Broadband oscillation treatment method and system based on risk assessment

Abstract

The invention provides a broadband oscillation treatment method and system based on risk assessment, and belongs to the field of power system control. The method comprises the following steps: in a preset wheel, identifying a high-risk new energy station based on a risk assessment model adapted to the broadband oscillation problem of the new energy station; in the early warning wheel, wavelet transform and a depth auto-encoder algorithm are fused, an anomaly detection model is generated for the high-risk new energy station, and based on a detection result of the model, a dynamic threshold adjustment mechanism is adopted to realize early warning of the broadband oscillation risk; in the flexible adjusting wheel, when it is detected that small-range oscillation with low amplitude exists in the new energy station, the new energy station is adjusted; and in a generator tripping control wheel, when oscillation is continuous and the condition is deteriorated, an oscillation source and generator tripping requirements are identified, and a differentiated generator tripping scheme is formulated. According to the method, the broadband oscillation risk can be effectively reduced, the capacity of the power grid for coping with complex dynamic disturbance is improved, and powerful support is provided for safe and stable operation of a high-proportion new energy power system.

Description

Technical Field

[0001] The present invention belongs to the field of power system control, and particularly relates to a method and system for suppressing broadband oscillation based on risk assessment. Background Art

[0002] With the large-scale access of new energy sources such as wind power and photovoltaic power to the power grid through power electronic converters, the dynamic characteristics of the power grid have changed significantly, and the risk of broadband oscillation has also increased significantly. Broadband oscillation is a system oscillation phenomenon with a frequency range from sub-synchronous (2 - 15 Hz) to high-frequency (50 - 500 Hz), which is usually more likely to occur under the condition of a weak power grid with a low short-circuit ratio (SCR). In recent years, broadband oscillation problems have frequently occurred in areas with a high proportion of new energy access at home and abroad. For example, in areas with intensive access of new energy such as Xinjiang Hami, Ningxia, and the vicinity of Zhaoyi in Shandong, oscillation events with various frequency ranges have occurred during the engineering commissioning and operation processes, seriously threatening the safe and stable operation of the large power grid.

[0003] Existing methods for suppressing broadband oscillation mainly focus on optimizing the control parameters of converters or using additional damping systems. However, the formation mechanism of new energy broadband oscillation is complex. It is a negative-damping electromagnetic oscillation formed by the control interaction between multiple units / converters and network elements (machines / motors / networks), and its occurrence is closely related to various factors such as controller parameters, operating conditions, and power grid structure. Due to the complex and changeable operation mode of the power system and the continuous expansion of the power grid scale, the characteristics such as the frequency and damping of the oscillation will be significantly affected by external environmental factors such as power electronic converters, new energy generating units, power grid structure, and wind and light, showing the characteristics of large-range time-varying. However, traditional off-line simulation analysis methods are difficult to accurately capture the dynamic characteristics of broadband oscillation and are also difficult to formulate effective prevention and control measures for its time-varying characteristics. Summary of the Invention

[0004] The object of the present invention is to overcome the deficiencies of the existing technologies and propose a method and system for suppressing broadband oscillation based on risk assessment. The present invention can effectively reduce the risk of broadband oscillation, improve the ability of the power grid to cope with complex dynamic disturbances, and provide strong support for the safe and stable operation of a high-proportion new energy power system.

[0005] The first aspect of the embodiments of the present invention proposes a method for suppressing broadband oscillation based on risk assessment, including:

[0006] In a preset round, based on a risk assessment model adapted to the broadband oscillation problem of new energy power stations, risk assessment is performed on each new energy power station to identify high-risk new energy power stations;

[0007] In the early warning wheel, wavelet transform and deep autoencoder algorithm are integrated to perform multi-scale analysis on the voltage or current waveform of the high-risk new energy station to generate an anomaly detection model. Based on the detection results of the anomaly detection model, a dynamic threshold adjustment mechanism is adopted to achieve early warning of broadband oscillation risks.

[0008] In the flexible regulating wheel, when a small-scale oscillation with a low amplitude is detected in a new energy station, the new energy station is regulated to suppress the oscillation;

[0009] In the machine cutting control wheel, when oscillation persists and the situation worsens, identify the oscillation source and the need for machine cutting; adopt a layered and zoned machine cutting strategy and formulate differentiated machine cutting plans.

[0010] In a specific embodiment of the present invention, the risk assessment model adapted to the broadband oscillation problem of new energy stations is expressed as follows:

[0011]

[0012] Where risk_score represents the risk score; α, β, and γ are weight coefficients, 0<α<1, 0<β<1, 0<γ<1, and α+β+γ=1;

[0013] Slope(PV) represents the slope of the active voltage curve of the renewable energy station, SCR represents the short-circuit ratio of the renewable energy station, and TCI represents the complexity index of the grid topology corresponding to the renewable energy station.

[0014] in,

[0015]

[0016] Where S sc is the short-circuit capacity of the power grid, S rated is the rated power of the station;

[0017]

[0018] In the formula, node i is the node where the new energy station is located, node j is the node where the other stations are located, and d ij is the shortest path length between nodes i and j, and N is the total number of grid nodes.

[0019] In a specific embodiment of the present invention, generating an anomaly detection model includes:

[0020] Perform wavelet transform on the voltage waveform or current waveform to obtain signal features at different scales; input the feature data after wavelet transform, i.e., wavelet coefficients, into a deep autoencoder for training to obtain an anomaly detection model. The input of this model is wavelet coefficients, and the output is the determination result of whether the original signal is abnormal. Among them, an output of 1 indicates that the original signal is abnormal, and an output of 0 indicates that the original signal is normal.

[0021] In a specific embodiment of the present invention, it further includes:

[0022] In the flexible regulation wheel, use the model predictive control algorithm to solve the optimization objective function to determine the optimal control sequence. The control sequence is the increment sequence of the gain coefficient of the power system stabilizer; the expression of the optimization objective function is:

[0023]

[0024] In the formula, J(x i ,u i ) is the objective function, x i is the state of the system at the i-th step, u i is the control input at the i-th step, and M is the prediction time domain.

[0025] In a specific embodiment of the present invention, it further includes:

[0026] In the generator tripping control wheel, identify the oscillation source substation by calculating the oscillation energy distribution coefficient E ij ;

[0027] Among them, node i represents the node where the new energy substation is located, and node j represents the grid connection point of the substation; the larger the oscillation energy distribution coefficient E ij , the more it indicates that the new energy substation corresponding to node i can be preferentially tripped.

[0028] The second aspect of the embodiments of the present invention proposes a wide-frequency oscillation governance system based on risk assessment, including:

[0029] A risk assessment module, used in the preset wheel, based on a risk assessment model adapted to the wide-frequency oscillation problem of new energy substations, perform risk assessment on each new energy substation to identify high-risk new energy substations;

[0030] An early warning module, used in the early warning wheel, fuse the wavelet transform and deep autoencoder algorithms, perform multi-scale analysis on the voltage or current waveforms of the high-risk new energy substations to generate an anomaly detection model; based on the detection results of the anomaly detection model, adopt a dynamic threshold adjustment mechanism to achieve early warning of wide-frequency oscillation risks;

[0031] A flexible adjustment module, which is used for a flexible adjustment wheel to adjust the new energy power station to suppress oscillations when it detects small - scale oscillations with low amplitude in the new energy power station;

[0032] A generator - tripping control module, which is used for a generator - tripping control wheel to identify the oscillation source and generator - tripping requirements when the oscillation continues and deteriorates; adopt a hierarchical and zonal generator - tripping strategy to formulate a differentiated generator - tripping plan.

[0033] In a specific embodiment of the present invention, the risk assessment model adapted to the wide - frequency oscillation problem of the new energy power station has the following expression:

[0034]

[0035] In the formula, risk_score represents the risk score; α, β, γ are weight coefficients, 0 < α < 1, 0 < β < 1, 0 < γ < 1, and α + β + γ = 1;

[0036] slope(PV) represents the slope of the active power - voltage curve of the new energy power station, SCR represents the short - circuit ratio of the new energy power station, and TCI represents the complexity index of the power grid topological structure corresponding to the new energy power station;

[0037] Among them,

[0038]

[0039] In the formula, S sc is the power grid short - circuit capacity, and S rated is the rated power of the power station;

[0040]

[0041] In the formula, node i is the node where the new energy power station is located, node j is the node where the other power stations are located, d ij is the shortest path length between node i and j, and N is the total number of power grid nodes.

[0042] In a specific embodiment of the present invention, the anomaly detection model includes:

[0043] Perform wavelet transform on the voltage waveform or current waveform to obtain signal features at different scales; input the feature data after wavelet transform, that is, wavelet coefficients, into a deep auto - encoder for training to obtain an anomaly detection model. The input of this model is wavelet coefficients, and the output is the determination result of whether the original signal is abnormal. Among them, the output of 1 indicates that the original signal is abnormal, and the output of 0 indicates that the original signal is normal.

[0044] In a specific embodiment of the present invention, it further includes:

[0045] In the flexible adjustment wheel, the model predictive control algorithm is used to solve the optimization objective function to determine the optimal control sequence, and the control sequence is the increment sequence of the gain coefficient of the power system stabilizer; the expression of the optimization objective function is:

[0046]

[0047] In the formula, J(x i ,u i ) is the objective function, x i is the state of the system at the i-th step, u i is the control input at the i-th step, and M is the prediction horizon.

[0048] In a specific embodiment of the present invention, it further includes:

[0049] In the generator tripping control wheel, by calculating the oscillation energy distribution coefficient E ij to identify the oscillation source substation;

[0050] Among them, Node i represents the node where the new energy substation is located, and node j represents the grid connection point of the substation; the larger the oscillation energy distribution coefficient E ij , the more it indicates that the new energy substation corresponding to node i can be preferentially tripped.

[0051] Thus, the risk of broadband oscillation can be effectively reduced, the ability of the power grid to cope with complex dynamic disturbances can be improved, and strong support can be provided for the safe and stable operation of the high-proportion new energy power system.

[0052] An embodiment of the third aspect of the present invention proposes an electronic device, including:

[0053] At least one processor; and a memory communicatively connected to the at least one processor;

[0054] Wherein, the memory stores instructions executable by the at least one processor, and the instructions are configured to execute the above-mentioned method for governing broadband oscillation based on risk assessment.

[0055] An embodiment of the fourth aspect of the present invention proposes a computer-readable storage medium, and the computer-readable storage medium stores computer instructions for causing the computer to execute the above-mentioned method for governing broadband oscillation based on risk assessment.

[0056] The features and beneficial effects of the present invention are as follows:

[0057] The present invention can combine with the real-time operation state of the power grid, dynamically evaluate the risk levels of broadband oscillations under different operation modes, and implement hierarchical and phased governance measures according to the risk levels. When the system operation mode changes, the damping characteristics of the system are enhanced by dynamically adjusting the converter control parameters or putting into additional damping devices; when the power grid structure changes, the oscillation risk is reduced by optimizing the power grid topology or enhancing the damping capacity of network components, so as to ensure the safe and stable operation of the power grid. In extreme cases, the present invention can also avoid the further expansion of oscillations by quickly cutting off some new energy units or loads, ensuring the safe and stable operation of the power grid. Through this systematic governance strategy of grading and in rounds, the risk of broadband oscillations can be effectively reduced, the ability of the power grid to cope with complex dynamic disturbances can be improved, and strong support can be provided for the safe and stable operation of a high-proportion new energy power system. Brief Description of the Drawings

[0058] Figure 1 is the overall flowchart of a method for governing broadband oscillations based on risk assessment according to an embodiment of the present invention. Detailed Embodiment

[0059] The present invention provides a method and system for governing broadband oscillations based on risk assessment, which will be further described in detail below with reference to the drawings and specific embodiments.

[0060] An embodiment of the first aspect of the present invention provides a method for governing broadband oscillations based on risk assessment, including:

[0061] In the preset round, based on a risk assessment model adapted to the broadband oscillation problem of new energy power stations, risk assessment is carried out on each new energy power station to identify high-risk new energy power stations;

[0062] In the early warning round, wavelet transform and deep autoencoder algorithm are fused to perform multi-scale analysis on the voltage or current waveforms of the high-risk new energy power stations to generate an anomaly detection model; based on the detection results of the anomaly detection model, a dynamic threshold adjustment mechanism is adopted to realize the early warning of the broadband oscillation risk;

[0063] In the flexible adjustment round, when it is detected that there are small-scale oscillations with low amplitudes in the new energy power station, the new energy power station is adjusted to suppress the oscillations;

[0064] In the generator tripping control round, when the oscillation continues and the situation deteriorates, the oscillation source and the generator tripping demand are identified; a hierarchical and zonal generator tripping strategy is adopted to formulate a differentiated generator tripping plan.

[0065] In a specific embodiment of the present invention, the overall process of the method for governing broadband oscillations based on risk assessment is as Figure 1As shown in the figure, it includes the following steps: 1) At the preset wheel, based on a risk assessment model adapted to the broadband oscillation problem of new energy power stations, conduct a risk assessment on each new energy power station to identify high-risk new energy power stations.

[0066] In this embodiment, the expression of the risk assessment model is as follows:

[0067]

[0068] In the formula, risk_score represents the risk score; α, β, and γ are weight coefficients determined based on the actual operation situation and data analysis, 0 < α < 1, 0 < β < 1, 0 < γ < 1, and α + β + γ = 1. In the actual application of the power system, α = 0.5, β = 0.3, and γ = 0.2 can be taken. slope(PV) represents the slope of the active power-voltage curve (PV curve) of the new energy power station, SCR represents the short-circuit ratio of the new energy power station, and TCI represents the complexity index of the grid topology structure corresponding to the new energy power station.

[0069] Among them,

[0070]

[0071] In the formula, S sc is the grid short-circuit capacity, and S rated is the rated power of the power station.

[0072]

[0073] In the formula, node i is the node where the new energy power station is located, node j is the node where the other power stations are located, and d ij is the shortest path length between nodes i and j, and N is the total number of grid nodes.

[0074] It should be noted that the grid topology structure complexity index (TCI) is used to quantitatively evaluate the complexity of the connection methods between various components (conventional generator sets, new energy power stations, loads) in the power system, identify key nodes and potential weak links, so as to provide a scientific basis for the suppression and location of broadband oscillations in the power system.

[0075] In this embodiment, the PV curve of the new energy power station can be generated by using data fitting technology after collecting and analyzing the historical operation data of the new energy power station.

[0076] Furthermore, in this embodiment, after conducting a risk assessment on each new energy power station, a grading standard corresponding to the risk score is given, and the risk assessment is divided into three grades: low risk (risk_score < 0.3), medium risk (0.3 ≤ risk_score < 0.7), and high risk (risk_score ≥ 0.7).

[0077] When any new energy power station is determined to be at high risk, the new energy power station needs to enter the warning round of step 2).

[0078] 2) In the warning round, fuse the wavelet transform and the deep autoencoder (DAE) algorithm to perform multi-scale analysis on the voltage or current waveforms of the high-risk new energy power station to generate an anomaly detection model; based on the detection results of the anomaly detection model, adopt a dynamic threshold adjustment mechanism to achieve early warning of wide-frequency oscillation risks; the specific steps are as follows:

[0079] 2-1) Through fusing the wavelet transform and the deep autoencoder algorithm, perform multi-scale fine analysis on the voltage or current waveforms to generate an anomaly detection model.

[0080] In this embodiment, the algorithm of fusing the wavelet transform and the deep autoencoder (DAE) includes: collecting voltage and current signals at a set frequency. In a specific embodiment of the present invention, the sampling rate is set to at least 1000 times per second.

[0081] Perform wavelet transform on the collected voltage or current signals, and the expression is as follows:

[0082]

[0083] In the formula, f(t) is the original signal, a is the scale parameter, b is the position parameter, and ψ(t) is the wavelet basis function.

[0084] In this embodiment, when performing the transform on the voltage waveform or the current waveform, the frequency of the harmonic components generated by the oscillation in the voltage or current waveform remains unchanged. The scale parameter a starts from 1 and gradually increases to cover the high-frequency to low-frequency components of the signal, and a suitable position range is selected according to the time characteristics of the signal. Usually, the position parameter covers the entire time interval of the signal. In this embodiment, the Haar wavelet is selected, which is the earliest wavelet basis function, simple and computationally efficient, and suitable for the fast decomposition of signals. The signal features at different scales are obtained through this transform. The feature data (wavelet coefficients) after wavelet transform are input into the deep autoencoder (DAE) for training to obtain an anomaly detection model. The input of this model is the wavelet coefficients, and the output is the determination result of whether the original signal is abnormal, where the output of 1 indicates that the original signal is abnormal, and the output of 0 indicates that the original signal is normal.

[0085] In this embodiment, the trained anomaly detection model can be used later to monitor in real time whether the voltage and current waveforms are abnormal.

[0086] In this embodiment, by fusing the wavelet transform and the deep autoencoder (DAE) algorithm, the effects of feature extraction and dimensionality reduction can be effectively improved, the accuracy and timeliness of voltage and current anomaly monitoring and analysis can be improved, and early warning before the oscillation occurs can be realized.

[0087] 2-2) Flexibly adjust the warning threshold according to the real-time operating state of the power grid; when the anomaly detection model obtained in step 1) detects an anomaly, if the index exceeds the set threshold, trigger the warning mechanism.

[0088] In this embodiment, the warning threshold is flexibly adjusted according to the real-time operating state of the power grid. Among them, when the power grid flow is heavy, the threshold can be appropriately reduced, and when the power grid flow is light, the threshold can be appropriately increased.

[0089] When it is detected that the total harmonic distortion (THD) exceeds the dynamic harmonic threshold, abnormal frequency components appear (in this embodiment, 2-15 Hz or 50-500 Hz), or the voltage deviation exceeds the dynamic voltage threshold, trigger the warning mechanism, and then enter the flexible adjustment wheel in step 3).

[0090] Among them, the calculation expression of the total harmonic distortion (THD) is:

[0091]

[0092] In the formula, V h is the effective value of the hth harmonic voltage, V1 is the effective value of the fundamental voltage, and H is the result of dividing the highest harmonic frequency by the fundamental frequency.

[0093] In this embodiment, the dynamic threshold adjustment mechanism can adjust the warning threshold in real time according to the current actual operating parameters and status of the power grid, thereby improving the accuracy and timeliness of the warning. This mechanism can not only adapt to the change of the power grid oscillation frequency, but also effectively cope with emergencies such as equipment failures and weather changes, providing strong support for the safe and stable operation of the power grid.

[0094] In this embodiment, the response of the warning signal to trigger the flexible adjustment wheel is linked with the high-risk stations of the preset wheel to reduce the risk of misoperation. Through the synergistic effect of wavelet transform and deep autoencoder algorithm, abnormal changes in voltage and current waveforms can be detected more accurately, improving the reliability of the warning.

[0095] 3) In the flexible adjustment wheel, when it is detected that there is a small-range oscillation with a low amplitude in the new energy power station, adjust the new energy power station to suppress the oscillation.

[0096] In this embodiment, when it is detected that there is a small-range oscillation with a low amplitude in the new energy power station (in a specific embodiment of the present invention, the oscillation amplitude > 10% or the oscillation duration > 10 seconds), start the distributed cooperative control strategy. Each new energy station shares the converter control parameters and oscillation information in real time through the communication network, and cooperatively adjusts the key damping gain parameters. Among them, increase the gain coefficient of the power system stabilizer and reduce the proportional coefficient of the power outer loop of the new energy unit.

[0097] Specifically, in combination with the model predictive control (MPC) algorithm, based on the current power grid state and the predicted oscillation trend, the regulation strategy is optimized in advance. Based on the amplitude ratio monitoring situation, the active power output is dynamically adjusted (considering 20%-30% of the amplitude ratio), and the high-risk power stations are preferentially controlled and regulated. The model predictive control algorithm determines the optimal control sequence by solving the optimization objective function (this control sequence is the increment sequence of the gain coefficient of the power system stabilizer, and the gain coefficient of the power system stabilizer is gradually increased). The expression of the optimization objective function is:

[0098]

[0099] In the formula, J(x i ,u i ) is the objective function, x i is the state of the system at the i-th step, u i is the control input at the i-th step, and M is the prediction horizon.

[0100] Furthermore, in this embodiment, the control range can be gradually expanded according to the propagation range and intensity of the oscillation, and coordinated regulation is implemented on the surrounding relevant new energy units.

[0101] Through the application of distributed cooperative control and the electrical quantity characteristic trend algorithm in this embodiment, more efficient oscillation suppression can be achieved, and the power grid stability can be improved.

[0102] Furthermore, in this embodiment, the system damping characteristics can also be improved by dynamically adjusting the converter control parameters, putting into additional damping devices or optimizing the power grid topology structure to suppress the development of oscillations, specifically including:

[0103] ① Optimization of converter control parameters: By adjusting the power outer loop gain K p and the integral time constant T i , the system damping characteristics are optimized. Among them, the optimization expression of the power outer loop gain is:

[0104]

[0105] In the formula, ω n represents the natural frequency of the system, and ζ represents the damping ratio.

[0106] ② Additional damping control, enhancing the system damping characteristics through additional damping control (virtual synchronous machine control or adaptive damping control). Among them, the output u of the additional damping control can be expressed as:

[0107]

[0108] In the formula, K d represents the damping coefficient, represents the rate of change of the power angle.

[0109] ③ Grid topology optimization. When the grid structure changes, the grid topology structure is optimized (adding tie lines or adjusting unit distribution) to reduce the oscillation risk.

[0110] Furthermore, if the oscillation cannot be effectively suppressed during the adjustment process, in this embodiment, when the amplitude ratio > 20% or the oscillation duration reaches 20 seconds, it is upgraded to the generator tripping control wheel.

[0111] 4) At the generator tripping control wheel, when the oscillation persists and the situation deteriorates, based on the improved calculation method of the oscillation energy distribution coefficient, identify the oscillation source and the generator tripping demand; at the same time, adopt a hierarchical and zonal generator tripping strategy, and formulate a differentiated generator tripping plan according to the characteristics of different regions of the power grid.

[0112] In this embodiment, when the oscillation persists and the situation deteriorates (amplitude ratio > 20% or duration reaches 20 seconds), based on the improved calculation method of the oscillation energy distribution coefficient, fully consider the line impedance characteristic Z ij , amplitude, transmission power P ij and other factors to more accurately identify the oscillation source substation. The calculation of the oscillation energy distribution coefficient E ij needs to comprehensively consider various factors. E ij = f(Z ij , P ij , …) (the specific function form is determined according to actual analysis).

[0113] In a specific embodiment of the present invention, Node i represents the node where the new energy substation is located, and node j represents the grid connection point of the substation. The larger the oscillation energy distribution coefficient E ij , the more it indicates that the new energy substation corresponding to node i can be preferentially tripped.

[0114] In this embodiment, a hierarchical and zonal generator tripping strategy is adopted. According to the characteristics of different regions of the power grid: voltage level, load distribution, power source layout, etc., a differentiated generator tripping plan is formulated. The generator tripping ratio is controlled within 15% - 30% and implemented step by step to minimize the interference to the power grid. Furthermore, an optimization model for the generator tripping sequence is established, comprehensively considering the impact of generator tripping on the power flow distribution and stability of the power grid, and determining the optimal generator tripping sequence. Through methods such as power flow calculation and stability analysis, different generator tripping sequences are evaluated and the optimal plan is selected.

[0115] As the last line of defense, it is started after the flexible adjustment wheel fails and needs to ensure the stability of the power grid. In this embodiment, the generator tripping sequence needs to be predefined. Through the improved calculation method of the oscillation energy distribution coefficient and the hierarchical and zonal generator tripping strategy, the oscillation source substation can be more accurately tripped to avoid chain reactions.

[0116] To implement the above embodiments, a second aspect embodiment of the present invention proposes a broadband oscillation governance system based on risk assessment, including:

[0117] A risk assessment module, configured to perform risk assessment on each new energy power station in a preset round based on a risk assessment model adapted to the broadband oscillation problem of new energy power stations, so as to identify high-risk new energy power stations;

[0118] An early warning module, configured to, in an early warning round, fuse wavelet transform and deep autoencoder algorithms to perform multi-scale analysis on the voltage or current waveforms of the high-risk new energy power stations, generate an anomaly detection model; based on the detection results of the anomaly detection model, adopt a dynamic threshold adjustment mechanism to achieve early warning of broadband oscillation risks;

[0119] A flexible adjustment module, configured to, in a flexible adjustment round, when it is detected that there is a small-range oscillation with a low amplitude in a new energy power station, adjust the new energy power station to suppress the oscillation;

[0120] A generator tripping control module, configured to, in a generator tripping control round, when the oscillation continues and the situation deteriorates, identify the oscillation source and the generator tripping demand; adopt a hierarchical and zonal generator tripping strategy to formulate a differentiated generator tripping plan.

[0121] In a specific embodiment of the present invention, the risk assessment model adapted to the broadband oscillation problem of new energy power stations has the following expression:

[0122]

[0123] In the formula, risk_score represents the risk score; α, β, and γ are weight coefficients, 0 < α < 1, 0 < β < 1, 0 < γ < 1, and α + β + γ = 1;

[0124] slope(PV) represents the slope of the active power-voltage curve of the new energy power station, SCR represents the short-circuit ratio of the new energy power station, and TCI represents the complexity index of the power grid topological structure corresponding to the new energy power station;

[0125] Among them,

[0126]

[0127] In the formula, S sc is the power grid short-circuit capacity, and S rated is the rated power of the power station;

[0128]

[0129] In the formula, node i is the node where the new energy power station is located, node j is the node where the other power stations are located, and d ij is the shortest path length between nodes i and j, and N is the total number of power grid nodes.

[0130] In a specific embodiment of the present invention, generating an anomaly detection model includes:

[0131] Perform wavelet transform on the voltage waveform or current waveform to obtain signal features at different scales; input the wavelet transformed feature data, i.e., the wavelet coefficients, into a deep autoencoder for training to obtain an anomaly detection model. The input of the model is the wavelet coefficients, and the output is the judgment result of whether the original signal is abnormal, where an output of 1 indicates that the original signal is abnormal, and an output of 0 indicates that the original signal is normal.

[0132] In a specific embodiment of the present invention, it also includes:

[0133] In the flexible regulating wheel, the model predictive control algorithm is used to solve the optimization objective function to determine the optimal control sequence. The control sequence is the sequence of increasing gain coefficients of the power system stabilizer. The expression of the optimization objective function is:

[0134]

[0135] In the formula, J(x i ,u i ) is the objective function, x i is the state of the system at step i, u i is the control input at step i, and M is the prediction time domain.

[0136] In a specific embodiment of the present invention, it also includes:

[0137] In the cutting machine control wheel, by calculating the oscillation energy distribution coefficient E ij To identify the oscillation source station;

[0138] in, Node i represents the node where the new energy station is located, and node j represents the grid connection point of the station; the oscillation energy distribution coefficient E ij The larger it is, the more likely it is that the new energy station corresponding to node i can be removed first.

[0139] This can effectively reduce the risk of broadband oscillations, enhance the grid's ability to cope with complex dynamic disturbances, and provide strong support for the safe and stable operation of high-proportion new energy power systems.

[0140] To implement the above embodiment, a third aspect of the present invention provides an electronic device, including:

[0141] at least one processor; and a memory communicatively coupled to the at least one processor;

[0142] Among them, the memory stores instructions executable by the at least one processor, and the instructions are configured to execute the above-mentioned method for governing broadband oscillation based on risk assessment.

[0143] To implement the above embodiments, a fourth aspect embodiment of the present invention proposes a computer-readable storage medium storing computer instructions for causing a computer to execute the above-mentioned method for governing broadband oscillation based on risk assessment.

[0144] It should be noted that the computer-readable medium in the present disclosure may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0145] The above computer-readable medium may be included in the above electronic device; or it may exist separately without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is caused to execute the method for governing broadband oscillation based on risk assessment in the above embodiments.

[0146] Computer program code for performing the operations of this disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0147] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0148] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, "a plurality" means at least two, such as two, three, etc., unless otherwise specifically and clearly defined.

[0149] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process. The scope of the preferred embodiments of this application includes additional implementations, where the functions may be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of this application belong.

[0150] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in conjunction with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion having one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0151] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0152] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by a program instructing relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0153] In addition, in each embodiment of the present application, each functional unit may be integrated into a processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0154] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A broadband oscillation governance method based on risk assessment, characterized in that, Including: In the pre - setting round, based on a risk assessment model adapted to the wide - frequency oscillation problem of new - energy power stations, conduct risk assessment on each new - energy power station to identify high - risk new - energy power stations; In the early - warning round, fuse the wavelet transform and the deep auto - encoder algorithm, conduct multi - scale analysis on the voltage or current waveforms of the high - risk new - energy power stations, and generate an anomaly detection model; Based on the detection results of the anomaly detection model, adopt a dynamic threshold adjustment mechanism to achieve early warning of wide - frequency oscillation risks; In the flexible - adjustment round, when it is detected that there is a small - scale oscillation with a low amplitude in a new - energy power station, adjust the new - energy power station to suppress the oscillation; In the generator - tripping control round, when the oscillation continues and the situation deteriorates, identify the oscillation source and the generator - tripping demand; adopt a hierarchical and zonal generator - tripping strategy to formulate a differentiated generator - tripping plan.

2. The method according to claim 1, wherein The risk assessment model adapted to the wide - frequency oscillation problem of new - energy power stations has the following expression: In the formula, risk_score represents the risk score; α, β, γ are weight coefficients, 0 < α < 1, 0 < β < 1, 0 < γ < 1, and α + β + γ = 1; slope(PV) represents the slope of the active - power voltage curve of the new - energy power station, SCR represents the short - circuit ratio of the new - energy power station, and TCI represents the complexity index of the power - grid topological structure corresponding to the new - energy power station; Wherein, Wherein, S sc is the short-circuit capacity of the power grid, and S rated is the rated power of the substation; Where node i is the node where the new energy station is located, node j is the node where the other stations are located, and d ij is the shortest path length between nodes i and j, and N is the total number of grid nodes.

3. The method according to claim 1, characterized in that The generation of the anomaly detection model includes: Conduct wavelet transform on the voltage waveform or current waveform to obtain signal features at different scales; input the feature data after wavelet transform, that is, wavelet coefficients, into the deep auto - encoder for training to obtain an anomaly detection model. The input of this model is wavelet coefficients, and the output is the determination result of whether the original signal is abnormal. Among them, the output of 1 indicates that the original signal is abnormal, and the output of 0 indicates that the original signal is normal.

4. The method according to claim 1, wherein It also includes: In the flexible - adjustment round, use the model predictive control algorithm to solve the optimization objective function to determine the optimal control sequence. The control sequence is the increment sequence of the gain coefficient of the power - system stabilizer; the expression of the optimization objective function is: where \(J(x i , u i )\) is the objective function, \(x i \) is the state of the system at the \(i\)-th step, \(u i \) is the control input at the \(i\)-th step, and \(M\) is the prediction horizon.

5. The method according to claim 1, characterized in that It also includes: In the generator tripping control wheel, by calculating the oscillation energy distribution coefficient E ij to identify the oscillation source substation; Among them, node i represents the node where the new energy power station is located, and node j represents the grid connection point of the power station; the oscillation energy distribution coefficient E ij The larger it is, it indicates that the new energy power station corresponding to node i can be preferentially disconnected.

6. A broadband oscillation governance system based on risk assessment, characterized in that, Including: A risk assessment module, used in the pre - setting round, based on a risk assessment model adapted to the wide - frequency oscillation problem of new - energy power stations, conduct risk assessment on each new - energy power station to identify high - risk new - energy power stations; An early - warning module, used in the early - warning round, fuse the wavelet transform and the deep auto - encoder algorithm, conduct multi - scale analysis on the voltage or current waveforms of the high - risk new - energy power stations, and generate an anomaly detection model; Based on the detection results of the anomaly detection model, adopt a dynamic threshold adjustment mechanism to achieve early warning of wide - frequency oscillation risks; A flexible - adjustment module, used in the flexible - adjustment round, when it is detected that there is a small - scale oscillation with a low amplitude in a new - energy power station, adjust the new - energy power station to suppress the oscillation; A generator - tripping control module, used in the generator - tripping control round, when the oscillation continues and the situation deteriorates, identify the oscillation source and the generator - tripping demand; adopt a hierarchical and zonal generator - tripping strategy to formulate a differentiated generator - tripping plan.

7. The system according to claim 6, characterized in that, The risk assessment model adapted to the wide - frequency oscillation problem of new - energy power stations has the following expression: Wherein, risk_score represents the risk score; α, β, and γ are weight coefficients, where 0 < α < 1, 0 < β < 1, 0 < γ < 1, and α + β + γ = 1; slope(PV) represents the slope of the active power - voltage curve of the new - energy power station, SCR represents the short - circuit ratio of the new - energy power station, and TCI represents the complexity index of the power - grid topological structure corresponding to the new - energy power station; Among them, Wherein, S sc is the short-circuit capacity of the power grid, and S rated is the rated power of the substation; Where node i is the node where the new energy power station is located, node j is the node where the other power stations are located, and d ij is the shortest path length between nodes i and j, and N is the total number of grid nodes.

8. The system according to claim 6, wherein The abnormal - detection model generation includes: Performing wavelet transform on the voltage waveform or current waveform to obtain signal features at different scales; inputting the feature data after wavelet transform, i.e., wavelet coefficients, into a deep auto - encoder for training to obtain an abnormal - detection model. The input of this model is wavelet coefficients, and the output is the determination result of whether the original signal is abnormal. Among them, an output of 1 indicates that the original signal is abnormal, and an output of 0 indicates that the original signal is normal.

9. The system according to claim 6, wherein It also includes: On the flexible regulating wheel, using the model predictive control algorithm to determine the optimal control sequence by solving the optimization objective function. The control sequence is the increment sequence of the gain coefficient of the power - system stabilizer; the expression of the optimization objective function is: where, J(x i , u i ) is the objective function, x i is the system state at the i-th step, u i is the control input at the i-th step, and M is the prediction horizon.

10. The system according to claim 6, characterized in that It also includes: On the generator tripping control wheel, by calculating the oscillation energy distribution coefficient E ij to identify the oscillation source substation; Among them, node i represents the node where the new energy power station is located, and node j represents the grid connection point of the power station; the oscillation energy distribution coefficient E ij The larger it is, the more it indicates that the new energy power station corresponding to node i can be preferentially disconnected.

Images