Power system monitoring method and system

Abstract

The invention relates to an electric power system monitoring method and system, and the method comprises the steps: obtaining first information, the first information comprises a collection frequency corresponding to the electric power data of an electric power system, and the electric power system comprises an electric power system employing solar energy for power supply; acquiring an electric energy signal of the power system according to the first information; de-noising processing is carried out on the electric energy signal of the electric power system to obtain the de-noised electric energy signal; performing feature extraction on the denoised electric energy signal to obtain feature information; and judging whether the electric energy signal of the electric power system is an electric energy quality disturbance signal according to the characteristic information to obtain a monitoring result, and realizing accurate monitoring of the electric power system taking renewable energy sources such as wind energy or solar energy as power supply energy.

Description

Technical Field

[0001] The present invention relates to the technical field of power system monitoring, and in particular to a power system monitoring method and system. Background Art

[0002] With the increasing severity of environmental pollution, some renewable energy sources such as solar energy and wind energy will be used to assist in power generation when a power system fails. However, due to the unstable factors of energy sources such as solar energy or wind energy, there are unstable factors in the power supply of the power system. Therefore, there is an urgent need for a power system monitoring method that can effectively monitor the power system to ensure the safe operation of the ship. Summary of the invention

[0003] The object of the present invention is to provide a power system monitoring method and system to improve the above-mentioned problem.

[0004] In order to achieve the above objectives, the present application provides the following technical solutions:

[0005] In one aspect, an embodiment of the present application provides a method for monitoring a power system, the method comprising:

[0006] Acquire first information, the first information including a collection frequency corresponding to power data of a power system, the power system including a power system powered by solar energy;

[0007] collecting electric energy signals of the electric power system according to the first information;

[0008] Performing denoising processing on the electric energy signal of the electric power system to obtain a denoised electric energy signal;

[0009] Extracting features of the denoised electric energy signal to obtain feature information;

[0010] It is determined whether the electric energy signal of the electric power system is a power quality disturbance signal according to the characteristic information to obtain a monitoring result.

[0011] In a second aspect, an embodiment of the present application provides a power system monitoring system, the system comprising:

[0012] An acquisition module, configured to acquire first information, wherein the first information includes a collection frequency corresponding to power data of a power system, wherein the power system includes a power system powered by solar energy;

[0013] A first processing module, configured to collect an electric energy signal of the power system according to the first information;

[0014] A second processing module is used to perform denoising on the electric energy signal of the electric power system to obtain a denoised electric energy signal;

[0015] A third processing module is used to extract features from the denoised electric energy signal to obtain feature information;

[0016] The fourth processing module is used to determine whether the power signal of the power system is a power quality disturbance signal according to the characteristic information, and obtain a monitoring result.

[0017] In a third aspect, an embodiment of the present application provides a device, the device comprising a memory and a processor. The memory is used to store a computer program; the processor is used to implement the steps of the above-mentioned power system monitoring method when executing the computer program.

[0018] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned power system monitoring method are implemented.

[0019] The beneficial effects of the present invention are:

[0020] The present invention acquires the collection frequency corresponding to the power data of the power system, collects the electric energy signal of the power system based on the collection frequency, effectively ensures the data quality, thereby improving the data processing efficiency, denoises the electric energy signal to obtain the denoised electric energy signal, and then extracts features from the denoised electric energy signal to obtain feature information, thereby judging whether the electric energy signal of the power system is abnormal based on the feature information, thereby realizing accurate monitoring of the power system that uses renewable energy such as wind energy or solar energy as power supply energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 It is a flowchart of the power system monitoring method described in an embodiment of the present invention.

[0023] Figure 2 Schematic diagram of the topological structure of the power system monitoring system described in an embodiment of the present invention.

[0024] Figure 3 It is a schematic diagram of the structure of the power system monitoring device described in an embodiment of the present invention.

[0025] Labels in the figure: 800, power system monitoring equipment; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0027] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0028] Embodiment 1:

[0029] This embodiment provides a method for monitoring an electric power system. It can be understood that a scenario can be laid out in this embodiment, for example: a scenario for monitoring an electric power system powered by solar energy. Particularly preferably, the electric power system can be used as a ship electric power system.

[0030] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4 and step S5, which specifically include:

[0031] Step S1, obtaining first information, wherein the first information includes a collection frequency corresponding to power data of a power system, wherein the power system includes a power system powered by solar energy;

[0032] Since the power systems of certain specific application scenarios (such as ships, etc.) have extremely high requirements on the stability of the power grid, when the power system uses solar energy for auxiliary power supply, the quality of the power data collected needs to be extremely high to ensure the accuracy of monitoring the power system. It should be noted that the power data includes but is not limited to current data, voltage data, power, frequency, and load type.

[0033] The step S1 also includes step S11, step S12, step S13 and step S14, which specifically include:

[0034] Step S11: Acquire historical power data of the power system to reflect the relationship between load changes and data collection requirements.

[0035] Step S12, preprocessing the historical power data of the power system to obtain preprocessed historical power data; in this step, the preprocessing of the historical power data of the power system includes cleaning the data, processing missing values, outliers and noise to ensure data quality.

[0036] Step S13: constructing a training model based on the preprocessed historical power data to generate a power model, wherein the power model is used to predict the load of the power system;

[0037] In this step, the power model selects the LSTM neural network, which can effectively capture the time series characteristics of historical data, thereby better reflecting the changing trend of the load.

[0038] Step S2: collecting electric energy signals of the electric power system according to the first information. Thus, the electric energy signals can be collected based on a real-time optimized collection frequency, which can effectively ensure the data quality of the electric energy signals.

[0039] Step S3, performing denoising processing on the electric energy signal of the electric power system to obtain a denoised electric energy signal;

[0040] Step S4, extracting features from the denoised electric energy signal to obtain feature information;

[0041] The step S4 also includes step S41, step S42, step S43 and step S44, which specifically include:

[0042] Step S41, performing Laplace transform on the denoised electric energy signal to obtain a frequency spectrum of the electric energy signal;

[0043] In this step, the Laplace transform indicates the time-frequency information in the time series. This transform only produces a frequency-based result, and gives the real and imaginary spectrum information at the same time. The basis function of the Laplace function is a sine-Gaussian modulation function, which makes it possible to use the frequency of the sine wave to perform time-frequency analysis. Like the Fourier transform, the Laplace transform has the advantage of signal format conversion, which can quickly transform from the time domain to the time-frequency domain without loss. Therefore, the spectrum diagram of the power signal can be obtained by performing Laplace transform on the denoised power signal.

[0044] Step S42, performing TT transformation on the denoised electric energy signal to obtain a time domain diagram of the electric energy signal;

[0045] In this step, the TT transformation can transform the one-dimensional signal in the time domain into a two-dimensional signal in the time-time domain. The TT transformation of the denoised electric energy signal can obtain the time domain diagram of the electric energy signal.

[0046] Step S43, calculating the standard deviation and average value of the highest frequency contour line in the time-frequency contour line according to the time domain diagram of the electric energy signal, to obtain the first characteristic information;

[0047] Step S44: Calculate the standard deviation of the frequency amplitude envelope and the average value of the square root of the frequency standard deviation curve according to the frequency spectrum of the electric energy signal to obtain second feature information.

[0048] Specifically, in step S44, the characteristic curves in the spectrum diagram, namely the frequency amplitude envelope and the frequency standard deviation curve, are first extracted, and then the frequency amplitude envelope standard deviation is calculated based on the frequency amplitude envelope, and the average value of the square root of the frequency standard deviation curve is calculated based on the frequency standard deviation curve to obtain the second characteristic information of the electric energy signal.

[0049] Therefore, by extracting the first characteristic information and the second characteristic information from the electric energy signal, the amount of data processing of the subsequent neural network model can be effectively reduced, thereby improving the detection speed and accuracy of the electric energy signal.

[0050] Step S5: determine whether the electric energy signal of the power system is a power quality disturbance signal according to the characteristic information, and obtain a monitoring result.

[0051] When the power signal of the power system is a power quality disturbance signal, it can be determined that the current power signal interferes with the power quality. During the power supply process, power fluctuations may create safety hazards. Therefore, when the monitoring result shows that the power signal of the power system is a power quality disturbance signal, predictions can be made for relevant staff to remind them that there are risks in the current power system.

[0052] Step S6: when the electric energy signal is a power quality disturbance signal, determining the type of the power quality disturbance signal and obtaining type information;

[0053] Step S7: establishing an optimization model according to the type information. Specifically, step S7 includes step S71 and step S72:

[0054] Step S71: when the type information is voltage surge, establishing a first optimization function and constraint conditions, wherein the first optimization function is used to minimize the power quality disturbance signal;

[0055] In this step, the first optimization function specifically includes:

[0056] J min =a 1 ·V+a 2 ·T+a 3 ·E+a 4 ·R+a 5 ·C

[0057] In the above formula, J min It represents the power quality disturbance index; V represents the peak value of voltage surge; T represents the duration of voltage surge; E represents the energy of voltage surge; R represents the response of load to voltage surge; C represents the coordination coefficient of voltage protection device; a 1 -a 5 They respectively represent the corresponding weight coefficients, which are used to adjust the importance of different factors in the first objective function according to actual conditions and priorities.

[0058] In this step, the constraints specifically include:

[0059]

[0060] In the above formula, V represents the peak value of the voltage surge, V max Indicates the maximum safe voltage of the power system; T indicates the duration of the voltage surge, T max Indicates the safety time threshold.

[0061] Step S72: Optimize the power data of the power system according to the first optimization function and the constraint conditions.

[0062] In this embodiment, the first optimization function and constraints can be used to determine how to modify the power data of the power system, thereby optimizing the power system and reducing the impact of the power quality disturbance signal on the power system, so that the power system can be restored to stability in a timely manner.

[0063] Step S8: Optimize the power data of the power system according to the optimization model.

[0064] Therefore, this embodiment can not only provide danger warning for the power system, but also realize corresponding power data optimization according to the type of power quality disturbance signal, so as to respond to the danger quickly, and maintain the stable operation of the power system while accurately monitoring the power system.

[0065] Embodiment 2:

[0066] The difference between this embodiment and embodiment 1 is that step S14, determining the acquisition frequency corresponding to the power data of the power system based on the power model, specifically includes the following steps:

[0067] Step S141, sending the real-time collected power data to the power model to obtain a prediction result, wherein the prediction result includes a change trend of the power system load;

[0068] Step S142: determining an expected acquisition frequency according to the prediction result; the expected acquisition frequency is determined according to the performance requirements and load characteristics of the power system.

[0069] Step S143, calculating according to the expected acquisition frequency and the actual acquisition frequency to obtain an acquisition frequency error;

[0070] Step S144: Process the acquisition frequency error using a PID algorithm to obtain an output result, wherein the output result includes the acquisition frequency value that needs to be adjusted.

[0071] Therefore, in this step, the acquisition frequency error is used as the input of the PID controller, and the acquisition frequency value that needs to be adjusted is calculated by the PID controller as the output result, and it is synchronized to the data acquisition system in the power system to adjust the frequency of data acquisition. The PID parameters can be adjusted in real time through feedback from the power system, thereby realizing dynamic adjustment of the acquisition frequency.

[0072] Therefore, the above steps can realize real-time optimization and adjustment of the collection frequency of power data, while reducing the amount of processed data, ensuring data quality, effectively improving data processing efficiency, and improving monitoring speed and monitoring accuracy.

[0073] Furthermore, step S3, performing denoising processing on the electric energy signal of the electric power system to obtain the denoised electric energy signal, specifically comprises the following steps:

[0074] Step S31, using dual-tree complex wavelet transform to process the electric energy signal of the electric power system to obtain wavelet coefficients;

[0075] Step S32, processing the wavelet coefficients using a maximum a posteriori estimation mathematical model to obtain processed wavelet coefficients;

[0076] In this step, the wavelet coefficients are processed by the maximum a posteriori estimation mathematical model. Specifically, the noise variance and signal variance are estimated by the maximum a posteriori estimation method for the detail coefficients of different levels of the signal dual-tree complex wavelet decomposition, and the threshold of each layer is calculated to perform threshold processing on the wavelet coefficients.

[0077] Step S33: inversely transform the processed wavelet coefficients to obtain a denoised electric energy signal.

[0078] Therefore, in this embodiment, the electric energy signal of the power system may be denoised through step S3.

[0079] Further, step S5, judging whether the power signal of the power system is a power quality disturbance signal according to the characteristic information, and obtaining a monitoring result, specifically comprises the following steps:

[0080] Step S51, obtaining disturbance characteristic information of at least one power quality disturbance signal and an initialized BP neural network model;

[0081] Among them, the disturbance characteristic information of the power quality disturbance signal includes one or more of the disturbance characteristic information of the power quality disturbance signal corresponding to voltage sag, voltage surge, voltage transient, voltage interruption, flicker, etc., among which the above-mentioned disturbance characteristic information is the first characteristic information and the second characteristic information of each power quality disturbance signal.

[0082] Step S52: constructing a sample set based on disturbance feature information of at least one of the power quality disturbance signals;

[0083] Step S53, sending the sample set to the initialized BP neural network model for training to obtain a trained BP neural network model;

[0084] Step S54: sending the characteristic information to the trained BP neural network model to obtain a monitoring result, wherein the monitoring result includes whether the electric energy signal is a power quality disturbance signal or the electric energy signal is not a power quality disturbance signal.

[0085] In this step, since the S transform and TT transform of the power quality disturbance signal have their unique characteristics, sending the feature information to the trained BP neural network model can accurately determine whether the power signal belongs to the power quality disturbance signal, and at the same time identify what kind of power quality disturbance signal it is, so that the staff can make timely adjustments to the power system to ensure the stable operation of the power system.

[0086] Embodiment 3:

[0087] like Figure 2 As shown, this embodiment provides a power system monitoring system, the system includes an acquisition module, a first processing module, a second processing module, a third processing module and a fourth processing module, which specifically include:

[0088] An acquisition module, configured to acquire first information, wherein the first information includes a collection frequency corresponding to power data of a power system, wherein the power system includes a power system powered by solar energy;

[0089] A first processing module, configured to collect an electric energy signal of the power system according to the first information;

[0090] A second processing module is used to perform denoising on the electric energy signal of the electric power system to obtain a denoised electric energy signal;

[0091] A third processing module is used to extract features from the denoised electric energy signal to obtain feature information;

[0092] The fourth processing module is used to determine whether the power signal of the power system is a power quality disturbance signal according to the characteristic information, and obtain a monitoring result.

[0093] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0094] Embodiment 3:

[0095] Corresponding to the above method embodiment, this embodiment further provides a power system monitoring device, and the power system monitoring device described below and the power system monitoring method described above can refer to each other.

[0096] Figure 3 FIG. 8 is a block diagram of a power system monitoring device 800 according to an exemplary embodiment. Figure 3 As shown, the power system monitoring device 800 may include: a processor 801 and a memory 802. The power system monitoring device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0097] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned power system monitoring method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the power system monitoring device 800 to complete the power system monitoring method described in the above-mentioned embodiment 1 or 2.

[0098] Embodiment 5:

[0099] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the power system monitoring method described above can refer to each other.

[0100] The above-mentioned readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the power system monitoring method described in the above-mentioned method embodiment 1 or 2 are implemented.

[0101] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0102] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A power system monitoring method, characterized in that: include: Acquire first information, the first information including a collection frequency corresponding to power data of a power system, the power system including a power system powered by solar energy; collecting electric energy signals of the electric power system according to the first information; Performing denoising processing on the electric energy signal of the electric power system to obtain a denoised electric energy signal; Extracting features of the denoised electric energy signal to obtain feature information; It is determined whether the electric energy signal of the electric power system is a power quality disturbance signal according to the characteristic information to obtain a monitoring result.

2. The power system monitoring method according to claim 1, characterized in that: Acquiring the first information, including Obtain historical power data of the power system; Preprocessing the historical power data of the power system to obtain preprocessed historical power data; Building a training model based on the preprocessed historical power data to generate a power model, wherein the power model is used to predict the load of the power system; A collection frequency corresponding to the power data of the power system is determined based on the power model.

3. The power system monitoring method according to claim 2, characterized in that: Determining a collection frequency corresponding to power data of the power system based on the power model includes: Sending the real-time collected power data to the power model to obtain prediction results, which include the change trend of the power system load; Determining an expected acquisition frequency according to the prediction result; Calculating according to the expected acquisition frequency and the actual acquisition frequency to obtain an acquisition frequency error; The acquisition frequency error is processed using a PID algorithm to obtain an output result, wherein the output result includes an acquisition frequency value that needs to be adjusted.

4. The power system monitoring method according to claim 1, characterized in that: The denoised electric energy signal is subjected to feature extraction to obtain feature information, including: Performing Laplace transform on the denoised electric energy signal to obtain a frequency spectrum of the electric energy signal; Performing TT transformation on the denoised electric energy signal to obtain a time domain diagram of the electric energy signal; Calculate the standard deviation and average value of the highest frequency contour line in the time-frequency contour line according to the time domain diagram of the electric energy signal to obtain the first feature information; The standard deviation of the frequency amplitude envelope and the average value of the square root of the frequency standard deviation curve are calculated according to the frequency spectrum of the electric energy signal to obtain the second characteristic information.

5. The power system monitoring method according to claim 1, characterized in that: Judging whether the electric energy signal of the electric power system is a power quality disturbance signal according to the characteristic information, and obtaining a monitoring result, including: Acquire disturbance characteristic information of at least one power quality disturbance signal and an initialized BP neural network model; Constructing a sample set based on disturbance characteristic information of at least one power quality disturbance signal; Sending the sample set to the initialized BP neural network model for training to obtain a trained BP neural network model; The characteristic information is sent to the trained BP neural network model to obtain a monitoring result, wherein the monitoring result includes whether the electric energy signal is a power quality disturbance signal or the electric energy signal is not a power quality disturbance signal.

6. The power system monitoring method according to claim 1, characterized in that: De-noising the electric energy signal of the electric power system to obtain the de-noised electric energy signal, including: Processing the electric energy signal of the electric power system by using dual-tree complex wavelet transform to obtain wavelet coefficients; Processing the wavelet coefficients using a maximum a posteriori estimation mathematical model to obtain processed wavelet coefficients; The processed wavelet coefficients are inversely transformed to obtain a denoised electric energy signal.

7. The power system monitoring method according to claim 1, characterized in that: After determining whether the electric energy signal of the electric power system is a power quality disturbance signal according to the characteristic information and obtaining the monitoring result, the method includes: When the electric energy signal is a power quality disturbance signal, determining the type of the power quality disturbance signal and obtaining type information; Establishing an optimization model according to the type information; The power data of the power system is optimized according to the optimization model.

8. The power system monitoring method according to claim 7, characterized in that: Establishing an optimization model according to the type information includes: When the type information is voltage surge, establishing a first optimization function and constraint conditions, wherein the first optimization function is used to minimize the power quality disturbance signal; The power data of the power system is optimized according to the first optimization function and the constraint condition.

9. The power system monitoring method according to claim 8, characterized in that: The first optimization function is specifically: J min =a1·V+a2·T+a3·E+a4·R+a5·C In the above formula, J min It represents the power quality disturbance index; V represents the peak value of voltage swell; T represents the duration of voltage swell; E represents the energy of voltage swell; R represents the response of load to voltage swell; C represents the coordination coefficient of voltage protection system; a1-a5 represent the corresponding weight coefficients, which are used to adjust the importance of different factors in the first objective function according to actual conditions and priorities.

10. A power system monitoring system, characterized in that: include: An acquisition module, configured to acquire first information, wherein the first information includes a collection frequency corresponding to power data of a power system, wherein the power system includes a power system powered by solar energy; A first processing module, configured to collect an electric energy signal of the power system according to the first information; A second processing module is used to perform denoising on the electric energy signal of the electric power system to obtain a denoised electric energy signal; A third processing module is used to extract features from the denoised electric energy signal to obtain feature information; The fourth processing module is used to determine whether the power signal of the power system is a power quality disturbance signal according to the characteristic information, and obtain a monitoring result.

Images