9 results about "Synchronous oscillations" patented technology

The invention discloses a wide-area oscillation source positioning method and system based on physical feature embedding and a graph attention network, and the method comprises the steps: obtaining synchronous phasor data of a power system, carrying out the modal parameter identification of subsynchronous oscillation and / or super-synchronous oscillation based on the synchronous phasor data, constructing a topological graph of the power system, and carrying out the positioning of a wide-area oscillation source. And constructing the oscillation amplitude, the attenuation factor and the phase of each node obtained by identification into a feature vector of each node in a topological graph, inputting the topological graph and the feature vector into a graph attention network, and outputting an oscillation source positioning result, so that high-frequency recording data after an accident does not need to be waited, and the positioning accuracy of the oscillation source is improved only on the basis of synchronous phasor data. The identified modal parameters are used as physical characteristics to be embedded into the graph attention network, and the interpretability of a physical mechanism and the graph structure mining capability of deep learning are fused, so that subsynchronous oscillation and super-synchronous oscillation are accurately positioned.

The invention discloses an L1 regularization and neural network-based power system sub / super synchronous oscillation parameter identification method and device applied to a synchronous phasor measurement device, and a storage medium, and belongs to the technical field of power system oscillation analysis. Recombining the non-missing parts into a continuous synchronous phasor sequence in sequence; 2, setting a neural network and a Fourier transform matrix as input, and setting a continuous synchronous phasor sequence as target output; 3, initializing weight parameters of the neural network; 4, adding L1 regularization as a penalty term of a target output error; 5, optimizing the network weight by using an RMSProp optimizer to obtain a solution of an equation set; and 6, calculating sub / super synchronous oscillation parameters according to a synchronous phasor algorithm in combination with the solution of the equation set. The method can be applied to a synchronous phasor measurement device, synchronous phasor data collected by the device serve as input of the method, and oscillation parameters of signals can be measured online.

The invention provides a subsynchronous oscillation traceability method and system based on high-dimensional deterministic learning modeling, and belongs to the technical field of power system stabilization, and the method comprises the steps: constructing graph structure data based on a power signal of a power grid, and employing a graph theory method to extract topological information from the graph structure data; for each node in the graph structure data, carrying out distributed dynamic modeling on a power signal corresponding to the node by adopting a deterministic learning mechanism, and constructing a pattern library; establishing a distributed dynamic estimator by using the neural network weight stored in the pattern library, inputting a to-be-detected power signal to the distributed dynamic estimator in a parallel mode at each topological node, and comparing the to-be-detected power signal with all patterns in the pattern library through a distributed dynamic pattern recognition mechanism to obtain a recognition residual error at each node; and carrying out real-time aggregation on the topological information of the identification residual generated at each topological node by adopting a graph convolution method to obtain a traceability result. According to the invention, the accuracy and reliability of subsynchronous oscillation detection are improved.

The invention discloses a new energy power system subsynchronous / super-synchronous oscillation dominant frequency rapid prediction and identification method and system based on transfer learning, and relates to the field of power systems and automation thereof, and the method comprises the steps: constructing forced oscillation data and subsynchronous / super-synchronous oscillation data; selecting electrical operation data in an oscillation initial stage from the forced oscillation data as characteristic data, taking dominant frequency in an oscillation stable stage in the forced oscillation data as a label, and constructing a forced oscillation sample; similarly, constructing a sub-synchronous / super-synchronous oscillation sample based on the sub-synchronous / super-synchronous oscillation data; taking a forced oscillation sample as a source domain, taking a sub / super-synchronous oscillation sample as a target domain, and training the machine learning neural network model through a transfer learning method to obtain an oscillation identification model; and performing rapid prediction and identification on the dominant frequency of the sub / super-synchronous oscillation of the new energy grid-connected point by using the oscillation identification model. The method has good timeliness for prediction and identification of the dominant frequency of the sub / super-synchronous oscillation.

The application discloses a power system sub / super-synchronous oscillation signal identification method and device, and aims to solve the technical problem that current related technologies cannot effectively monitor and accurately distinguish sub-synchronous and super-synchronous oscillation signals. Multi-source time sequence information of a power system is collected, and a fusion representation vector is constructed according to the multi-source time sequence information; the multi-source time sequence information is subjected to frequency spectrum analysis and enhancement, and an oscillation signal containing a sub / super-synchronous frequency band is obtained; based on the frequency spectrum analysis result in the frequency spectrum analysis and enhancement process, the oscillation mode parameters of the oscillation signal in the sub / super-synchronous frequency band are identified, and the oscillation risk level is evaluated based on the oscillation mode parameters; the fusion representation vector is fused and verified according to the multi-source time sequence information and the oscillation mode parameters, the sub / super-synchronous oscillation region and the time sequence evolution path are identified; the oscillation mode parameters are subjected to reverse verification, and when the reverse verification is passed, various types of identification information obtained in the previous steps are output as the multi-dimensional identification result of the oscillation signal.

The invention discloses an oscillator dynamics synchronous control system and method based on a graph attention mechanism, the system is a graph structure formed by coupling a plurality of oscillators as nodes, and the graph structure depicts a connection mode between any units through a proximity matrix; the state of each node is controlled through the internal dynamics of the oscillator and the influence of other oscillators on the oscillator, and the influence of the other oscillators is obtained by mapping the multi-head attention coefficient of each attention head to the state space of each neuron by using a multi-layer neural network; the multi-head attention coefficient is dynamically generated in combination with the state of each node of the network and a user-specified desired phase. According to the method, the coupling parameters of the network are autonomously learned by defining the node coupling relationship in the oscillator network as the graph attention weight. Training can be carried out in a small-scale oscillator network, and the trained model can directly generate a synchronous oscillation mode meeting any phase relation in any large-scale oscillator network.

The application utilizes variational mode decomposition (VMD) and principal component analysis (PCA), and proposes a VMD-PCA-based sub-synchronous oscillation energy characteristic influence factor identification method. The port energy characteristics of sub-synchronous oscillation under different working conditions are extracted through time domain simulation, and a regression model is established to perform regression analysis on the port energy of sub-synchronous oscillation. The process is as follows: the VMD mode decomposition is performed on the measured voltage and current at the outlet of the fan to obtain the voltage and current components under the sub-synchronous oscillation mode, and the transient energy flow at the outlet of the fan is obtained by calculation; the transient energy flow function of the fan outlet is fitted, and the energy flow power is taken as the stability characteristic quantity of sub-synchronous oscillation for research; the principal component method is used to solve the multicollinearity problem between the energy characteristic influence factors, a variable fitting evaluation model of the energy characteristic is established based on the stepwise regression method, and the key influence factors of the sub-synchronous oscillation energy characteristic are identified. The method can judge the current system energy characteristic of the system in time, identify the key influence factors affecting the system energy characteristic, and has important engineering significance for maintaining the safe and stable operation of the new power system.

Provided are a method and system for screening a sub-synchronous oscillation curve, and a storage medium and an electronic device. The method comprises: acquiring amplitude data point sequences to be determined of electromagnetic transient simulation phasors of a plurality of consecutive time windows; on the basis of a pre-established classifier, outputting the categories of said amplitude data point sequences; using a time-frequency domain wavelet packet decomposition method to analyze said amplitude data point sequence having an oscillation behavior, so as to acquire the frequencies and amplitudes of inter-harmonic components to be screened; comparing amplitude percentages of said inter-harmonic components with a predetermined amplitude threshold value, and using, as remaining inter-harmonic components, said inter-harmonic components for which noise has been filtered; and on the basis of the frequencies and amplitude percentages of the remaining inter-harmonic components, determining an output sub-synchronous oscillation curve.

The invention provides a sub-hyper-synchronous oscillation detection method and system based on a tunable wave trap, and a medium, and the method comprises the steps: enabling a DC digital filter to be in cascade connection with the tunable digital wave trap, and obtaining a single-frequency oscillation signal detector; constructing an energy function based on the oscillation signal to be detected and the output of the single-frequency oscillation signal detector by taking the notch angular frequency of the tunable notch filter as an independent variable; and adopting a gradient descent method, carrying out iterative updating on the negative gradient direction of the independent variable along the energy function at a fixed step length, and searching the minimum value of the energy function: when the gradient of the energy function to the independent variable is zero, determining the corresponding angular frequency as the angular frequency of the oscillation signal to be measured. The implementation process is simple and easy to implement, the calculated amount is small, implementation is easy, and real-time accurate detection of the sub-hyper-synchronous oscillation signal can be achieved.