Communication signal recovery method, device and equipment of power distribution network, medium and product

Abstract

The invention discloses a communication signal recovery method and device for a power distribution network, equipment, a medium and a product. The method comprises the following steps: acquiring initial communication signals of the power distribution network on a plurality of signal propagation paths; performing weighted synthesis on each initial communication signal to obtain a weighted signal, performing frequency domain enhancement on the weighted signal to obtain an enhanced signal, and judging whether the enhanced signal has a missing signal; and if the missing signal exists, reconstructing and correcting the missing signal to obtain a complete signal, inputting the complete signal into a preset adaptive filter to eliminate interference components to obtain an effective signal, and performing signal enhancement on the effective signal to obtain a recovered communication signal of the power distribution network, the preset adaptive filter is obtained by performing parameter optimization based on historical prediction interference data. According to the invention, the communication quality of the power system can be improved by recovering the communication signal of the power distribution network.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power distribution network communication, in particular to a communication signal recovery method, device, equipment, medium and product of a power distribution network. BACKGROUND

[0002] As a key component of the power system, the communication quality of the power distribution network directly affects the reliability and timeliness of core functions such as power dispatching, fault detection, and device control. The power distribution network mainly relies on low-voltage carrier communication (PLC) technology to achieve signal transmission. However, in actual operation, electromagnetic interference generated by power equipment, superimposed distortion caused by signal multi-path propagation, and signal attenuation and loss in complex environments can cause communication signal distortion, increased error rate, or even transmission interruption, seriously affecting the accuracy and stability of power distribution network data transmission.

[0003] Existing technologies mainly recover the communication signals of the power distribution network through fixed filtering, traditional error correction, and simple signal enhancement methods. However, these technologies do not fundamentally solve the problems of signal distortion and attenuation, and the error rate remains high during communication. In some cases, the signal loss cannot be effectively completed, ultimately resulting in insufficient stability and reliability of the power distribution network communication system, making it difficult to meet the demand for high-quality communication in complex power environments. SUMMARY

[0004] The present application provides a communication signal recovery method, device, equipment, medium and product for a power distribution network, which can recover the communication signals of the power distribution network to improve the communication quality of the power system.

[0005] In a first aspect, an embodiment of the present application provides a communication signal recovery method for a power distribution network, comprising:

[0006] Obtaining initial communication signals of the power distribution network on a plurality of signal propagation paths;

[0007] Weightedly combining the initial communication signals to obtain a weighted signal, and performing frequency domain enhancement on the weighted signal to obtain an enhanced signal, and determining whether the enhanced signal has a missing signal;

[0008] If the missing signal exists, reconstructing and correcting the missing signal to obtain a complete signal, inputting the complete signal into a preset adaptive filter to remove interference components to obtain an effective signal, and performing signal enhancement on the effective signal to obtain the recovered communication signal of the power distribution network, wherein the preset adaptive filter is obtained by parameter optimization based on historical predicted interference data.

[0009] In this way, by acquiring initial communication signals on a plurality of signal propagation paths of the power distribution network, the transmission state of the same signal on different paths can be acquired, the feasibility of signal recovery is guaranteed from the source, and the communication quality of the power system is improved; the initial communication signals on different propagation paths are weighted and combined to obtain a weighted signal, which can offset the adverse effects of multi-path propagation on the signal, and the signal quality is improved to help signal recovery and improve communication quality; it is judged whether the enhanced signal exists missing signal, and the missing signal is reconstructed and corrected to obtain complete signal, which can ensure the integrity and accuracy of the signal, to help signal recovery and improve communication quality; the complete signal is input into the adaptive filter based on the historical prediction interference data to obtain the effective signal, which can remove the residual interference, and then the effective signal is enhanced to obtain the recovered target signal, realizing effective recovery of the power distribution network communication signal, and finally improving the communication quality of the power system. The communication signal of the power distribution network can be recovered to improve the communication quality of the power system.

[0010] Further, the optimization method of the preset adaptive filter specifically comprises:

[0011] The acquired historical communication signal is subjected to feature extraction to obtain historical interference features;

[0012] The initial interference signal in the historical communication signal is determined based on the historical interference features;

[0013] The initial interference signal is input into a preset prediction model to obtain the historical prediction interference data;

[0014] The parameters of an initial adaptive filter are adjusted based on the historical prediction interference data to obtain the preset adaptive filter after optimization.

[0015] In this way, by extracting interference features from historical communication signals, the initial interference signal in the historical communication signal can be accurately located, providing a feature basis for subsequent prediction of interference data; the initial interference signal is input into a preset prediction model to obtain historical prediction interference data, which can help to master the change rule of interference in advance and avoid the blindness of interference prediction; and then the parameters of the initial adaptive filter are adjusted based on the historical prediction interference data, which can make the filtering characteristics of the preset adaptive filter highly match the actual interference characteristics, greatly improve the pertinence and accuracy of the filter in removing interference components, and provide reliable support for the recovery of power distribution network communication signals, and finally further improve the communication quality of the power system.

[0016] Further, the feature extraction of the acquired historical communication signal to obtain historical interference features specifically comprises:

[0017] performing spectrum analysis on the obtained historical communication signal to obtain a frequency feature;

[0018] performing time domain analysis on the historical communication signal to obtain a time domain analysis result, and performing peak value detection based on the time domain analysis result to obtain an amplitude feature;

[0019] performing wavelet transform on the historical communication signal to obtain a time feature;

[0020] integrating the frequency feature, the amplitude feature and the time feature to obtain a historical interference feature.

[0021] In this way, the frequency feature is obtained by performing spectrum analysis on the historical communication signal, the distribution rule of the interference signal in the frequency dimension can be determined; the amplitude feature is obtained by performing time domain analysis and peak value detection, abnormal fluctuations of the interference signal in signal strength can be captured; the time feature is obtained by means of wavelet transform, the time node and the duration of the interference signal can be mastered; the frequency, amplitude and time features are integrated into the historical interference feature, the characteristics of the interference signal can be obtained from multiple dimensions, the interference recognition deviation caused by a single feature can be avoided, the communication signal recovery quality is improved, and the communication quality of the power system is improved.

[0022] Further, the weighting and synthesizing of each initial communication signal to obtain a weighted signal specifically includes:

[0023] correlation values of each initial communication signal and a preset reference signal are calculated respectively, and corresponding time delay deviations are determined based on the correlation values, time synchronization is performed on each initial communication signal by using the time delay deviations to obtain corresponding synchronized signals;

[0024] time-frequency features are determined based on each synchronized signal, and interference separation is performed on the synchronized signal by using the time-frequency features to obtain separated signals;

[0025] each separated signal is weighted and synthesized with a preset weighting coefficient to obtain a weighted signal.

[0026] In this way, the time delay deviation is determined by calculating the cross-correlation values of the initial communication signal and the preset reference signal, and the time synchronization is realized based on the time delay deviation, the time difference of the signals in different propagation paths can be eliminated, the distortion caused by the asynchronous signals in the weighting and synthesizing process is avoided, and the basic accuracy of the subsequent signal recovery is ensured; the time-frequency features are determined based on the synchronized signal, and the interference separation is performed, part of the obvious interference components can be stripped in advance, the influence of the interference on the subsequent weighting and synthesizing is reduced, and the signal recovery quality is improved; the separated signal is weighted and synthesized with the preset weighting coefficient, the reasonable weight is allocated according to the quality of the signals in different paths, the overall quality of the weighted signal is further improved, the communication signal recovery effect is improved, and finally the communication quality of the power system is improved.

[0027] Further, if the missing signal exists, the missing signal is reconstructed and corrected to obtain a complete signal, specifically comprising:

[0028] determining a missing type of the missing signal, if the missing signal belongs to a first missing type, reconstructing the missing signal by using an interpolation method to obtain a first reconstructed signal, if the missing signal belongs to a second missing type, reconstructing the missing signal by using a compressed sensing method to obtain a second reconstructed signal;

[0029] performing error detection on the first reconstructed signal or the second reconstructed signal to obtain an error detection result, and correcting the error detection result to obtain the complete signal.

[0030] In this way, the missing type of the missing signal is first determined, the interpolation method is used for reconstruction for the first missing type, which can quickly fill in small-range and continuous signal missing; the compressed sensing method is used for reconstruction for the second missing type, which can accurately recover the signal based on signal sparsity when the signal missing ratio is high; error detection and correction are performed on the reconstructed signal, which can identify and correct errors possibly introduced in the reconstruction process, so as to ensure that the complete signal obtained finally is neither missing nor erroneous, and the reliability of the communication signal recovery of the power distribution network is improved, and the communication quality of the power system is improved.

[0031] Further, the effective signal is enhanced based on a gain factor to obtain the recovered communication signal of the power distribution network, specifically comprising: the effective signal is enhanced based on a gain factor to obtain the communication signal, wherein the gain factor is obtained by updating based on predicted interference data, and the predicted interference data is obtained by inputting the initial communication signal into a preset prediction model.

[0032] In this way, the gain factor is updated based on the predicted interference data obtained by the initial communication signal through the preset prediction model, which can make the adjustment of the gain factor real-time match the interference situation faced by the current signal; the effective signal is enhanced based on the dynamically updated gain factor, which can maximize the retention of the effective signal information while accurately resisting the current interference, and finally ensure the recovery quality of the communication signal of the power distribution network and improve the communication quality of the power system.

[0033] In a second aspect, an embodiment of the present application provides a communication signal recovery device of a power distribution network, comprising a first module, a second module and a third module.

[0034] The first module is used for acquiring initial communication signals of a power distribution network on a plurality of signal propagation paths.

[0035] The second module is configured to synthesize the initial communication signals to obtain a weighted signal, and perform frequency domain enhancement on the weighted signal to obtain an enhanced signal, and determine whether the enhanced signal has a missing signal.

[0036] The third module is configured to reconstruct and correct the missing signal to obtain a complete signal, input the complete signal into a preset adaptive filter to remove interference components to obtain an effective signal, perform signal enhancement on the effective signal to obtain a recovered communication signal of the power distribution network, and the preset adaptive filter is obtained based on historical predicted interference data.

[0037] In this way, the first module obtains initial communication signals on a plurality of signal propagation paths of the power distribution network, the transmission state of the same signal on different paths is obtained, the feasibility of signal recovery is ensured from the source, and the communication quality of the power system is improved. The second module synthesizes the initial communication signals on different propagation paths to obtain a weighted signal, which can offset the adverse effects of multi-path propagation on the signal, and the signal quality is improved to help signal recovery and improve communication quality. The third module reconstructs and corrects the missing signal to obtain a complete signal, which can ensure the integrity and accuracy of the signal to help signal recovery and improve communication quality. The complete signal is input into an adaptive filter based on historical predicted interference data to remove interference components to obtain an effective signal, which can remove residual interference, and the effective signal is enhanced to obtain a recovered target signal, which realizes effective recovery of the communication signal of the power distribution network, and finally improves the communication quality of the power system. The present application can recover the communication signal of the power distribution network to improve the communication quality of the power system.

[0038] In a third aspect, another embodiment of the present application provides a terminal device, comprising: a processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface complete communication with each other through the communication bus;

[0039] The memory is used to store at least one executable instruction, and the executable instruction makes the processor execute the operation of the power distribution network communication signal recovery method.

[0040] In a fourth aspect, another embodiment of the present application provides a computer readable storage medium, which comprises a stored computer program, wherein when the computer program runs, it controls the device or apparatus where the computer readable storage medium is located to execute the power distribution network communication signal recovery method.

[0041] In a fifth aspect, another embodiment of the present application provides a computer program product comprising computer programs or instructions, which, when executed by a communication device, implement the communication signal recovery method of the power distribution network. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0043] Figure 1 is a flowchart of an embodiment of the communication signal recovery method of the power distribution network provided by the present application;

[0044] Figure 2 is a flowchart of steps S201 to S204 provided by the present application;

[0045] Figure 3 is a structural diagram of the communication signal recovery device of the power distribution network provided by the present application. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and advantages of the present application more clear, the technical solutions in the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort fall within the scope of protection of the present application.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "include" and "have" and any variations thereof in the specification and claims of the present application and the above description of drawings are intended to cover non-exclusive inclusion.

[0048] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "a plurality of" is two or more, unless otherwise explicitly and specifically limited.

[0049] Reference to an“embodiment” herein means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase that the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of other embodiments. It is explicitly contemplated that embodiments described herein can be combined with other embodiments in combinations other than the ones explicitly presented if such embodiments result in equivalent systems.

[0050] In the description of the embodiments of the application, the term“and / or” only means an association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character“ / ” herein generally means that the front and rear associated objects are in an“or” relationship.

[0051] In the description of the embodiments of the application, the term“a plurality of” means more than two (including two), and similarly, “a plurality of groups” means more than two groups (including two groups), and “a plurality of pieces” means more than two pieces (including two pieces).

[0052] In the description of the embodiments of the application, unless otherwise explicitly specified and limited, the technical terms“mounting”,“connection”,“connection”,“fixing” and the like should be understood in a broad sense, for example, it can be fixedly connected, or it can be detachably connected, or it can be integrated; it can be mechanical connection, or it can be electrical connection; it can be directly connected, or it can be indirectly connected through an intermediate medium; it can be the internal communication of two elements or the interaction relationship between two elements. For those skilled in the art, the specific meaning of the above terms in the embodiments of the application can be understood according to the specific circumstances.

[0053] In the field of power distribution network communication, the communication quality of the power distribution network is the key to guarantee the reliable operation of the core functions such as power dispatching and fault detection, but the current power distribution network signal recovery faces significant challenges. The existing technology has defects: the signal recovery only relies on fixed filtering, traditional error correction and simple enhancement methods, and the signal distortion attenuation problem is not fundamentally solved, and the signal loss cannot be effectively completed, resulting in insufficient stability and reliability of the communication system, which is difficult to meet the high-quality communication demand in complex power environment.

[0054] Reference Figure 1 In order to improve the communication quality of the power system by recovering the communication signal of the power distribution network, an embodiment of the application provides a communication signal recovery method of a power distribution network, comprising steps S101 to S103.

[0055] Step S101, obtaining initial communication signals of the power distribution network on a plurality of signal propagation paths;

[0056] In some embodiments, the acquiring the initial communication signals on the plurality of signal propagation paths of the power distribution network comprises: deploying signal receiving devices at a plurality of signal collection nodes of the power distribution network, each signal collection node corresponding to a different signal propagation path in the power distribution network; and synchronously collecting the initial communication signals transmitted in the power distribution network by the signal receiving devices.

[0057] In step S102, the initial communication signals are weighted and combined to obtain a weighted signal, and the weighted signal is enhanced in a frequency domain to obtain an enhanced signal, and it is determined whether the enhanced signal is missing.

[0058] In some embodiments, the weighting and combining of the initial communication signals to obtain a weighted signal comprises: calculating a cross-correlation value of each initial communication signal and a preset reference signal, respectively, determining a time delay deviation based on each cross-correlation value, time-synchronizing each initial communication signal by using each time delay deviation to obtain a corresponding synchronized signal, determining a time-frequency feature based on each synchronized signal, and separating interference from the synchronized signal by using each time-frequency feature to obtain a separated signal, and weighting and combining each separated signal with a preset weighting coefficient to obtain a weighted signal. Specifically, a preset reference signal in a power distribution network communication scenario is determined; for each initial communication signal, a cross-correlation calculation is performed between the initial communication signal and the preset reference signal to obtain a cross-correlation value of each initial communication signal relative to the reference signal; according to the variation law of the cross-correlation value, a maximum cross-correlation value is found, and a time delay deviation is determined based on the maximum cross-correlation value; the time axis of each initial communication signal is adjusted according to the obtained time delay deviation to obtain a corresponding synchronized signal of each propagation path; a short-time Fourier transform (STFT) is used to analyze the time-frequency of each synchronized signal to obtain a time-frequency feature; based on the extracted time-frequency feature, a blind source separation (BSS) technique is used to process the synchronized signal to separate the independent effective signal component from the interference signal component in the synchronized signal, remove the interference component, and only retain the effective signal component to obtain a separated signal corresponding to each synchronized signal; a preset weighting coefficient is calculated with each separated signal to obtain a weighted component of each separated signal, and the weighted components of all separated signals are superimposed and summed to obtain a final weighted signal.

[0059] It should be noted that the weighting coefficient is obtained by optimizing the minimum mean square error (MMSE) criterion with the goal of minimizing the distortion of the superimposed multi-path signal; the preset reference signal is a standard interference-free signal in power distribution network communication, which is used as a reference for signal synchronization and quality comparison, and has consistent frequency, phase, and amplitude characteristics with the original transmitted signal of the signal sending end; in addition to the short-time Fourier transform, the wavelet transform can also be used for time-frequency analysis.

[0060] In some embodiments, the combining the initial communication signals to obtain a weighted signal comprises:

[0061] Cross-correlation function:

[0062]

[0063] wherein x(t) represents a preset reference signal; y(t) represents an initial communication signal; τ represents a time delay; R xγ (τ) represents a cross-correlation value of x(t) and y(t) at delay τ;

[0064] Signal synchronization formula:

[0065] y synchronized (t) = y(t-Δt);

[0066] wherein y synchronized (t) represents a synchronization signal; Δt represents a time delay deviation; y(t) represents an initial communication signal;

[0067] Short-time Fourier transform formula:

[0068]

[0069] wherein x(τ) represents a time-domain representation of the synchronization signal; w(τ-t) represents a window function; f represents a frequency; t represents an analysis time parameter; τ represents a time variable for indexing the time-domain value of the synchronization signal; e -j2πfτ is a complex exponential base function of Fourier transform;

[0070] Basic linear mixing model expression of blind source separation:

[0071] y(t) = As(t);

[0072] wherein A represents a mixing matrix; s(t) represents a separation signal; y(t) represents a synchronization signal;

[0073] Signal weighting formula:

[0074]

[0075] wherein α n represents a weighting coefficient on path n; y total (t) represents a weighted signal; y n (t) represents a separation signal corresponding to path n; N represents a total path; n represents a path index;

[0076] Optimization formula of minimum mean square error criterion:

[0077]

[0078] wherein, a n represents the weighting coefficient on path n; y target (t) represents the expected target signal; y total (t) represents the weighted signal.

[0079] In this way, by calculating the cross-correlation value of the initial communication signal and the preset reference signal, the time delay deviation is determined, and time synchronization is realized based on the time delay deviation, which can eliminate the time difference of signals under different propagation paths, avoid the distortion of weighted synthesis caused by asynchronous signals, and ensure the basic accuracy of subsequent signal recovery; based on the synchronization signal, the time-frequency characteristics are determined and interference separation is performed, which can strip part of the obvious interference components in advance, reduce the influence of interference on subsequent weighted synthesis, and improve the signal recovery quality; the separated signal is weighted and synthesized with the preset weighting coefficient, which can reasonably allocate the weight according to the quality of the signals of different paths, further improve the overall quality of the weighted signal, promote the improvement of the communication signal recovery effect, and finally improve the communication quality of the power system.

[0080] In some embodiments, the frequency domain enhancement of the weighted signal to obtain an enhanced signal specifically includes: using fast Fourier transform (FFT) to convert the weighted signal from time domain to frequency domain to obtain the enhanced signal.

[0081] In some embodiments, the related formula of the frequency domain enhancement of the weighted signal to obtain an enhanced signal specifically includes:

[0082] Fast Fourier transform formula:

[0083] X enhanced (f) = X(f) · H(f);

[0084] wherein, X(f) represents the weighted signal; H(f) represents a frequency response function, which represents the enhancement or suppression of different frequency components.

[0085] In this way, by selecting a suitable frequency response function, the influence of multipath interference on the communication signal can be effectively reduced.

[0086] In some embodiments, the judging whether the enhanced signal has missing signal comprises: analyzing a time domain waveform of the enhanced signal, and determining that the signal has local missing when it is detected that amplitudes of continuous multiple sampling points in the waveform are lower than a preset noise threshold or the amplitudes are constant zero; decoding the enhanced signal in a packet switching based communication protocol, and checking sequence number continuity of data packets, and determining that there is data packet missing if the sequence number is discontinuous; calculating total energy of the enhanced signal in a power distribution network communication effective frequency band, and comparing the total energy with an energy level of historical normal signal, and determining that the signal has overall quality missing or serious attenuation if the current signal frequency band energy is significantly lower than the historical level.

[0087] In step S103, if the missing signal exists, the missing signal is reconstructed and corrected to obtain a complete signal, the complete signal is input into a preset adaptive filter to remove interference components to obtain an effective signal, the effective signal is signal enhanced to obtain a recovered power distribution network communication signal, and the preset adaptive filter is obtained based on parameter optimization of historical predicted interference data.

[0088] Please refer to Figure 2 In some embodiments, the optimization method of the preset adaptive filter comprises steps S201 to S204.

[0089] In step S201, historical communication signals are acquired and feature extraction is performed to obtain historical interference features.

[0090] In some embodiments, the feature extraction of the acquired historical communication signals to obtain historical interference features comprises: performing frequency spectrum analysis on the acquired historical communication signals to obtain frequency features; performing time domain analysis on the historical communication signals to obtain time domain analysis results, and performing peak value detection based on the time domain analysis results to obtain amplitude features; performing wavelet transform on the historical communication signals to obtain time features; and integrating the frequency features, the amplitude features and the time features to obtain historical interference features.

[0091] Specifically, the acquired historical communication signal is subjected to fast Fourier transform (FFT) for frequency domain conversion to obtain a frequency domain spectrum of the signal, the frequency components corresponding to the interference signal are identified by analyzing the spectrum, the center frequency and bandwidth of the interference signal are extracted to form a frequency feature; the historical communication signal is subjected to time domain waveform analysis, the amplitude variation of the signal is recorded, an amplitude threshold is set, the transient peak exceeding the threshold in the time domain waveform is detected, the peak amplitude and time interval of the peak are extracted to form an amplitude feature; the historical communication signal is subjected to wavelet transform, the local features of the signal under different time scales are captured by using the multi-resolution analysis capability of the wavelet transform, the instantaneous frequency (real-time frequency of the interference signal at a moment) and the instantaneous amplitude (real-time amplitude of the interference signal at a moment) of the interference signal at different time points are determined by analyzing the wavelet transform result to form a time feature; the extracted frequency feature, amplitude feature and time feature are integrated to form a historical interference feature containing the frequency, amplitude and time information of the interference signal.

[0092] In some embodiments, the feature extraction on the acquired historical communication signal to obtain the historical interference feature includes the following related formulas:

[0093] Fast Fourier transform formula:

[0094]

[0095] In the formula, X(f) is the frequency domain representation of the signal; x(t) represents the historical communication signal; t represents time; and f represents frequency.

[0096] Transient peak calculation formula:

[0097] Peak(x) = max(|x(t)|);

[0098] In the formula, Peak(x) represents the transient peak of the signal; x(t) represents the historical communication signal; and t represents time.

[0099] Wavelet transform formula:

[0100]

[0101] In the formula, a represents a scale factor; b represents a translation factor; ψ(t) represents a wavelet function; x(t) represents the historical communication signal; and t represents time.

[0102] In this way, frequency characteristics of the historical communication signal are obtained through spectrum analysis, the distribution rule of the interference signal in the frequency dimension can be determined; amplitude characteristics are obtained through time domain analysis and peak value detection, abnormal fluctuations of the interference signal in signal strength can be captured; time characteristics are obtained through wavelet transform, time nodes and duration of the interference signal can be mastered; the three types of characteristics of frequency, amplitude and time are integrated into historical interference characteristics, the characteristics of the interference signal can be obtained from multiple dimensions, interference recognition deviation caused by a single characteristic can be avoided, thereby improving the communication signal recovery quality and the communication quality of the power system.

[0103] In step S202, initial interference signals in the historical communication signal are determined based on the historical interference characteristics.

[0104] In some embodiments, the determination of the initial interference signals in the historical communication signal based on the historical interference characteristics specifically includes: using a classification algorithm to classify signals in combination with the historical interference characteristics, judging whether the signals are interference signals, and determining the initial interference signals based on the classification results.

[0105] It should be noted that a support vector machine (SVM) or K-nearest neighbor (K-NN) can be selected as the classification algorithm.

[0106] In step S203, the initial interference signals are input into a preset prediction model to obtain the historical predicted interference data.

[0107] In some embodiments, the input of the initial interference signals into the preset prediction model to obtain the historical predicted interference data specifically includes: inputting the historical interference characteristics corresponding to the initial interference signals in the form of a feature vector into the preset prediction model, the prediction model generates historical prediction parameters by learning the mapping relationship between the characteristics of the initial interference signals and the evolution rule of the historical interference, and the prediction parameters are arranged in a time sequence to form the historical predicted interference data.

[0108] In some embodiments, the training process of the preset prediction model specifically includes: performing feature extraction on the collected initial interference signal samples to obtain interference feature vectors, inputting the interference feature vectors into a machine learning model as training data, training an interference prediction function in the model to minimize prediction error, and obtaining the prediction model until a preset condition is met.

[0109] In some embodiments, the related formula of the training process of the preset prediction model specifically includes:

[0110] The formula for minimizing the prediction error is:

[0111]

[0112] In the formula, n represents the number of samples, f(x) represents the prediction function, and x represents the input of the prediction function.i represents a prediction function; x i represents an interference feature vector of the i th sample; y i represents actual interference data of the i th sample; n represents the number of samples.

[0113] Step S204, adjusting the parameters of the initial adaptive filter based on the historical predicted interference data, to obtain the preset adaptive filter after optimization.

[0114] In some embodiments, the adjusting of the parameters of the initial adaptive filter based on the historical predicted interference data to obtain the preset adaptive filter after optimization specifically comprises:

[0115] The interference parameters are extracted from the historical predicted interference data as a target reference set for initial adaptive filter parameter adjustment. The to-be-optimized parameters of the initial adaptive filter are determined in combination with adaptive filtering requirements, and the core dimension of parameter adjustment is clarified. The interference parameters in the target reference set and the normal communication signal benchmark are used to determine the parameter adjustment boundary, with the maximum interference suppression attenuation and the minimum normal signal distortion as the optimization target. The historical predicted interference data are used to generate a simulated input signal, and the normal communication signal without interference is used as an expected signal. The LMS algorithm is used to calculate the filtering error, and the filter coefficient and step factor are iteratively adjusted according to the coefficient update formula. After each round of adjustment, the interference suppression effect and signal fidelity of the filter output signal are verified through a preset verification rule. When the preset verification rule is met, the current filter parameters are solidified, a parameter adjustment log is generated, and the preset adaptive filter after optimization that adapts to the historical predicted interference characteristics is obtained.

[0116] In some embodiments, the related formula for adjusting the parameters of the initial adaptive filter based on the historical predicted interference data to obtain the preset adaptive filter after optimization specifically comprises:

[0117] The output signal formula of the adaptive filter:

[0118]

[0119] Minimize the error function:

[0120] e(n) = d(n) - y(n);

[0121] Filter coefficient update formula:

[0122] w k (n+1) = w k (n) + μ·e(n)·x(n-k);

[0123] In the formula, w k(n) represents filter coefficients; x(n) represents a signal to be filtered; y(n) represents an output signal; d(n) represents a desired output signal; e(n) represents an error; n represents a discrete time index; M represents a filter order; μ represents a step factor; and k represents an iteration number index.

[0124] In this way, by extracting the interference features from the historical communication signals, the initial interference signals in the historical communication signals can be accurately located, and a feature basis for subsequent prediction of interference data is provided. The initial interference signals are input into a preset prediction model to obtain historical predicted interference data, so that the variation law of the interference can be grasped in advance, and the blindness of interference prediction can be avoided. Then, based on the historical predicted interference data, the initial adaptive filter parameters are adjusted, so that the filtering characteristics of the adaptive filter can be highly matched with the actual interference characteristics, the pertinence and accuracy of the adaptive filter in removing the interference components can be greatly improved, reliable support for the recovery of the power distribution network communication signals is provided, and finally the communication quality of the power system is further improved.

[0125] In some embodiments, if the missing signal exists, the missing signal is reconstructed and corrected to obtain a complete signal, specifically including: determining a missing type of the missing signal, if the missing signal belongs to a first missing type, reconstructing the missing signal by using an interpolation method to obtain a first reconstructed signal, if the missing signal belongs to a second missing type, reconstructing the missing signal by using a compressive sensing method to obtain a second reconstructed signal; performing error detection on the first reconstructed signal or the second reconstructed signal to obtain an error detection result, and correcting the error detection result to obtain the complete signal.

[0126] Specifically, the missing type of the missing signal is determined, the first missing type is local missing (such as continuous multiple sampling point amplitudes in the time domain waveform being lower than a noise threshold or being constantly zero), and the second missing type is integral missing (such as an enhanced signal frequency band energy being lower than a historical level or continuous multiple data packets being lost); if the first missing type, an interpolation method is used to reconstruct the missing signal, effective time domain signal data before and after the missing section is extracted, if the missing point has strong linear correlation with adjacent effective data, the missing value is calculated by linear interpolation, and a first reconstructed signal is obtained based on the missing value, if the missing interval needs to keep waveform smooth (such as continuous waveforms of power distribution network carrier signals), spline interpolation is used to construct a segmented smooth curve to fit the effective data and complete the missing section, and the first reconstructed signal is obtained; if the second missing type, a compressed sensing method is used to reconstruct the missing signal to obtain a second reconstructed signal; for the first reconstructed signal or the second reconstructed signal, an error detection mechanism is used, for a digital signal, a cyclic redundancy check (CRC) is used to calculate a check value of the signal data, and the check value is compared with a preset check value; for an analog signal, a time domain amplitude fluctuation range and a frequency domain feature matching degree are used to check an abnormal data section, and an error position and an error type are marked to obtain an error detection result; a corresponding correction technology is selected according to the error type, if it is a single-bit error, a Hamming code is used to locate and flip the error bit through exclusive or operation of the check bit and the information bit; if it is a multi-bit error or a data frame error, an LDPC code (low density parity check code) is used to correct the error data through an iterative decoding algorithm to obtain a complete signal.

[0127] In some embodiments, if the missing signal exists, the missing signal is reconstructed and corrected to obtain a complete signal, and the related formula is specifically as follows:

[0128] Linear interpolation formula:

[0129] χ reconstructed (t)=α·x(t1)+(1-α)·x(t2);

[0130] In the formula, α represents an interpolation coefficient; t1 and t2 are two continuous effective signal time points before and after the missing time t of the signal; x(t1) and x(t2) represent original effective signal amplitudes collected at t1 and t2 time points without missing and interference;

[0131] Compressed sensing formula:

[0132] min x ‖x‖1 subject to y=Ax+∈;

[0133] In the formula, y represents a measurement vector; A represents a measurement matrix; ∈ is a noise term; x represents a signal to be reconstructed; and ‖x‖1 represents an L1 norm of the signal x;

[0134] Thus, the missing type of the missing signal is first determined, the interpolation method is used for reconstruction for the first missing type, small-range and continuous signal missing can be quickly filled, the compressed sensing method is used for reconstruction for the second missing type, the signal can be accurately recovered based on the signal sparsity when the signal missing ratio is high, error detection and correction are performed on the reconstructed signal, errors possibly introduced in the reconstruction process can be identified and corrected, the reliability of the communication signal recovery of the power distribution network is improved, and the communication quality of the power system is improved.

[0135] In some embodiments, the complete signal is input into a preset adaptive filter to remove interference components to obtain an effective signal, specifically including: the complete signal is input into the preset adaptive filter point by point according to a discrete time sequence, the filter outputs a signal in real time through linear weighting calculation based on optimized filter coefficients; real-time interference residual detection is performed on the output signal, if the residual interference meets the standard, the output signals of all time points meeting the standard are spliced to form a continuous effective signal in which interference components are removed.

[0136] In some embodiments, the effective signal is subjected to signal enhancement to obtain the recovered communication signal of the power distribution network, specifically including: the effective signal is subjected to signal enhancement based on a gain factor to obtain the communication signal, wherein the gain factor is obtained by updating based on predicted interference data, and the predicted interference data is obtained by inputting the initial communication signal into the prediction model.

[0137] Specifically, after obtaining the predicted interference data output by the prediction model each time, if the predicted interference data shows that the subsequent interference amplitude is high (i.e., greater than a preset threshold), it indicates that the effective signal may be covered, therefore, the gain factor is adjusted to a higher value (such as 1.2-1.5) to avoid the signal amplitude exceeding the receiving threshold of the communication equipment of the power distribution network; if the predicted interference data shows that the subsequent interference amplitude is weak (i.e., less than the preset threshold), it indicates that the stability of the effective signal is good, therefore, the gain factor is maintained at a reference value (such as 1.0-1.1) to ensure that the signal is not distorted; then, the effective signal output by the adaptive filter is extracted, each time point of the effective signal is taken as a gain signal, and the gain factor is updated to perform multiplication operation to realize signal amplitude enhancement at each time point; finally, all time points of the enhanced signal are spliced to obtain the recovered communication signal of the power distribution network.

[0138] In some embodiments, the related formula for signal enhancement of the effective signal to obtain the recovered communication signal of the power distribution network, specifically includes:

[0139] Gain adjustment formula:

[0140] y enhanced (n)=G·y(n);

[0141] In the formula, G represents a gain factor; y(n) represents a signal to be amplified; and n represents a discrete time index.

[0142] Thus, the gain factor is updated based on the predicted interference data obtained by the preset prediction model based on the initial communication signal, so that the adjustment of the gain factor is matched with the interference situation faced by the current signal in real time; and the effective signal is enhanced based on the dynamically updated gain factor, so that the information of the effective signal is maximized while the current interference is accurately resisted, thereby ensuring the recovery quality of the power distribution network communication signal and improving the communication quality of the power system.

[0143] Thus, the initial communication signal on the plurality of signal propagation paths of the power distribution network is obtained, the transmission state of the same signal under different paths is obtained, the feasibility of signal recovery is ensured from the source, and the communication quality of the power system is improved; the initial communication signals of different propagation paths are weighted and combined to obtain a weighted signal, which can offset the adverse effects of multi-path propagation on the signal; the weighted signal is enhanced in the frequency domain to obtain an enhanced signal, which can improve the signal quality and help signal recovery to improve the communication quality; it is judged whether the enhanced signal has a missing signal, and the missing signal is reconstructed and corrected to obtain a complete signal, which can ensure the integrity and accuracy of the signal to help signal recovery and improve the communication quality; the complete signal is input into an adaptive filter based on historical predicted interference data for parameter optimization to obtain an effective signal by removing interference components, which can remove residual interference, and the effective signal is enhanced to obtain a recovered target signal, thereby realizing effective recovery of the power distribution network communication signal and finally improving the communication quality of the power system. The communication signal of the power distribution network is recovered to improve the communication quality of the power system.

[0144] Referring to Figure 3 On the basis of the above-mentioned method embodiment, a corresponding device embodiment is provided.

[0145] An embodiment of the present application provides a communication signal recovery device of a power distribution network, which comprises a first module 100, a second module 200 and a third module 300.

[0146] The first module 100 is used for obtaining initial communication signals of a power distribution network on a plurality of signal propagation paths.

[0147] The second module 200 is used for weighting and combining the initial communication signals to obtain a weighted signal, performing frequency domain enhancement on the weighted signal to obtain an enhanced signal, and judging whether the enhanced signal has a missing signal.

[0148] The third module 300 is configured to reconstruct and correct the missing signal to obtain a complete signal, input the complete signal into a preset adaptive filter to remove interference components to obtain an effective signal, and perform signal enhancement on the effective signal to obtain the recovered communication signal of the power distribution network.

[0149] In this way, the first module can obtain initial communication signals on a plurality of signal propagation paths of the power distribution network, the transmission state of the same signal on different paths can be obtained, the feasibility of signal recovery can be ensured from the source, and the communication quality of the power system can be improved. The second module can obtain a weighted signal by weighting and synthesizing the initial communication signals on different propagation paths, the adverse effects of multi-path propagation on the signal can be offset, the signal quality can be improved by performing frequency domain enhancement on the weighted signal to help signal recovery and improve the communication quality. The third module can ensure the integrity and accuracy of the signal by reconstructing and correcting the missing signal to obtain a complete signal, which helps signal recovery and improves the communication quality. The complete signal is input into an adaptive filter based on historical prediction interference data to remove interference components to obtain an effective signal, the residual interference can be removed, and the recovered target signal can be obtained by performing signal enhancement on the effective signal, thereby effectively recovering the communication signal of the power distribution network and finally improving the communication quality of the power system. The communication signal of the power distribution network can be recovered to improve the communication quality of the power system.

[0150] It can be understood that the above-mentioned device embodiments correspond to the method embodiments of the present application, and can realize the communication signal recovery method of the power distribution network provided by any one of the above-mentioned method embodiments.

[0151] It should be noted that the device embodiments described above are only schematic, and some or all of the modules can be selected to achieve the purpose of the present embodiment. In addition, in the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which can be realized as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor.

[0152] On the basis of the above-mentioned embodiment of the communication signal recovery method of the power distribution network, another embodiment of the present application provides a terminal device, which comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the communication signal recovery method of the power distribution network of any one embodiment of the present application is realized.

[0153] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present application. The one or more modules can be a series of computer program instruction segments capable of completing a specific function, which are used to describe the execution process of the computer program in the terminal device.

[0154] The terminal device can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The terminal device can include, but is not limited to, a processor and a memory.

[0155] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and connects all parts of the terminal device through various interfaces and lines.

[0156] On the basis of the above-mentioned method embodiment, another embodiment of the present application provides a computer readable storage medium, including a stored computer program, wherein when the computer program runs, the device where the computer readable storage medium is located executes the communication signal recovery method of the power distribution network according to any one of the above-mentioned method embodiments of the present application.

[0157] The modules / units integrated in the device / terminal equipment, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0158] On the basis of the above-mentioned method embodiment, another embodiment of the present application provides a computer program product, which includes a computer program or instructions, and the computer program or instructions are executed by a communication device to realize a communication signal recovery method of a power distribution network according to any one of the embodiments of the present application.

[0159] The above is the preferred embodiment of the present application. It should be pointed out that, for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements are also considered to be within the scope of protection of the present application.

Claims

1. A method for restoring communication signals in a power distribution network, characterized in that, include: Acquire the initial communication signals of the power distribution network along several signal propagation paths; The initial communication signals are weighted and synthesized to obtain a weighted signal, and the weighted signal is enhanced in the frequency domain to obtain an enhanced signal. It is then determined whether the enhanced signal contains any missing signals. If the missing signal exists, the missing signal is reconstructed and corrected to obtain a complete signal. The complete signal is then input into a preset adaptive filter to remove interference components and obtain an effective signal. The effective signal is then enhanced to obtain the restored communication signal of the distribution network. The preset adaptive filter is obtained by parameter optimization based on historical predicted interference data.

2. The method for restoring communication signals in a power distribution network as described in claim 1, characterized in that, The optimization method for the preset adaptive filter specifically includes: Feature extraction is performed on the acquired historical communication signals to obtain historical interference features; The initial interference signal in the historical communication signal is determined based on the historical interference characteristics; The initial interference signal is input into a preset prediction model to obtain the historical predicted interference data; The parameters of the initial adaptive filter are adjusted based on the historical predicted interference data to obtain the optimized preset adaptive filter.

3. The method for restoring communication signals in a power distribution network as described in claim 2, characterized in that, The step of extracting features from the acquired historical communication signals to obtain historical interference features specifically includes: The acquired historical communication signals are subjected to spectral analysis to obtain frequency characteristics; The historical communication signal is subjected to time-domain analysis to obtain the time-domain analysis results, and peak detection is performed based on the time-domain analysis results to obtain amplitude characteristics; Wavelet transform is performed on the historical communication signals to obtain time characteristics; By integrating the frequency features, amplitude features, and time features, historical interference features are obtained.

4. The method for restoring communication signals in a power distribution network as described in claim 1, characterized in that, The step of weighting and synthesizing the initial communication signals to obtain a weighted signal specifically includes: The cross-correlation values ​​of each initial communication signal and the preset reference signal are calculated respectively, and the corresponding time delay deviation is determined based on each cross-correlation value. The time delay deviation is used to synchronize each initial communication signal to obtain the corresponding synchronization signal. Based on each of the synchronization signals, the corresponding time-frequency characteristics are determined, and the synchronization signals are separated by interference using each of the time-frequency characteristics to obtain the separated signals; The separated signals are weighted and synthesized with preset weighting coefficients to obtain a weighted signal.

5. The method for restoring communication signals in a power distribution network as described in claim 1, characterized in that, If the missing signal exists, the missing signal is reconstructed and corrected to obtain the complete signal, specifically including: The missing signal is determined to be of the missing type. If the missing signal belongs to the first missing type, the missing signal is reconstructed using an interpolation method to obtain a first reconstructed signal. If the missing signal belongs to the second missing type, the missing signal is reconstructed using a compressed sensing method to obtain a second reconstructed signal. Error detection is performed on the first reconstructed signal or the second reconstructed signal to obtain an error detection result, and the error detection result is corrected to obtain the complete signal.

6. The method for restoring communication signals in a power distribution network as described in claim 2, characterized in that, The step of enhancing the effective signal to obtain the restored communication signal of the distribution network specifically includes: enhancing the effective signal based on a gain factor to obtain the communication signal, wherein the gain factor is obtained by updating based on predicted interference data, and the predicted interference data is obtained by inputting the initial communication signal into the prediction model.

7. A communication signal recovery device for a power distribution network, characterized in that, It includes Module 1, Module 2, and Module 3; The first module is used to acquire the initial communication signals of the power distribution network on several signal propagation paths; The second module is used to weight and synthesize each of the initial communication signals to obtain a weighted signal, and to enhance the weighted signal in the frequency domain to obtain an enhanced signal, and to determine whether there is a missing signal in the enhanced signal; The third module is used to reconstruct and correct the missing signal if the missing signal exists, to obtain a complete signal, input the complete signal into a preset adaptive filter to remove interference components, to obtain an effective signal, and to enhance the effective signal to obtain the restored communication signal of the distribution network. The preset adaptive filter is obtained by parameter optimization based on historical predicted interference data.

8. A terminal device, characterized in that, include: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction that causes the processor to perform the operation of the communication signal recovery method for the power distribution network as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device or apparatus containing the computer-readable storage medium to perform the communication signal recovery method for a power distribution network as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or instructions are executed by the communication device, they implement the communication signal recovery method for the power distribution network as described in any one of claims 1 to 6.

Images