CN117992851A - Power grid power quality disturbance classification method and device, electronic equipment and storage medium - Google Patents
Power grid power quality disturbance classification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117992851A CN117992851A CN202410191104.9A CN202410191104A CN117992851A CN 117992851 A CN117992851 A CN 117992851A CN 202410191104 A CN202410191104 A CN 202410191104A CN 117992851 A CN117992851 A CN 117992851A
- Authority
- CN
- China
- Prior art keywords
- disturbance
- curve
- quality disturbance
- power quality
- layer
- 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
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000013145 classification model Methods 0.000 claims abstract description 54
- 238000012549 training Methods 0.000 claims abstract description 39
- 238000001514 detection method Methods 0.000 claims abstract description 38
- 238000004590 computer program Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 13
- 230000004913 activation Effects 0.000 claims description 12
- 230000001364 causal effect Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 16
- 238000004891 communication Methods 0.000 description 8
- 239000002131 composite material Substances 0.000 description 5
- 230000010355 oscillation Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000009466 transformation Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 230000010339 dilation Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power grid power quality disturbance classification method, a device, electronic equipment and a storage medium, wherein a historical curve of historical power signal data is obtained, and a power signal comprises time and voltage; marking the historical curve with the type of power quality disturbance, the wave crest, the wave trough and the time stamps corresponding to the wave crest and the wave trough to obtain training data; training data is imported into an initial disturbance classification model to be trained, and a trained disturbance classification model is obtained, wherein the disturbance classification model is a model based on TCN-BIGRU; acquiring a detection curve generated by power signal data detected in real time; and inputting the detection curve into a trained disturbance classification model for prediction to obtain the electric energy quality disturbance type corresponding to the detection curve. The disturbance classification model can learn the rule and the relation between the power quality disturbance type, the wave crest and the wave trough of the curve and the corresponding time stamp, has better anti-noise capability, and still maintains the efficient and accurate classification capability in a complex environment.
Description
Technical Field
The invention relates to the technical field of power grid power quality disturbance classification, in particular to a power grid power quality disturbance classification method, a device, electronic equipment and a storage medium.
Background
In recent years, a large amount of new energy sources, nonlinear loads such as an electric vehicle charging device and the like are connected to a power grid, and the problems of unstable voltage, frequency fluctuation, harmonic disturbance and the like can be caused, so that the normal operation and the power supply quality of the power grid are affected. This not only directly affects the electricity consumption experience of the residents, but may also jeopardize the stability of the grid. Therefore, accurate identification of the power quality disturbance is a key step for improving the power quality, and has become a research direction of common attention of domestic and foreign students.
At present, the research on the disturbance classification of the electric energy quality is mainly divided into two directions: one is a traditional method for extracting electric signal characteristics through a signal processing algorithm and then classifying by using a classifier; the other is based on data driving and applies an artificial intelligence method of deep learning. In the traditional method, common signal analysis methods comprise Fourier transformation, wavelet transformation, S transformation, empirical mode decomposition and the like, after time-frequency characteristics are acquired, mapping between a classifier learning sequence and a label is transferred, and common classifiers comprise decision trees, support vector machines, neural networks and the like.
The traditional method is mature when aiming at single disturbance recognition, but is difficult to have higher recognition rate when aiming at compound disturbance problem because complex feature quantity overlapping exists. In addition, the signal processing method has limitations, such as that wavelet transformation is very sensitive to fundamental wave selection, S variation is complex in calculation, and error separation is easy to generate when the oscillation mode of empirical mode decomposition in a signal is close to the noise frequency, so that the self-adaptive capacity and robustness of the existing power quality disturbance classification method are poor.
Disclosure of Invention
The invention provides a power grid power quality disturbance classification method, which aims at solving the problems that the prior art is difficult to have higher recognition rate aiming at the composite disturbance problem and the self-adaption capability and the robustness of the prior power quality disturbance classification method are poor.
In a first aspect, the present invention provides a method for classifying power quality disturbances of a power grid, including:
acquiring a historical curve generated from historical power signal data, the power signal including time and voltage;
Marking the historical curve with the type of power quality disturbance, the wave crest, the wave trough and the time stamps corresponding to the wave crest and the wave trough to obtain training data;
The training data is imported into an initial disturbance classification model for training, and a trained disturbance classification model is obtained, wherein the disturbance classification model is a model based on TCN-BIGRU;
Acquiring a detection curve generated by power signal data detected in real time;
and inputting the detection curve into the trained disturbance classification model for prediction to obtain the electric energy quality disturbance type corresponding to the detection curve.
In a second aspect, the present invention provides a power grid power quality disturbance classification device, including:
A history curve acquisition module for acquiring a history curve generated from historical power signal data including time and voltage;
The training data determining module is used for marking the historical curve with the power quality disturbance type, the wave crest, the wave trough and the time stamps corresponding to the wave crest and the wave trough to obtain training data;
The model training module is used for importing the training data into an initial disturbance classification model for training to obtain a trained disturbance classification model, wherein the disturbance classification model is a model based on TCN-BIGRU;
The detection curve generation module is used for acquiring a detection curve generated by the power signal data detected in real time;
And the disturbance classification module is used for inputting the detection curve into the trained disturbance classification model to predict so as to obtain the electric energy quality disturbance type corresponding to the detection curve.
In a third aspect, the present invention provides an electronic device, including:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the grid power quality disturbance classification method according to the first aspect of the invention.
In a fourth aspect, the present invention provides a computer readable storage medium storing computer instructions for causing a processor to implement the grid power quality disturbance classification method according to the first aspect of the present invention when executed.
The embodiment of the invention provides a power grid power quality disturbance classification method, which comprises the steps of obtaining a historical curve generated by historical power signal data, wherein the power signal data comprises time and voltage; marking the historical curve with the type of power quality disturbance, the wave crest, the wave trough and the time stamps corresponding to the wave crest and the wave trough to obtain training data; training data is imported into an initial disturbance classification model to be trained, and a trained disturbance classification model is obtained, wherein the disturbance classification model is a model based on TCN-BIGRU; acquiring a detection curve generated by power signal data detected in real time; and inputting the detection curve into a trained disturbance classification model for prediction to obtain the electric energy quality disturbance type corresponding to the detection curve. On the one hand, because the training data are marked with the electric energy quality disturbance types, the wave crests, the wave troughs and the time stamps corresponding to the wave crests and the wave troughs, the disturbance classification model can learn the rule and the relation between the electric energy quality disturbance types and the wave crests, the wave troughs and the time stamps corresponding to the wave crests and the wave troughs of the curve, and can more accurately obtain the electric energy quality disturbance types corresponding to the detection curve when the electric power signal data are detected in real time and the detection curve is generated. On the other hand, the disturbance classification model is a model based on TCN-BIGRU, TCN-BIGRU is a deep learning model, and the advantages of TCN and BiGRU are combined.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a power grid power quality disturbance classification method provided by an embodiment of the invention;
FIG. 2 is a normal waveform diagram without power quality disturbance according to an embodiment of the present invention;
FIG. 3 is a waveform diagram of a different type of power quality disturbance provided by an embodiment of the present invention;
FIG. 4 is a schematic diagram of a disturbance classification model according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating the operation of a residual network according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a basic unit of BiGRU provided by an embodiment of the present invention;
FIG. 7 is a comparison chart of classification results provided by an embodiment of the present invention;
fig. 8 is a schematic structural diagram of a power quality disturbance classification device for a power grid according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Fig. 1 is a flowchart of a power grid power quality disturbance classification method according to an embodiment of the present invention, where the method may be performed by a power grid power quality disturbance classification device, and the power grid power quality disturbance classification device may be implemented in hardware and/or software, and the power grid power quality disturbance classification device may be configured in an electronic device.
Where power quality refers to stability and purity of parameters such as voltage, current and frequency in a power system where various power quality disturbances may occur, which may be caused by equipment failure, power load changes, power system failure or other external factors.
As shown in fig. 1, the power quality disturbance classification method of the power grid includes:
S101, acquiring a historical curve generated by historical power signal data, wherein the power signal data comprises time and voltage.
The power quality disturbance includes a single disturbance, i.e., only one power quality disturbance form, and a composite disturbance, i.e., a power quality disturbance form including two or more single disturbances.
The single disturbance includes: voltage fluctuations, voltage sags, harmonics, breaks, oscillations, pulses, etc. The composite disturbance comprises voltage fluctuation + harmonic wave, voltage fluctuation + oscillation, oscillation + harmonic wave, voltage sag + harmonic wave and the like, wherein "+" represents that two disturbance signals are combined.
Fig. 2 is a normal waveform diagram without power quality disturbance. According to the standard of IEEE-1159, common disturbance signals are simulated through software Matlab, the simulated sampling period is N=10 periods, the sampling frequency is fs=6.4 kHz, the number of sampling points is 1280, 7 single disturbance signals and 6 composite disturbance signals are constructed, waveform diagrams of 13 electric energy faults are shown in a waveform diagram 3, the waveform diagrams of different electric energy quality disturbance types are shown in the figure 3, the abscissa in the figure 2 and the figure 3 is time, and the ordinate is voltage. In fig. 3, "+" indicates that the two disturbance signals are combined, i.e. the power quality disturbance is a combined disturbance.
In an alternative embodiment, obtaining a historical curve generated from historical power signal data includes: acquiring historical power signal data; removing abnormal data and filling incomplete data from the historical power signal data to obtain first data; carrying out standardization processing on the first data to obtain second data; a history curve is generated based on the second data. The normalization process is used for eliminating the influence caused by the difference of different data amount classes so as to facilitate subsequent training.
S102, marking the historical curve with the power quality disturbance type, the wave crest, the wave trough and the time stamps corresponding to the wave crest and the wave trough to obtain training data.
As shown in fig. 3, there are different features for different types of power quality disturbance, including: the peaks, the troughs and the changes of the timestamps corresponding to the peaks and the troughs are used for marking the characteristics of the historical curves, so that the disturbance classification model can learn the association between the power quality disturbance type and the characteristics.
In an alternative embodiment, the annotated data set may be written at 0.8:0.2 dividing training data for training the model and test data for testing the performance of the model.
S103, training data are imported into an initial disturbance classification model to be trained, and a trained disturbance classification model is obtained, wherein the disturbance classification model is a model based on TCN-BIGRU.
First, a disturbance classification model based on TCN-BIGRU may be built, and fig. 4 is a schematic structural diagram of a disturbance classification model, and as shown in fig. 4, the disturbance classification model includes an input layer 100, a TCN layer 200, a BIGRU layer 300, and an output layer 400.
Firstly, constructing a TCN layer, wherein the TCN layer comprises a plurality of residual error networks, and the residual error networks comprise a causal expansion convolution layer, a normalization layer, an activation function layer and a regularization layer.
The causal expansion convolution layer mainly comprises two convolution modes, namely causal convolution and expansion convolution.
Causal convolution is a special type of convolution operation in a convolutional neural network that maintains the input in dimensional agreement with the convolution calculation output by a vector of zero values of some complementary length preceding the input sequence. In causal convolution, the convolution kernel can only slide from the past moment to the current moment of input data, but cannot acquire information of the future moment, so that output information only depends on the past input information, and interference of the future information is effectively avoided.
The expansion convolution is also called hole convolution, and expansion is realized by inserting zero between convolution kernel elements, so that the receptive field of each layer of convolution kernel is increased under the condition of keeping the number of parameters unchanged, and the problem that the causal convolution needs a plurality of layers or the convolution kernel is increased to increase the receptive field is solved. In general, under the condition that the number of model parameters is relatively small due to the addition of the expansion convolution, the receptive field is enlarged, and further, the performance of the model is improved. The formula of the dilation convolution is as follows:
Wherein: x is the input sequence; f is a filter; i is the convolution kernel position; k is the convolution kernel size; s-di represents the s-di element of the upper layer.
Fig. 5 shows the operation of the residual network, in which, as shown in fig. 5, the input features sequentially pass through the first causal expansion convolution layer (Dilated Causal ConV), the normalization layer (WeightNorm), the activation function layer (ReLU), and the regularization layer (Dropout), and the output results are input to the second expansion convolution layer (Dilated Causal ConV), the normalization layer (WeightNorm), the activation function layer (ReLU), and the regularization layer (Dropout), so as to obtain the final output features.
But unlike the standard residual structure, the inputs are added directly to the output of the residual function, in TCN the inputs and outputs may have different widths. Therefore, a convolution of 1×1 is used in the residual network of fig. 5 to ensure that the element addition receives the same shaped tensor. Assuming that the input of the ith residual network is X i and the output is X i+1, then the relationship between the two is:
Xi+1＝Activation(Xi+F(Xi))；
Wherein, the Activation is an Activation function, and F (X i) is a residual network operation.
With respect to the BiGRU module, the BiGRU model is a special recurrent neural network specifically designed to process time series data, and BiGRU can process the time series data forward and backward, respectively, by introducing a bi-directional loop structure. Therefore, long-term dependency of the time sequence can be better captured, and the past and future information of the time sequence signal can be captured, so that the problem of gradient vanishing explosion is avoided.
FIG. 6 is a schematic diagram of the basic unit of BiGRU, as shown in FIG. 6, where x t is the current input; h t is the current cell hidden state (input); h t-1 is the hidden state (input) of the previous moment; A hidden state calculated for the reset gate; sigma is a sigmoid activation function; r t is reset gate; z t is the update gate. At each time step, the update gate decides whether to update the hidden state calculated by the reset gate with the hidden layer state h t, and the reset gate decides whether to forget the previous hidden layer state h t.
Wherein BIGRU layers include a GRU layer that accepts forward and reverse inputs; the output of the output layer is determined by the following expression:
Wherein, Forward input and reverse input at time t respectively,/>The forward input and the reverse input at the time t-1 are respectively, W t、Ut is weight, b t is bias, and h t is output at the time t of the output layer.
The GRU layer is composed of an update gate and a reset gate, and the formula of the GRU layer update process at the time t comprises:
reset gate r t＝σ(Wrxt+Urht-1+br);
Update door z t＝σ(Wzxt+Uzht-1+bz);
hidden state
The output h t of the GRU layer,
Wherein σ is a sigmoid activation function, and x t is a current input; w r、Ur、Wz、Uz、Wc、Uc is the weight matrix and b r、bz、bc is the bias.
In one example, test data is input into a trained disturbance classification model, resulting in a classification result comparison graph as shown in FIG. 7. Wherein, C1 represents no power quality disturbance, C2-C14 respectively correspond to 13 power quality disturbance types, the actual type is the actual power quality disturbance type corresponding to the test data, and the predicted type is the power quality disturbance type predicted by the disturbance classification model. It can be seen that the number of the consistent actual types and the predicted types is the vast majority, and only a very small part of the predicted types are inconsistent with the actual types, which means that the disturbance classification model has higher accuracy in predicting the power quality disturbance types. The invention combines the advantages of both TCN and BiGRU, and compared with the traditional method, the model has excellent performance on the classification task of the electric energy quality disturbance, and the classification accuracy is obviously improved (the classification accuracy of the traditional method for the composite disturbance is low). The disturbance classification model has better anti-noise capability, and still maintains the efficient and accurate classification capability in a complex environment.
S104, acquiring a detection curve generated by the power signal data detected in real time.
Likewise, in generating the detection curve, it is possible to: acquiring power signal data detected in real time; removing abnormal data and filling incomplete data from the power signal data detected in real time to obtain third data; carrying out standardization processing on the third data to obtain fourth data; a detection curve is generated based on the fourth data.
S105, inputting the detection curve into a trained disturbance classification model for prediction, and obtaining the power quality disturbance type corresponding to the detection curve.
After the disturbance classification model is trained, the detection curve is input into the trained disturbance classification model for prediction, and then the electric energy quality disturbance type corresponding to the detection curve is obtained.
The embodiment of the invention provides a power grid power quality disturbance classification method, which comprises the steps of obtaining a historical curve generated by historical power signal data, wherein the power signal data comprises time and voltage; marking the historical curve with the type of power quality disturbance, the wave crest, the wave trough and the time stamps corresponding to the wave crest and the wave trough to obtain training data; training data is imported into an initial disturbance classification model to be trained, and a trained disturbance classification model is obtained, wherein the disturbance classification model is a model based on TCN-BIGRU; acquiring a detection curve generated by power signal data detected in real time; and inputting the detection curve into a trained disturbance classification model for prediction to obtain the electric energy quality disturbance type corresponding to the detection curve. On the one hand, because the training data are marked with the electric energy quality disturbance types, the wave crests, the wave troughs and the time stamps corresponding to the wave crests and the wave troughs, the disturbance classification model can learn the rule and the relation between the electric energy quality disturbance types and the wave crests, the wave troughs and the time stamps corresponding to the wave crests and the wave troughs of the curve, and can more accurately obtain the electric energy quality disturbance types corresponding to the detection curve when the electric power signal data are detected in real time and the detection curve is generated. On the other hand, the disturbance classification model is a model based on TCN-BIGRU, TCN-BIGRU is a deep learning model, and the advantages of TCN and BiGRU are combined.
Fig. 8 is a schematic structural diagram of a power grid power quality disturbance classification device according to an embodiment of the present invention. As shown in fig. 8, the power grid power quality disturbance classification device includes:
A history curve acquisition module 801 for acquiring a history curve generated from historical power signal data including time and voltage;
The training data determining module 802 is configured to label the historical curve with a power quality disturbance type, a peak, a trough, and time stamps corresponding to the peak and the trough, so as to obtain training data;
the model training module 803 is configured to import the training data into an initial disturbance classification model for training, so as to obtain a trained disturbance classification model, where the disturbance classification model is a TCN-BIGRU-based model;
a detection curve generating module 804, configured to obtain a detection curve generated by the power signal data detected in real time;
And the disturbance classification module 805 is configured to input the detection curve into the trained disturbance classification model to predict, so as to obtain the power quality disturbance type corresponding to the detection curve.
In an alternative embodiment, the history curve acquisition module 801 includes:
the data acquisition sub-module is used for acquiring historical power signal data;
The first data determining sub-module is used for eliminating abnormal data and filling incomplete data for the historical power signal data to obtain first data;
the second data determining submodule is used for carrying out standardization processing on the first data to obtain second data;
And the history curve submodule is used for generating a history curve based on the second data.
In an alternative embodiment, the training data determination module 802 includes:
The first information determining submodule is used for marking the power quality disturbance type for the history curve to obtain first information;
the second information sub-module is used for correlating the wave crest and the wave trough in the history curve with the time stamp to obtain second information;
And the training data determining submodule is used for taking the history curve, the first information and the second information as training data.
In an alternative embodiment, the perturbation classification model includes an input layer, a TCN layer, BIGRU layers, and an output layer.
In an alternative embodiment, the TCN layer comprises a plurality of residual networks including a causal dilation convolution layer, a normalization layer, an activation function layer, and a regularization layer.
In an alternative embodiment, the BIGRU layers include a GRU layer that accepts forward and reverse inputs; the output of the output layer is determined by the following expression:
Wherein, Forward input and reverse input at time t respectively,/>The input is respectively a forward input and a reverse input at the time t-1, W t、Ut is a weight, b t is a bias, and h t is the output of the output layer at the time t.
In an alternative embodiment, the GRU layer is composed of an update gate and a reset gate, and the formula of the update procedure of the GRU layer at time t includes:
reset gate r t＝σ(Wrxt+Urht-1+br);
Update door z t＝σ(Wzxt+Uzht-1+bz);
hidden state
The output h t of the GRU layer,
Wherein σ is a sigmoid activation function, and x t is a current input; w r、Ur、Wz、Uz、Wc、Uc is the weight matrix and b r、bz、bc is the bias.
The power grid power quality disturbance classification device provided by the embodiment of the invention can execute the power grid power quality disturbance classification method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Fig. 9 shows a schematic diagram of an electronic device 40 that may be used to implement an embodiment of the 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. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. 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. 9, the electronic device 40 includes at least one processor 41, and a memory communicatively connected to the at least one processor 41, such as a Read Only Memory (ROM) 42, a Random Access Memory (RAM) 43, etc., in which the memory stores a computer program executable by the at least one processor, and the processor 41 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 42 or the computer program loaded from the storage unit 48 into the Random Access Memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the electronic device 40 may also be stored. The processor 41, the ROM 42 and the RAM 43 are connected to each other via a bus 44. An input/output (I/O) interface 45 is also connected to bus 44.
Various components in electronic device 40 are connected to I/O interface 45, including: an input unit 46 such as a keyboard, a mouse, etc.; an output unit 47 such as various types of displays, speakers, and the like; a storage unit 48 such as a magnetic disk, an optical disk, or the like; and a communication unit 49 such as a network card, modem, wireless communication transceiver, etc. The communication unit 49 allows the electronic device 40 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 41 may be various general and/or special purpose processing components with processing and computing capabilities. Some examples of processor 41 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, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 41 performs the various methods and processes described above, such as the grid power quality disturbance classification method.
In some embodiments, the grid power quality disturbance classification method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 40 via the ROM 42 and/or the communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the grid power quality disturbance classification method described above may be performed. Alternatively, in other embodiments, the processor 41 may be configured to perform the grid power quality disturbance classification method in any other suitable way (e.g. by means of firmware).
Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out 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 implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the 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. The 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) through 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 may 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 input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background 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 background, 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. The client and server are typically 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 hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A power grid power quality disturbance classification method, comprising:
acquiring a historical curve generated from historical power signal data, the power signal data including time and voltage;
Marking the historical curve with the type of power quality disturbance, the wave crest, the wave trough and the time stamps corresponding to the wave crest and the wave trough to obtain training data;
The training data is imported into an initial disturbance classification model for training, and a trained disturbance classification model is obtained, wherein the disturbance classification model is a model based on TCN-BIGRU;
Acquiring a detection curve generated by power signal data detected in real time;
and inputting the detection curve into the trained disturbance classification model for prediction to obtain the electric energy quality disturbance type corresponding to the detection curve.
2. The power grid power quality disturbance classification method according to claim 1, wherein said obtaining a historical curve generated from historical power signal data includes:
Acquiring historical power signal data;
removing abnormal data and filling incomplete data from the historical power signal data to obtain first data;
carrying out standardization processing on the first data to obtain second data;
a history curve is generated based on the second data.
3. The power grid power quality disturbance classification method according to claim 1, wherein the marking the historical curves with the power quality disturbance type, the peak, the trough, and the time stamps corresponding to the peak and the trough to obtain training data includes:
labeling the historical curve with a power quality disturbance type to obtain first information;
Correlating the wave crest and the wave trough in the history curve with the time stamp to obtain second information;
and taking the history curve, the first information and the second information as training data.
4. A method of classifying a power quality disturbance of a power grid according to any one of claims 1 to 3, wherein the disturbance classification model comprises an input layer, a TCN layer, a BIGRU layer and an output layer.
5. The power grid power quality disturbance classification method according to claim 4, wherein the TCN layer comprises a plurality of residual networks including a causal expansion convolution layer, a normalization layer, an activation function layer, and a regularization layer.
6. The grid power quality disturbance classification method according to claim 5, wherein said BIGRU layers include a GRU layer that accepts forward and reverse inputs; the output of the output layer is determined by the following expression:
Wherein, Forward input and reverse input at time t respectively,/>The input is respectively a forward input and a reverse input at the time t-1, W t、Ut is a weight, b t is a bias, and h t is the output of the output layer at the time t.
7. The power grid power quality disturbance classification method according to claim 6, wherein the GRU layer is composed of an update gate and a reset gate, and the formula of the update process of the GRU layer at time t includes:
reset gate r t＝σ(Wrxt+Urht-1+br);
Update door z t＝σ(Wzxt+Uzht-1+bz);
hidden state
The output h t of the GRU layer,
Wherein σ is a sigmoid activation function, and x t is a current input; w r、Ur、Wz、Uz、Wc、Uc is the weight matrix and b r、bz、bc is the bias.
8. A power grid power quality disturbance classification device, comprising:
A history curve acquisition module for acquiring a history curve generated from historical power signal data including time and voltage;
The training data determining module is used for marking the historical curve with the power quality disturbance type, the wave crest, the wave trough and the time stamps corresponding to the wave crest and the wave trough to obtain training data;
The model training module is used for importing the training data into an initial disturbance classification model for training to obtain a trained disturbance classification model, wherein the disturbance classification model is a model based on TCN-BIGRU;
The detection curve generation module is used for acquiring a detection curve generated by the power signal data detected in real time;
And the disturbance classification module is used for inputting the detection curve into the trained disturbance classification model to predict so as to obtain the electric energy quality disturbance type corresponding to the detection curve.
9. An electronic device, the electronic device comprising:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the grid power quality disturbance classification method according to any one of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to implement the grid power quality disturbance classification method according to any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410191104.9A CN117992851A (en) | 2024-02-21 | 2024-02-21 | Power grid power quality disturbance classification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410191104.9A CN117992851A (en) | 2024-02-21 | 2024-02-21 | Power grid power quality disturbance classification method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117992851A true CN117992851A (en) | 2024-05-07 |
Family
ID=90902106
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410191104.9A Pending CN117992851A (en) | 2024-02-21 | 2024-02-21 | Power grid power quality disturbance classification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117992851A (en) |
-
2024
- 2024-02-21 CN CN202410191104.9A patent/CN117992851A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Data-driven remaining useful life prediction via multiple sensor signals and deep long short-term memory neural network | |
| Deng et al. | Wind power forecasting methods based on deep learning: A survey | |
| Yang et al. | Remaining useful life prediction based on denoising technique and deep neural network for lithium-ion capacitors | |
| Zhang et al. | Time series anomaly detection for smart grids: A survey | |
| Li et al. | Online dynamic security assessment of wind integrated power system using SDAE with SVM ensemble boosting learner | |
| Fu et al. | Correlation analysis and augmentation of samples for a bidirectional gate recurrent unit network for the remaining useful life prediction of bearings | |
| CN116245033B (en) | Artificial intelligent driven power system analysis method and intelligent software platform | |
| Kaplan et al. | A novel method based on Weibull distribution for short-term wind speed prediction | |
| Guo et al. | AI-oriented smart power system transient stability: the rationality, applications, challenges and future opportunities | |
| Xie et al. | Residual life prediction of lithium-ion batteries based on data preprocessing and a priori knowledge-assisted CNN-LSTM | |
| Yan et al. | Deep learning technology for chiller faults diagnosis | |
| Sun et al. | The CEEMD-LSTM-ARIMA model and its application in time series prediction | |
| CN116485031A (en) | Method, device, equipment and storage medium for predicting short-term power load | |
| Jia et al. | DC-DC Buck circuit fault diagnosis with insufficient state data based on deep model and transfer strategy | |
| Haiqiang et al. | Ultra‐short‐term wind speed forecasting method based on spatial and temporal correlation models | |
| CN117332898A (en) | New energy small time scale power time sequence rolling prediction method based on machine learning | |
| CN115796231B (en) | Temporal analysis ultra-short term wind speed prediction method | |
| CN116859255A (en) | Method, device, equipment and medium for predicting state of health of energy storage battery | |
| Lu et al. | Physics guided neural network: Remaining useful life prediction of rolling bearings using long short-term memory network through dynamic weighting of degradation process | |
| Xiong et al. | Forecasting ultra‐short‐term wind power by multiview gated recurrent unit neural network | |
| CN117992851A (en) | Power grid power quality disturbance classification method and device, electronic equipment and storage medium | |
| Xu et al. | NWP feature selection and GCN-based ultra-short-term wind farm cluster power forecasting method | |
| Khetarpal et al. | Power quality disturbance signal segmentation and classification based on modified BI‐LSTM with double attention mechanism | |
| CN114971062A (en) | Photovoltaic power prediction method and device | |
| CN114818455A (en) | Power system multi-agent transient state stability judging method and system for small amount of PMU sampling |
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 |