life state identification method | |
| CN116401532B (en) | Method and system for recognizing frequency instability of power system after disturbance | |
| CN111478314A (en) | Transient stability assessment method for power system | |
| Li et al. | DNN-based distributed voltage stability online monitoring method for large-scale power grids | |
| CN111401792A (en) | Dynamic safety assessment method based on extreme gradient lifting decision tree | |
| CN113675878B (en) | Offshore wind farm grid-connected performance testing method and system, computer equipment and medium | |
| CN114266396A (en) | Transient stability discrimination method based on intelligent screening of power grid characteristics | |
| CN112909939A (en) | Power system transient stability assessment method based on load flow characteristics before and after fault | |
| CN117424201A (en) | Power system transient stability interpretable evaluation method, system, equipment and storage medium | |
| CN110098610B (en) | Real-time identification method and system for oscillation leading mode of power system under fault disturbance | |
| CN110514953B (en) | Power angle and voltage aliasing-based power grid fault simulation identification method and system | |
| Xue et al. | An efficient and robust case sorting algorithm for transient stability assessment | |
| Shi et al. | Fast identification of power transformer magnetizing inrush currents based on mathematical morphology and ANN | |
| CN116204771A (en) | Power system transient stability key feature selection method, device and product | |
| CN116502149A (en) | Low-voltage power distribution network user-transformation relation identification method and system based on current characteristic conduction | |
| CN113067352B (en) | Power grid critical removal time prediction method based on EEAC and ELM | |
| Cui et al. | High impedance fault detection method based on Data divergence in the distribution network | |
| CN113468745A (en) | Power distribution network reliability rapid evaluation method and system based on historical faults | |
| CN113258563B (en) | Method and device for determining relay protection sensitivity of alternating current power grid accessed by flexible direct island | |
| CN110909795A (en) | Method for judging transient voltage stability of power grid | |
| CN117408505A (en) | Distribution cable line operation risk deduction algorithm | |
| CN111130120B (en) | Method and system for evaluating voltage instability of mixed-superposition type regional power grid | |
| CN111814395A (en) | Static voltage stability evaluation method based on principal component analysis and confidence detection | |
| Xie et al. | Power Transformer Fault Diagnosis Model Based on Association Rules Analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |