Multi-time scale transient stability control method and device for new energy output fluctuation

Abstract

The application discloses a kind of new energy output fluctuation-oriented multi-time scale transient stability control method and device, the method includes: determining new energy historical output sequence, weather characteristics, time characteristics and the historical fluctuation characteristics of new energy output, and characteristic matrix;Determine the new energy output prediction value of each time in preset period based on characteristic matrix;Based on the new energy real output value of target time, the new energy output prediction value after target time is corrected, and the corrected new energy output prediction value is obtained;Based on the new energy output prediction value after correction and the fluctuation characteristics of new energy output of target time, system transient risk assessment is carried out, and risk assessment result is obtained;Based on risk assessment result, intra-day resource adjustment is carried out, and intra-day resource adjustment scheme is obtained, and corresponding control measure is determined based on intra-day resource adjustment scheme and new energy fluctuation scenario of target time.

Description

Technical Field

[0001] This application relates to the field of power system technology, and in particular to a multi-timescale transient stability control method and device for new energy output fluctuations. Background Technology

[0002] With the continuous increase in the penetration rate of new energy sources such as wind power and photovoltaics, the randomness and volatility of new energy output pose a severe challenge to the transient stability of the power system. The volatility of new energy output can easily lead to transient instability. Existing solutions are difficult to balance between quickly resolving transient instability and efficient resource utilization. Summary of the Invention

[0003] This application provides a multi-timescale transient stability control method and device for new energy power output fluctuations, which can effectively address the transient instability caused by new energy power output fluctuations and effectively suppress transient instability while making efficient use of resources.

[0004] In a first aspect, embodiments of this application provide a multi-timescale transient stability control method for fluctuations in new energy power output, including:

[0005] The historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy power generation are determined, and a feature matrix is ​​constructed based on the historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics.

[0006] Based on the feature matrix, the predicted value of new energy output at each moment in the preset time period is determined;

[0007] If the deviation between the predicted value of renewable energy output at the target time and the actual value of renewable energy output at the target time does not meet the preset conditions, the predicted value of renewable energy output after the target time is corrected based on the actual value of renewable energy output at the target time to obtain the corrected predicted value of renewable energy output.

[0008] Based on the corrected predicted value of renewable energy output and the fluctuation characteristics of renewable energy output at the target time, a system transient risk assessment is conducted to obtain the risk assessment results.

[0009] Based on the risk assessment results, intraday resource adjustments are made to obtain an intraday resource adjustment plan, and corresponding control measures are determined based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time.

[0010] Secondly, embodiments of this application provide a multi-timescale transient stability control device for fluctuations in new energy output, including:

[0011] The data preprocessing module is used to determine the historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy output, and to construct a feature matrix based on the historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics.

[0012] The new energy output prediction module is used to determine the predicted value of new energy output at each moment in a preset time period based on the feature matrix.

[0013] The correction module is used to correct the predicted value of new energy output after the target time based on the actual value of new energy output at the target time if the deviation between the predicted value of new energy output at the target time and the actual value of new energy output at the target time does not meet the preset conditions, so as to obtain the corrected predicted value of new energy output.

[0014] The transient risk assessment module is used to conduct a system transient risk assessment based on the corrected renewable energy output forecast and the fluctuation characteristics of renewable energy output at the target time, and obtain the risk assessment result.

[0015] The adjustment control module is used to adjust intraday resources based on the risk assessment results, obtain an intraday resource adjustment plan, and determine corresponding control measures based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time.

[0016] Thirdly, embodiments of this application provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the method provided in embodiments of this application.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to perform the method provided in embodiments of this application.

[0018] The technical solution provided in this application constructs a feature matrix by using historical power output sequences of new energy sources, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy power output. The feature matrix is ​​then used to determine the predicted power output values ​​for each moment within a preset time period. These predicted values ​​are then modified to obtain corrected new energy predicted values, improving prediction accuracy and effectively addressing the problem of insufficient sensitivity to new energy fluctuations. Based on the corrected new energy predicted values ​​and the new energy power output fluctuation characteristics at the target time, a transient risk assessment is performed to obtain the risk assessment results. Based on these results, intraday resource adjustments are made to obtain an intraday resource adjustment plan. Based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time, corresponding control measures are determined, achieving efficient resource utilization. Furthermore, by determining corresponding control measures based on the intraday resource adjustment plan and the new energy fluctuation scenario, the problem of transient instability can be effectively solved, achieving dual optimization of transient stability control and resource utilization. Attached Figure Description

[0019] Figure 1 A flowchart of a multi-timescale transient stability control method for new energy power output fluctuations provided for the implementation of this application;

[0020] Figure 2 A structural block diagram of a multi-timescale transient stability control device for new energy power output fluctuations provided for the implementation of this application;

[0021] Figure 3 This is a schematic diagram of an electronic device structure provided in an embodiment of this application. Detailed Implementation

[0022] The present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] Figure 1 This is a flowchart of a multi-timescale transient stability control method for new energy power output fluctuations provided in this application embodiment. The method can be executed by a multi-timescale transient stability control device for new energy power output fluctuations. The device can be implemented by software and / or hardware and can be configured in electronic devices such as computers.

[0024] like Figure 1 As shown, the technical solutions provided in this application include:

[0025] S110: Determine the historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy output, and construct a feature matrix based on the historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy.

[0026] In this embodiment, data can be acquired from multiple data sources through the data acquisition module. These data sources include: New energy source side: wind power output can be acquired through wind power grid connection point power sensors; photovoltaic power output can be acquired through photovoltaic grid connection point power sensors; wind speed can be acquired through anemometers; and sunlight intensity can be acquired through light sensors. Grid side: node voltage can be acquired through bus node voltage transformers; line current can be acquired through current transformers; and system frequency can be acquired through synchronous phasor measurement devices. Environmental side: temperature, cloud cover, etc., can be acquired from meteorological stations. Historical side: records of new energy output, load, and transient events (such as historical maximum fluctuations) from the database can be retrieved over the past year. By acquiring raw data such as new energy output, grid operation data, and environmental data from multiple data sources, historical new energy output sequences, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy output can be extracted from the raw data, forming a feature matrix.

[0027] In this embodiment, steps S110-S130 can be determined using a new energy output prediction model. Specifically, the four types of features mentioned above can be filtered through the data preprocessing module in the new energy output prediction model to form a feature matrix. .in: The historical power output sequence of new energy sources is obtained by selecting power output data at the 15-minute level for the first 7 days to form a continuous time series sample. Meteorological characteristics (including environmental parameters that affect the output of new energy sources, such as wind speed, light intensity, temperature, and cloud cover). Time characteristics (including hourly and weekday / weekend identifiers, used to capture intraday periodic patterns); Historical fluctuation characteristics (extracting the maximum drop in the corresponding period of the previous 7 days to enhance sensitivity to fluctuations).

[0028] Among these methods, meteorological characteristics can be normalized using formulas. The data is compressed to the interval [0, 1] to eliminate the interference of dimensional differences on the training of the system energy output prediction model, where: This is the original meteorological characteristic data; , These are the historical minimum and maximum values ​​for this meteorological characteristic, respectively. These are the standardized meteorological characteristics.

[0029] Among them, the hour feature in the time feature uses sine and cosine coding, through the formula and ( (For hours, 0-23) This transforms discrete time information into a continuous vector, more accurately capturing intraday periodicity. This is a sinusoidal encoding value for the hourly feature, reflecting the periodic trend of the hour's number within a 24-hour cycle. The cosine encoded value of the hour feature, and Together they form a two-dimensional continuous vector, avoiding "distance distortion" between discrete hours.

[0030] S120: Determine the predicted output value of new energy sources at each moment in the preset time period based on the feature matrix.

[0031] In this embodiment, the predicted output value of new energy at each moment in a preset time period can be obtained based on the feature matrix using the output prediction module in the new energy output prediction model. This output prediction module can be an improved Long Short-Term Memory (LSTM) prediction module. The preset time period can be a future time period starting from the prediction time point. For example, if the prediction starts at 11:00, the prediction time point is 11:00, and the preset time period can be the next 4 hours starting from 11:00, i.e., 11:00-15:00.

[0032] In this embodiment, an attention mechanism is incorporated into the traditional LSTM to enhance the model's ability to capture key temporal features and construct a network structure suitable for the output prediction module.

[0033] In this embodiment, for the construction of the basic LSTM layer, an LSTM unit containing an input gate, a forget gate, a cell state gate, and an output gate can be used. A set of formulas is used to achieve long-term memory and short-term processing of temporal features:

[0034]

[0035] in, For the sigmoid activation function, various weight matrices (such as...) , , , , , ) and bias terms (such as , , , Optimize through subsequent training; The input feature vector at time t is composed of the row vectors in the feature matrix corresponding to time t. The input feature weight matrix is ​​used to quantize the input feature vector at time t. The degree of influence on the input gate output; The hidden state of the LSTM cell at time t-1; Here is the hidden state weight matrix of the input gate, used to quantize the hidden state at time t-1. The degree of influence on the input gate output; This is the bias vector of the input gate, used to adjust the output reference of the input gate; The output vector of the input gate at time t, with a value range of [0,1], is used to control the proportion of new information entering the cell state; The input feature weight matrix of the forget gate is used to quantize the input features at time t. The degree of impact on the output of the forget gate; This is the hidden state weight matrix for the forget gate, used to quantize the hidden state at time t-1. The degree of impact on the output of the forget gate; This is the bias vector for the forget gate, used to adjust the output baseline of the forget gate; This is the output vector of the Forget Gate, with a value range of [0,1], used to control the proportion of historical information retained in the cell state; The input feature weight matrix is ​​used to quantize the input features at time t. The extent of its impact on cell state renewal; Here is the hidden state weight matrix for the cell state, used to quantize the hidden state at time t-1. The extent of its impact on cell state renewal; is the bias vector of the cell state, used to adjust the update benchmark of the cell state; tanh is the hyperbolic tangent activation function, with a value range of [-1,1], used to perform nonlinear transformation on the candidate update values ​​of the cell state; This is the cell state vector at time t-1, storing long-term memory information at time t-1; The cell state vector at time t is updated through the synergistic effect of the forget gate and the input gate, storing the long-term memory information at time t; The input feature weight matrix is ​​used to quantize the input features at time t. The degree of impact on the output of the output gate; The hidden state weight matrix is ​​used to quantize the hidden state at time t-1. The degree of impact on the output of the output gate; This is the bias vector of the output gate, used to adjust the output reference of the output gate; is the output vector of the output gate at time t, with a value range of [0,1], used to control the output ratio from the cell state to the hidden state; The hidden state of the LSTM cell at time t comprehensively reflects the short-term key information at time t.

[0036] To address the issue of attention mechanism embedding and enhance the attention given to recent data in the new energy output prediction model (recent data has a greater impact on short-term predictions), an attention mechanism is added to the hidden state sequence output by the LSTM unit. This is achieved through the formula... Calculate the hidden state at time t Attention weights ;in, Let t be the energy value of the hidden state at time t; Energy value , This is the weight matrix. For bias terms, The sequence length; Let be the energy value of the hidden state at time k, where k ranges from [1, T]; and through... Generate the hidden state after weighted fusion This strengthens the role of key temporal features.

[0037] For the output layer construction, the hidden states will be integrated with the attention mechanism. Input the fully connected layer, through the formula Mapping to generate the predicted output of new energy sources at time t ( This is the output layer weight matrix. (as a bias term), completing the transformation from features to prediction results.

[0038] S130: If the deviation between the predicted value of renewable energy output at the target time and the corresponding actual renewable energy output does not meet the preset conditions, the predicted value of renewable energy output after the target time is corrected based on the actual renewable energy output at the target time to obtain the corrected predicted value of renewable energy output.

[0039] In this embodiment, to address the discrepancy between the actual output of new energy sources and their predicted values, short-term forecasts can be corrected hourly based on the latest data to improve forecast timeliness. Step S130 can be executed through the intraday rolling correction module in the new energy output forecasting model. Specifically, the actual output value of new energy sources can be retrieved hourly. , and the corresponding predicted value of new energy power output The data is compared and the deviation is calculated. When the deviation exceeds a preset threshold, a prediction correction mechanism is triggered. For example, a feature matrix can be constructed based on historical data from the past 7 days (with a time granularity of 15 minutes) to obtain the predicted renewable energy output values ​​for each time point in the next 4 hours. For instance, the predicted renewable energy output values ​​from 11:00 to 15:00 can be obtained. If the current time is the target time, which is 12:00, the actual renewable energy output value at the current time is retrieved, and the predicted renewable energy output values ​​from 13:00 to 15:00 are corrected based on the actual renewable energy output value at the current time.

[0040] In this embodiment, a weighted fusion method can be used to update the predicted value of future renewable energy output. Optionally, the correction of the predicted value of renewable energy output after the target time based on the actual renewable energy output value at the target time includes:

[0041] The predicted output value of new energy sources is corrected based on the following formula:

[0042]

[0043] in, The corrected predicted output value of new energy sources at time t. for The real output value of new energy sources at any given moment; The weighting coefficients for the predicted output of new energy sources at time t; for Weighting coefficients for the actual output value of new energy sources at any given time; For time intervals; where, It can be greater than ,in, It could be 0.7. It can be 0.3, where the weighting coefficient can be dynamically adjusted according to the actual deviation (the larger the deviation, the higher the weight of the true value of new energy output). This is a time interval parameter, which can take the value of 1 hour.

[0044] In this embodiment, before step S120, the method may further include iteratively training the power prediction module using training set data, adjusting the parameters of the power prediction module based on a loss function, collecting validation set data to validate the power prediction module, and adjusting the feature matrix if the deviation between the loss function value corresponding to the validation set data and the loss function value corresponding to the training set data exceeds a preset deviation; wherein, the loss function is:

[0045]

[0046] in, The value of the loss function; Let t be the predicted output value of new energy sources at time t; The actual output value of the new energy source at time t; The predicted output of new energy sources at time t+1; This is the fluctuation penalty coefficient.

[0047] Specifically, the parameters of the new energy power output prediction model can be trained and adjusted through the model training and optimization module in the new energy power output prediction model to reduce prediction errors and avoid overfitting, ensuring the model's generalization ability in real-world scenarios. The loss function uses a composite loss function with a fluctuation penalty term, which controls overall prediction bias while enhancing the ability to capture power output fluctuations. In this loss function, the first term is the sum of the squared errors between the predicted new energy power output value and the corresponding actual new energy power output value, which can be used to control overall bias; the second term is the sum of the absolute values ​​of the fluctuations in the predicted new energy power output value, which is penalized by the fluctuation penalty coefficient. (Set according to the scenario) Improve the model's sensitivity to sudden changes in output; 96 is the number of time points with 15-minute granularity within 24 hours to ensure full coverage of the intraday cycle.

[0048] In this embodiment, the Adam optimizer can be used to iteratively update the parameters of the power output prediction module (the learning rate and number of iterations are adjusted according to the training effect), and an early stopping mechanism is introduced: if the loss function value of the validation set does not decrease after 10 consecutive iterations, training can be stopped to avoid overfitting the training data. During training, the error changes between the training set and the validation set are monitored in real time. If the deviation is too large, the process returns to the feature preprocessing stage to readjust the features in the input feature matrix until the power output prediction module converges and its generalization ability meets the standard. Specifically, features can be added to the feature matrix, such as real-time weather warning signals; or the feature granularity can be refined, for example, by splitting the data granularity into 10-minute intervals; or cross features can be added, such as "hour × season × weather type" to increase the amount of information. It should be noted that the above training process mainly involves parameter adjustments to the power output prediction module (the improved LSTM module) in the new energy power output prediction model.

[0049] S140: Based on the corrected predicted value of renewable energy output and the fluctuation characteristics of renewable energy output at the target time, a system transient risk assessment is conducted to obtain the risk assessment results.

[0050] In this embodiment, optionally, the system transient risk assessment based on the corrected new energy power output prediction value and the fluctuation characteristics of the new energy power output at the target time includes: determining the power angle stability margin and voltage stability margin based on the corrected new energy power output prediction value; and determining the risk level based on the power angle stability margin, the voltage stability margin, and the fluctuation characteristics of the new energy power output at the target time.

[0051] In this embodiment, the transient risk assessment module can quantify the transient stability of the system and classify risk levels based on the corrected renewable energy output forecast values, providing a basis for subsequent resource optimization. Specifically, 1) Forecast data reception and preprocessing: It can receive relevant data output from the renewable energy output forecast model and perform preliminary processing to lay the foundation for subsequent assessment. 2) Data reception: Obtain the corrected renewable energy output forecast values. And the fluctuation characteristics of new energy output at the target time (e.g., the current time), including the maximum drop (unit: MW) and fluctuation rate (unit: MW / min). 3) Data verification: Check the integrity of the data. If there are missing data (e.g., some time periods...) (Missing data) is filled using linear interpolation; at the same time, the rationality of the data is checked, for example, the maximum drop should not exceed 50% of the total installed capacity of new energy. If it exceeds this, it is marked as abnormal and fed back to the new energy output prediction model. 4) Data format conversion: The corrected new energy output prediction values ​​are converted into a format that matches the grid topology data to ensure that subsequent power flow calculations and other processes can be called normally.

[0052] In this embodiment, the system's power angle stability can be evaluated through equivalent simplification and energy calculation. The system equivalent simplification can employ the extended equal-area criterion, simplifying the multi-machine power system into an equivalent two-machine model consisting of a "critical unit" and "the remaining units," highlighting the unit that plays a crucial role in transient stability. The energy area calculation can determine the acceleration area absorbed by the critical unit during the acceleration phase. (Unit: MW) s) and the deceleration area released during the deceleration phase (Unit: MW) s). Here, the acceleration area reflects the excess energy gained by the unit due to disturbance, and the deceleration area reflects the system's ability to suppress acceleration. This can be determined according to the formula:

[0053] Calculate the power angle stability margin (unit:%). The larger the value, the better the system's power angle stability. hour, The system's transient power angle is stable.

[0054]

[0055]

[0056] in, To predict fluctuations in new energy power output, To speed up the process; This is the predicted power output value 1 second after the disturbance occurs, for the new energy fluctuation prediction model. Available energy storage power based on predicted risk configuration Let be the deceleration time. Wherein, the predicted output value of the new energy source at time t... Forecast value of new energy power output at time t+1 Predicting fluctuations in new energy output .

[0057] In this embodiment, the system voltage stability level is assessed by combining the grid topology with the corrected renewable energy output forecast. Specifically, the assessment can be based on the corrected renewable energy output forecast. Load data and acquired power grid topology data (such as line impedance, transformer parameters, etc.) are used to perform power flow calculations to obtain the voltage at each bus node. (Unit: pu). From the calculated node voltages, the lowest voltage value is selected. (Unit: pu). Based on the formula

[0058] Calculate voltage stability margin (Unit: %), of which pu represents the rated voltage. The larger the value, the more sufficient the system voltage stability reserve.

[0059] Specifically, the risk level of the system can be determined by comprehensively considering the power angle stability margin, voltage stability margin, and fluctuation characteristics of renewable energy output. The power angle stability margin can be used as a starting point. Voltage stability margin The maximum drop in new energy output is used as the core basis for risk level classification.

[0060] Specifically, when , And the maximum drop in power output from new energy sources When the risk level is MW (Modular Motion), the system is considered low-risk, indicating good transient stability and an extremely low probability of instability. When the 12% threshold is met... 15% Or 10MW Maximum drop in power output of new energy sources If any of the MW (Modular, Variable, and Variable) indicators is classified as medium risk, the system has a certain risk of transient instability and requires appropriate reserves of stability resources; when , When the maximum power output drop of new energy sources exceeds 20MW, it is considered high-risk, indicating a high risk of system transient instability. Priority should be given to allocating stable resources and preparing control measures. The risk level, , The corresponding judgment criteria are compiled into a risk report. The risk assessment results may include power angle stability margin, voltage stability margin, and the corresponding risk level.

[0061] S150: Based on the risk assessment results, intraday resource adjustments are made to obtain an intraday resource adjustment plan, and a corresponding control strategy is determined based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time.

[0062] In this embodiment, the evaluation results are transmitted to the optimization model, and relevant data is stored for subsequent analysis. The power angle stability margin can be... Voltage stability margin The risk level is transmitted to the optimization model, and various data generated during this assessment process, including the original prediction data, calculated energy area, voltage value and risk level, are stored in the database to provide data support for post-assessment and iteration.

[0063] In this embodiment, optionally, intraday resource adjustments are performed based on the risk assessment results to obtain an intraday resource adjustment plan, including: defining the power system state using the power angle stability margin, the voltage stability margin, the maximum power drop of new energy output, the energy storage reserve capacity, and the load shelving reserve; defining the power system execution actions using the energy storage reserve adjustment capacity and the load shelving reserve adjustment amount; and establishing a reward function using the power angle stability margin, the voltage stability margin, and the control cost of the intraday resource adjustment plan; determining the optimal execution action of the power system based on the power system state at the target time and the reward function, as the intraday resource adjustment plan; wherein; the energy storage reserve adjustment capacity satisfies the constraint within a first preset range; and the load shelving reserve adjustment amount satisfies the constraint within a second preset range;

[0064] The reward function is: ;

[0065] in, This refers to the stability margin of the power angle; This refers to the voltage stability margin; Cost control for intraday resource adjustment plans; To maximize allowable cost control, This is the reward value.

[0066] In this embodiment, an optimization model can be used to optimize the allocation of schedulable resources based on risk assessment results, reducing costs while ensuring system stability. Specifically, the types of resources available for stability control and related parameters can be identified first, providing basic data for resource optimization. Resource type determination involves identifying schedulable stable resources, primarily including energy storage systems and controllable loads. Key parameters for various resources are obtained from the data acquisition module. The parameters for energy storage systems may include: total capacity. (Unit: MWh), Maximum charge / discharge power (Unit: MW) and standby cost coefficient (Unit: Yuan / kWh). The parameters for controllable load may include: total shelvable load. (Unit: MW), Unit compensation cost (Unit: Yuan / MW) h). Resource status verification: Check the current status of various resources. For example, the state of charge (SOC) of the energy storage system should be within a reasonable range (e.g., 20%-80%). If it exceeds the range, record it and consider it in subsequent optimizations.

[0067] In this embodiment, the power system status is collected once every hour to obtain the latest status variables from relevant modules or models and verify their validity, providing reliable input for subsequent adjustments, as shown in Table 1.

[0068] Table 1 Power System Status Data Table

[0069]

[0070] In this embodiment, if any of the above variables exceeds a reasonable range, an exception handling mechanism is triggered. Specifically, if... or If the risk is identified as "emergency instability risk," skip routine adjustments and directly trigger the emergency measures of the real-time collaborative control module (such as emergency energy storage discharge); if the energy storage SOC < 20%, mark it. Given the "low capacity" status, this adjustment only allows for increases in capacity. (Reduction is prohibited), and the maximum adjustment amount is ≤ 10% of the total capacity; if Data missing: Use linear interpolation (based on the fluctuation trend of the previous 30 minutes) to fill in the missing data; the error must be ≤5%. The largest drop in energy output.

[0071] In this embodiment, the current transient risk level (consistent with the transient risk assessment module level standard) can be mapped first based on the real-time state variables mentioned above, and then the priority of resource adjustment can be determined.

[0072] Among them, combining 3 core indicators ( , , Risks are determined according to the rules shown in Table 2.

[0073] Table 2 Risk Level Information Table

[0074]

[0075] In this embodiment, the actions performed by the power system have a certain priority; specifically, the actions to be performed... ( Adjusting capacity for energy storage backup The priority rule for adjusting the available load reserve capacity can be: prioritize adjusting the energy storage reserve capacity. Because "the unit stabilization cost of energy storage is lower than the load shedding cost" (e.g., energy storage cost is 0.5 yuan / kWh, and load shedding compensation is 200 yuan / MW). h), only when Reaching capacity limit ( Only when the SOC is insufficient should the load be adjusted for standby. The adjustment range strictly adheres to the ±5% constraint. , That is, the energy storage reserve adjustment capacity meets the constraint of a first preset range, and the load shelving reserve adjustment amount meets the constraint of a second preset range. The target time is the energy storage reserve capacity, which is the current time. The available load is reserved for the target time, i.e., the current time.

[0076] In this embodiment, the reward value can be calculated based on the real-time status of the power system. The optimal resource adjustment amount is determined by "maximizing the reward value," ensuring that the intraday resource adjustment plan simultaneously satisfies "stable improvement" and "controllable cost." In the above reward function, the parameter 0.6 is the weight coefficient of stability margin, and since transient stability is the core objective, its weight is higher than that of cost (0.4). Considering both stability margins, the minimum value of the power angle stability margin and voltage stability margin is chosen to avoid situations where one indicator fails while another fails (e.g., ...). but (The overall stability margin is calculated at 12%). The parameter 0.4 is the weighting coefficient for the cost ratio: taking into account economic efficiency and avoiding excessive resource allocation that could lead to a surge in costs. Cost control for intraday resource adjustment plan (RMB): ;in, For energy storage backup costs, The cost of load shedding compensation all comes from the data acquisition module. The maximum allowable control cost (in yuan) can be determined based on the daily control cost ceiling optimized the day before, which is usually 1 / 24 of the daily control cost budget.

[0077] In this embodiment, for different risk levels, an enumeration method is used (due to the adjustment range being only ±5%, the enumeration quantity is small and the real-time performance is high) to calculate the corresponding resource adjustment amount. ,choose The most ambitious option:

[0078] In high-risk scenarios: only the adjustment amount for "increasing reserves" is enumerated ( ; ); Low-risk scenarios: Only enumerate the adjustment amount for "reduce reserve" ( ; ), prioritize reducing To reduce costs; Medium-risk scenario: Enumerate the adjustment amount for "small increase / maintain" ( ; To avoid over-adjustment, under different risk levels, different resource adjustment amounts are enumerated, and the corresponding reward value is calculated using a reward function. The resource adjustment amount corresponding to the maximum reward value is selected to obtain the intraday resource adjustment plan.

[0079] In this embodiment, after intraday resource optimization and adjustment, the following constraints need to be met:

[0080] Energy storage backup capacity constraints: ( (Total energy storage capacity)

[0081] Shelvable load standby constraints: ( (Total shearable load);

[0082] Energy storage SOC constraint: after adjustment The corresponding SOC should be between 20% and 80%, for example, MWh, SOC=30% corresponding to MWh, after adjustment It must not exceed 15MWh.

[0083] In this embodiment, the corresponding control strategy is determined based on the intraday resource adjustment plan and the renewable energy fluctuation scenario at the target time, including: if the renewable energy fluctuation scenario at the target time is a small fluctuation scenario, calculating the virtual inertia of the wind power / photovoltaic converter and controlling the wind power / photovoltaic converter based on the virtual inertia; if the renewable energy fluctuation scenario at the target time is a medium fluctuation scenario, discharging energy storage at a first rate based on the energy storage reserve capacity and cutting off load based on the load shelving reserve; if the renewable energy fluctuation scenario at the target time is a high fluctuation scenario, discharging energy storage at a second rate based on the energy storage reserve capacity and cutting off load based on the load shelving reserve.

[0084] Specifically, the collaborative control model can take corresponding control measures based on intraday resource adjustment plans to suppress transient instability when the actual output of new energy sources fluctuates. It can monitor the fluctuations in new energy output in real time and classify the fluctuation scenarios. Real-time data is collected through devices such as synchronous phasor measurement units (PMUs) at a sampling frequency of 100Hz to obtain the true output of new energy sources. Data such as [data missing]. Specifically, for the calculation of the actual power output fluctuation of new energy sources, the actual power output fluctuation of new energy sources is calculated within 100ms, using the following formula: ,in This represents the actual power output fluctuation of new energy sources (unit: MW, negative values ​​indicate power output drops). The actual output value of new energy at time t (unit: MW). The actual power output of new energy sources at time t-1 (unit: MW). Fluctuation scenarios are divided based on the aforementioned fluctuations in actual new energy power output.

[0085] Specifically, for scenarios with small fluctuations, when the actual power output fluctuations of new energy sources are monitored... With a capacity of MW and the system at a low / medium risk level, fluctuations can be suppressed through self-regulation of the renewable energy source. The core strategy employed is virtual inertia control: based on the system frequency deviation collected by the synchronous phasor measurement unit (PMU). ( Hz, f is the real-time frequency of the system), according to the formula ( The basic inertia, for example, could be 2s. MW, Calculate virtual inertia using frequency deviation coefficients. The virtual inertia control command is then sent to the wind power converter or photovoltaic converter. By adding virtual inertia to the converter, the system inertia is increased, and frequency fluctuations are quickly suppressed.

[0086] Specifically, for scenarios with moderate disturbances, when the actual output fluctuation of new energy sources is within a certain range... When the system has a capacity of MW and is classified as medium / high risk, energy storage can be used as the core approach: energy storage backup capacity can be obtained. Can be switched off for standby and maximum charge / discharge power Calculate the available power of energy storage (10 represents the maximum duration of emergency discharge, for example, it could be 10 seconds).

[0087] according to Determine the energy storage discharge power and prioritize allocating all energy storage power to the node with the lowest voltage as calculated by power flow calculation; if the energy storage reserve capacity cannot fully fill the power gap ( If the load is cut off, no more than 30% of the available load will be reserved (prioritizing the cut-off of low-importance industrial interruptible loads), while virtual inertia control will be retained as an auxiliary measure. Control commands will be issued in the order of "energy storage → load shedding" with an interval of 50ms to ensure that the execution is completed within 300ms, balancing the stabilization effect and resource cost.

[0088] Specifically, for scenarios with large fluctuations, when the actual output of new energy fluctuates... When the system is at high risk (MW), multi-resource joint control is adopted to quickly curb the instability trend: the first step is to trigger emergency discharge of energy storage, according to the discharge power of the energy storage system. The energy storage discharge rate is set at the maximum rate (1.2 is the overload factor), the duration of which does not exceed 10 seconds, and the total discharge amount does not exceed the energy storage reserve capacity. The third step is if a power deficit still exists after the energy storage discharges ( Then calculate the amount of load that needs to be removed. And strictly control the standby load that can be switched off. Within the specified range, priority is given to cutting off marked low-priority loads; instructions are issued in the order of "energy storage → load shedding" with an interval of 50ms, and the voltage and frequency recovery status is monitored in real time to ensure that the voltage is maintained above 0.9pu and the frequency deviation is controlled within ±0.15Hz within 1s, with a response delay of no more than 300ms, so as to minimize the risk of transient instability.

[0089] In this embodiment, control commands of the control strategy can be sent to execution nodes such as energy storage and load through the scheduling data network, requiring a response delay of ≤300ms, and real-time monitoring of the command execution status of each execution node, such as the actual discharge power of energy storage and the actual load shedding amount, as well as collecting feedback information from the execution nodes, including whether the command execution was successful and the actual execution parameters.

[0090] The technical solution provided in this application constructs a feature matrix by using historical power output sequences of new energy sources, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy power output. The feature matrix is ​​then used to determine the predicted power output values ​​for each moment within a preset time period. These predicted values ​​are then modified to obtain corrected new energy predicted values, improving prediction accuracy and effectively addressing the problem of insufficient sensitivity to new energy fluctuations. Based on the corrected new energy predicted values ​​and the new energy power output fluctuation characteristics at the target time, a transient risk assessment is performed to obtain the risk assessment results. Based on these results, intraday resource adjustments are made to obtain an intraday resource adjustment plan. Based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time, corresponding control measures are determined, achieving efficient resource utilization. Furthermore, by determining corresponding control measures based on the intraday resource adjustment plan and the new energy fluctuation scenario, the problem of transient instability can be effectively solved, achieving dual optimization of transient stability control and resource utilization.

[0091] In this embodiment of the application, optionally, the step of adjusting intraday resources based on the risk assessment results to obtain an intraday resource adjustment plan includes: adjusting intraday resources based on the risk assessment results using an optimization model to obtain an intraday resource adjustment plan;

[0092] The control strategy is determined based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time, including: determining the corresponding control strategy through a collaborative control model based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time.

[0093] The method further includes:

[0094] Obtain control effect evaluation indicators, and adjust the parameters of the new energy output prediction model, the optimization model, and the collaborative control model based on the control effect evaluation indicators; wherein the control effect evaluation indicators include stability evaluation indicators and economic evaluation indicators.

[0095] Specifically, the control effect can be evaluated through a post-evaluation and iteration module, and the model parameters and strategies can be optimized based on the evaluation results. The control effect can be evaluated from two dimensions: stability and economy.

[0096] The stability evaluation includes frequency and voltage metrics. Specifically, the frequency metric involves calculating the maximum frequency deviation. The requirement is ≤±0.15Hz, where Maximum frequency deviation during the control process (unit: Hz). Voltage index: Statistical minimum voltage value. The requirement is ≥0.9 pu, where The actual minimum voltage during the control process (unit: pu).

[0097] Among them, the economic indicator assessment includes calculating the unit stable cost using the following formula: ,in Unit stabilization cost (unit: yuan / (MW)) s)), Cost control for intraday resource adjustment plan (unit: yuan). To control the stability margin (including voltage stability margin and power angle stability margin) (unit: %). To control the stability margin (in %), it is required that Yuan / (MW) (s). By combining the evaluation results of stability assessment indicators and economic assessment indicators, a control effectiveness evaluation report can be generated.

[0098] In this embodiment, the relevant model parameters can be adjusted and optimized based on the evaluation results. Specifically, regarding the adjustment of the parameters for the new energy output prediction model, if the predicted value of new energy output... Compared with the actual output value of new energy If the error is >10%, add relevant data from the target time to the training set and adjust the attention weights of the improved LSTM module, increasing the weights of recent data (e.g., adding recent data to the training set). Increase by 0.1).

[0099] Based on the above embodiments, strategy optimization suggestions can be formed based on the control effect evaluation results and model parameter adjustments, and relevant information can be fed back to each related module to promote continuous optimization of the overall strategy.

[0100] Specifically, resource allocation recommendations can be generated by combining the correlation analysis of "fluctuation-resource-cost". For example, in fluctuation scenarios above 10MW, when the unit stabilization cost supported by energy storage is lower than the load shedding, the recommendation is to "prioritize the use of energy storage resources and reduce the load shedding amount"; if the long-term utilization rate of a certain type of resource is less than 30%, it is recommended to adjust the reserve ratio of that type of resource.

[0101] Specifically, suggestions for adjusting control strategies are proposed based on the control effects in different fluctuation scenarios. For example, in scenarios with large fluctuations (large impacts), if the voltage recovery speed does not meet expectations, it is recommended to optimize the response speed parameters of the unit's reactive power regulation; if the virtual inertia control is not effective in suppressing frequency in scenarios with small fluctuations, it is recommended to adjust the base inertia or coefficients for virtual inertia calculation.

[0102] Specifically, optimization suggestions can be proposed based on prediction errors and assessment accuracy. If the prediction error increases significantly under specific meteorological conditions (such as heavy rain), it is recommended to increase the feature weight of such meteorological conditions in the new energy output prediction model; if the risk level determination deviates significantly from the actual control requirements, it is recommended to recalibrate the threshold for risk level classification.

[0103] Based on the above embodiments, iterative information can also be fed back.

[0104] Specifically, model parameter feedback: The adjusted attention weights, cost weights, etc. of the LSTM module can be fed back to the new energy output prediction model, optimization model, and collaborative control model respectively, to ensure that each part uses the updated parameters for subsequent calculations.

[0105] Strategy suggestion feedback: The generated strategy optimization suggestions are compiled and fed back to the relevant control strategy formulation stages. For example, resource allocation optimization suggestions are fed back to the optimization model as a reference for formulating resource allocation schemes; control strategy optimization suggestions are fed back to the collaborative control model to guide it in adjusting the scenario-adaptive control strategy.

[0106] Data support feedback: Key data generated during this evaluation and iteration process, such as comparisons of stability indicators before and after optimization, and analysis of the expected effects of strategy recommendations, will be stored in the database and shared with various modules or models to provide data support for subsequent optimization.

[0107] For example, a power grid includes wind power (installed capacity 200MW) and photovoltaic power (installed capacity 150MW), with a new energy penetration rate of 35%. During the summer afternoons (14:00-16:00), affected by severe convective weather, wind power output may experience a sudden drop in second-level magnitude (maximum drop of 30MW), and photovoltaic power may experience fluctuations of 10-15MW due to cloud cover. It is necessary to achieve transient stability and coordinated optimization of new energy consumption through the control method provided in the embodiments of this application.

[0108] Implementation steps (according to closed-loop control process)

[0109] I. Data Acquisition Module: Fusion of Real-Time and Historical Data

[0110] Data source collection

[0111] New energy side: wind power grid connection point power sensor (actual output 120MW), photovoltaic grid connection point power sensor (actual output 80MW), anemometer (10m / s, expected to drop to 5m / s after 30 minutes), and light sensor (800W / ㎡, expected to drop to 400W / ㎡ after 10 minutes).

[0112] Grid side: bus node voltage (1.02 pu), line current (450 A), system frequency (50.02 Hz);

[0113] Environmental data: Weather station data (temperature 32℃, cloud cover 30%, expected to rise to 80% in 15 minutes);

[0114] Historical data: retrieve the maximum wind power drop (25MW) and photovoltaic fluctuation records (±12MW) for the same period in the past year (summer afternoon).

[0115] Data Synchronization Storage

[0116] Data is synchronized to a real-time database through the power dispatch network, with timestamps accurate to the second (e.g., 14:00:00, 14:00:01), providing highly timely input for subsequent forecasts.

[0117] II. New Energy Fluctuation Prediction Model:

[0118] The data preprocessing module performs data preprocessing:

[0119] Filtering core features: 15-minute output data of the previous 7 days (historical fluctuation features), real-time wind speed / sunlight (meteorological features), 14:00 (hourly features, encoded as a continuous vector by sine and cosine).

[0120] Standardization process: The light intensity (400-1000W / ㎡) is compressed to the [0,1] range using a normalization formula to eliminate the influence of dimensions.

[0121] Improved LSTM module prediction:

[0122] Embedded attention mechanism: Assign higher attention weight (α=0.6) to data from the past 30 minutes to enhance the capture of short-term fluctuations;

[0123] Forecast results: Output trajectory from 14:00 to 16:00. It is expected that wind power will drop sharply by 28MW at 14:15 (120MW→92MW), and photovoltaic power will drop to 65MW at 14:30 due to cloud cover.

[0124] Intraday rolling module fix:

[0125] At 14:05, the deviation between the actual output value and the predicted output value of new energy reached 6% (triggering the correction threshold). The subsequent prediction was corrected by weighted fusion algorithm (70% predicted value + 30% actual value): the maximum drop in wind power was corrected to 30MW and the minimum output of photovoltaic was corrected to 62MW.

[0126] III. Transient Risk Assessment Module: Quantifying Risk Levels

[0127] Data preprocessing and validation

[0128] Receive the revised new energy output forecast, fill in the missing data from 14:20 to 14:22 through linear interpolation, and verify the maximum drop (30MW≤200MW×50%, reasonable and effective).

[0129] Stability margin calculation

[0130] Stability margin of work angle: calculated by extending the equal area criterion, accelerating area. =80MW s, deceleration area =100MW s, =1-80 / 100=20%;

[0131] Voltage stability margin: the lowest node voltage calculated from power flow. =0.88pu, =1-0.88 / 1.0=12%.

[0132] Risk level determination

[0133] Due to voltage stability margin =12% ​​< 15%, which is considered high risk and requires priority allocation of stable resources.

[0134] IV. Stable Resource Optimization Module: Dynamically Configure Resources

[0135] Scheduled resource parameters

[0136] Energy storage: Total capacity 50MWh, maximum charge / discharge power 20MW, backup cost 0.5 yuan / kWh;

[0137] Controllable load: Total slack-off capacity 30MW, compensation cost 200 yuan / MW h;

[0138] Synchronous generator units: maximum reactive power reserve of 50,000 kvar, parameter adjustment cost of 0.1 yuan / kvar.

[0139] Intraday resource adjustments (based on real-time risk)

[0140] State s: =20%, =12%, maximum dropout rate 30MW, current energy storage reserve 10MWh;

[0141] Action a: Based on the reward function (0.6 × stability margin - 0.4 × cost ratio), increase the energy storage reserve capacity by 5% (to 10.5MWh) and the load shelving reserve by 5% (to 1.5MW).

[0142] V. Collaborative Control Model: Scene-Adaptive Control

[0143] Fluctuation scene recognition

[0144] At 14:15, real-time monitoring showed a sudden drop of 30MW in wind power output (|ΔP|=30MW>20MW), which was determined to be a major impact scenario.

[0145] Implementation of control measures

[0146] Emergency discharge of energy storage: Discharge at a maximum rate of 1.2 × 20 MW = 24 MW for 10 seconds;

[0147] Load shedding standby control: A power shortfall of 30MW needs to be compensated, deducting 24MW of energy storage, and shedding 6MW of load. =30-24=6MW).

[0148] Instruction execution and feedback

[0149] The control command was sent through the dispatch data network with a response delay of 250ms (≤300ms). The feedback information showed that the actual energy storage discharge was 23.8MW, the load shedding was 5.9MW, and the execution was successful.

[0150] VI. Post-event evaluation and iteration module: Optimization strategy

[0151] Control effect evaluation

[0152] Stability evaluation indicators: maximum frequency deviation 0.1Hz (≤±0.15Hz), minimum voltage 0.92pu (≥0.9pu);

[0153] Economic evaluation indicators: The control cost of the intraday resource adjustment plan is 25,000 yuan, and the stability margin is increased by 8% (from 12% to 20%). The unit stabilization cost = 25,000 yuan / (8% × corresponding energy) = 3.1 yuan / (MW) s) (≤8 yuan / (MW) s)).

[0154] Model parameter iteration

[0155] Since the prediction error (30MW actual drop vs 28MW initial prediction) is ≤10%, there is no need to adjust the LSTM attention weights; the control effect meets the target, so the current parameters are maintained.

[0156] Strategy optimization suggestions

[0157] In high-impact scenarios, the cost of energy storage support is lower than that of load shedding. It is recommended to prioritize the use of energy storage in similar scenarios in the future (which can reduce the amount of load shedding by 10%).

[0158] Therefore, this application constructs a closed-loop control system of "data acquisition-prediction-evaluation-optimization-control-iteration". Through the coordinated linkage of each part, it achieves precise response to transient instability caused by fluctuations in renewable energy output, breaking through the limitations of the fragmented links in traditional control. By using a renewable energy output prediction mechanism based on an improved LSTM module, and integrating an attention mechanism and an intraday rolling correction strategy, the predictive ability of output fluctuation trends and characteristics is improved, solving the problem of insufficient sensitivity of traditional prediction models to random fluctuations. This application establishes a multi-dimensional transient risk assessment and resource optimization collaborative mechanism, combining power angle stability margin and voltage stability margin to classify risk levels, realizing dynamic allocation of stable resources, and avoiding resource waste caused by indiscriminate control. Through scenario-adaptive real-time collaborative control and closed-loop iterative strategies, corresponding control measures are taken according to the renewable energy fluctuation scenario, and the model parameters and control strategies are continuously optimized through ex-post evaluation, enhancing the adaptability and economy of the control scheme.

[0159] Figure 2 This is a structural block diagram of a multi-timescale transient stability control device for new energy power output fluctuations provided in an embodiment of this application, as shown in the following example. Figure 2 As shown, the device includes:

[0160] The data preprocessing module 210 is used to determine the historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy output, and to construct a feature matrix based on the historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy output.

[0161] The power output prediction module 220 is used to determine the predicted value of new energy power output at each moment in a preset time period based on the feature matrix.

[0162] The correction module 230 is used to correct the predicted value of new energy output after the target time based on the actual value of new energy output at the target time if the deviation between the predicted value of new energy output at the target time and the actual value of new energy output at the target time does not meet the preset conditions, so as to obtain the corrected predicted value of new energy output.

[0163] The transient risk assessment module 240 is used to conduct a system transient risk assessment based on the corrected new energy output prediction value and the fluctuation characteristics of the new energy output at the target time, and obtain the risk assessment result.

[0164] The adjustment control module 250 is used to adjust intraday resources based on the risk assessment results, obtain an intraday resource adjustment plan, and determine corresponding control measures based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time.

[0165] In an optional embodiment, determining the predicted output value of new energy sources at each moment within a preset time period based on the feature matrix includes:

[0166] The feature matrix is ​​determined by the new energy output prediction model, and the new energy output prediction value and the corrected new energy output prediction value are obtained at each time in the preset time period.

[0167] The device model iterative optimization module is used for:

[0168] The new energy output prediction model is iteratively trained using training set data, and the parameters of the new energy output prediction model are adjusted based on the loss function.

[0169] The new energy output prediction model is validated by collecting validation set data. If the deviation between the loss function value corresponding to the validation set data and the loss function value corresponding to the training set data exceeds a preset deviation, the feature matrix is ​​adjusted. The loss function is:

[0170]

[0171] in, The value of the loss function; The predicted output of new energy sources at time t; The actual output value of the new energy source at time t; The predicted output of new energy sources at time t+1; This is the fluctuation penalty coefficient.

[0172] In an optional embodiment, the correction of the predicted new energy output value after the target time based on the actual new energy output value at the target time includes:

[0173] The predicted output value of new energy sources is corrected based on the following formula:

[0174]

[0175] in, The corrected predicted output value of new energy sources at time t. Let t be the predicted output value of new energy sources at time t; for The real output value of new energy sources at any given moment; The weighting coefficients for the predicted output of new energy sources at time t; for Weighting coefficients for the actual output value of new energy sources at any given time; For time intervals.

[0176] In an optional embodiment, the system transient risk assessment based on the corrected renewable energy output forecast and the fluctuation characteristics of renewable energy output at the target time includes:

[0177] The power angle stability margin and voltage stability margin are determined based on the corrected new energy output prediction values.

[0178] The risk level is determined based on the power angle stability margin, the voltage stability margin, and the fluctuation characteristics of the new energy output at the target time.

[0179] In one optional embodiment, intraday resource adjustments are made based on the risk assessment results to obtain an intraday resource adjustment plan, including:

[0180] The state of the power system is defined by the power angle stability margin, the voltage stability margin, the maximum drop in new energy output, the energy storage reserve capacity, and the load shelving reserve. The execution actions of the power system are defined by the energy storage reserve adjustment capacity and the load shelving reserve adjustment amount. A reward function is established by the power angle stability margin, the voltage stability margin, and the control cost of the intraday resource adjustment scheme.

[0181] The optimal action of the power system is determined based on the state of the power system at the target time and the reward function, serving as an intraday resource adjustment scheme; wherein the energy storage reserve adjustment capacity satisfies the constraint within a first preset range; and the load shelving reserve adjustment amount satisfies the constraint within a second preset range.

[0182] The reward function is: ;

[0183] in, This refers to the stability margin of the power angle; This refers to the voltage stability margin; Cost control for intraday resource adjustment plans; To maximize allowable cost control, This is the reward value.

[0184] In an optional embodiment, determining the corresponding control measures based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time includes:

[0185] If the new energy fluctuation scenario at the target time is a small fluctuation scenario, calculate the virtual inertia of the wind power converter or the photovoltaic converter, and control the wind power converter or the photovoltaic converter based on the virtual inertia;

[0186] If the new energy fluctuation scenario at the target time is a medium fluctuation scenario, energy storage discharge is performed at a first rate based on the energy storage reserve capacity and load shedding is performed based on the load shedding reserve.

[0187] If the new energy fluctuation scenario at the target time is a high-fluctuation scenario, energy storage discharge is performed at a second rate based on the energy storage reserve capacity and load shedding is performed based on the load shedding reserve; wherein, the second rate is greater than the first rate.

[0188] In one optional embodiment, the step of adjusting intraday resources based on the risk assessment results to obtain an intraday resource adjustment plan includes:

[0189] Based on the risk assessment results, intraday resources are adjusted using an optimization model to obtain an intraday resource adjustment plan;

[0190] Based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time, the corresponding control strategy is determined, including:

[0191] Based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time, the corresponding control strategy is determined through a collaborative control model.

[0192] The device further includes a parameter tuning module for:

[0193] Obtain control effect evaluation indicators, and adjust the parameters of the new energy output prediction model, the optimization model, and the collaborative control model based on the control effect evaluation indicators; wherein the control effect evaluation indicators include stability evaluation indicators and economic evaluation indicators.

[0194] like Figure 3 As shown in the figure, this application provides an electronic device, including a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0195] Memory 113 is used to store computer programs;

[0196] In one embodiment of this application, when the processor 111 executes a program stored in the memory 113, it implements the method provided in any of the foregoing method embodiments, including:

[0197] The historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy power generation are determined, and a feature matrix is ​​constructed based on the historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics.

[0198] Based on the feature matrix, the predicted value of new energy output at each moment in the preset time period is determined;

[0199] If the deviation between the predicted value of renewable energy output at the target time and the actual value of renewable energy output at the target time does not meet the preset conditions, the predicted value of renewable energy output after the target time is corrected based on the actual value of renewable energy output at the target time to obtain the corrected predicted value of renewable energy output.

[0200] Based on the corrected predicted value of renewable energy output and the fluctuation characteristics of renewable energy output at the target time, a system transient risk assessment is conducted to obtain the risk assessment results.

[0201] Based on the risk assessment results, intraday resource adjustments are made to obtain an intraday resource adjustment plan, and corresponding control measures are determined based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time.

[0202] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method provided in any of the foregoing method embodiments.

[0203] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0204] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0205] The above embodiments are merely illustrative examples and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations. However, obvious variations or modifications derived therefrom are still within the scope of protection of this application.

Claims

1. A multi-timescale transient stability control method for new energy power output fluctuations, characterized in that, include: The historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy power generation are determined, and a feature matrix is ​​constructed based on the historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics. Based on the feature matrix, the predicted value of new energy output at each moment in the preset time period is determined; If the deviation between the predicted value of renewable energy output at the target time and the actual value of renewable energy output at the target time does not meet the preset conditions, the predicted value of renewable energy output after the target time is corrected based on the actual value of renewable energy output at the target time to obtain the corrected predicted value of renewable energy output. Based on the corrected predicted value of renewable energy output and the fluctuation characteristics of renewable energy output at the target time, a system transient risk assessment is conducted to obtain the risk assessment results. Based on the risk assessment results, intraday resource adjustments are made to obtain an intraday resource adjustment plan, and corresponding control measures are determined based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time. The system transient risk assessment based on the corrected renewable energy output forecast and the fluctuation characteristics of renewable energy output at the target time includes: The power angle stability margin and voltage stability margin are determined based on the corrected new energy output prediction values. The risk level is determined based on the power angle stability margin, the voltage stability margin, and the fluctuation characteristics of the new energy output at the target time. The control measures determined based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time include: If the new energy fluctuation scenario at the target time is a small fluctuation scenario, calculate the virtual inertia of the wind power converter or the photovoltaic converter, and control the wind power converter or the photovoltaic converter based on the virtual inertia; If the new energy fluctuation scenario at the target time is a medium fluctuation scenario, energy storage discharge is performed at a first rate based on the energy storage reserve capacity and load shedding is performed based on the load shedding reserve. If the new energy fluctuation scenario at the target time is a high-fluctuation scenario, energy storage discharge is performed at a second rate based on the energy storage reserve capacity and load shedding is performed based on the load shedding reserve; wherein, the second rate is greater than the first rate.

2. The method according to claim 1, characterized in that, The step of determining the predicted output value of new energy sources at each moment in the preset time period based on the feature matrix includes: The power output prediction module in the new energy power output prediction model determines the predicted value of new energy power output at each moment in the preset time period based on the feature matrix. The method further includes: The output prediction module is iteratively trained using training set data, and the parameters of the output prediction module are adjusted based on the loss function. The output prediction module is validated by collecting validation set data. If the deviation between the loss function value corresponding to the validation set data and the loss function value corresponding to the training set data exceeds a preset deviation, the feature matrix is ​​adjusted. The loss function is: ； in, The value of the loss function; The predicted output of new energy sources at time t; The actual output value of the new energy source at time t; The predicted output of new energy sources at time t+1; This is the fluctuation penalty coefficient.

3. The method according to claim 1, characterized in that, The correction of the predicted new energy output value after the target time based on the actual new energy output value at the target time includes: The predicted output value of new energy sources is corrected based on the following formula: ； in, The corrected predicted output value of new energy sources at time t. Let t be the predicted output value of new energy sources at time t; for The real output value of new energy sources at any given moment; The weighting coefficients for the predicted output of new energy sources at time t; for Weighting coefficients for the actual output value of new energy sources at any given time; For time intervals.

4. The method according to claim 1, characterized in that, Based on the risk assessment results, intraday resource adjustments are made to obtain an intraday resource adjustment plan, including: The state of the power system is defined by the power angle stability margin, the voltage stability margin, the maximum drop in new energy output, the energy storage reserve capacity, and the load shelving reserve. The execution actions of the power system are defined by the energy storage reserve adjustment capacity and the load shelving reserve adjustment amount. A reward function is established by the power angle stability margin, the voltage stability margin, and the control cost of the intraday resource adjustment scheme. The optimal action of the power system is determined based on the state of the power system at the target time and the reward function, serving as an intraday resource adjustment scheme; wherein the energy storage reserve adjustment capacity satisfies the constraint within a first preset range; and the load shelving reserve adjustment amount satisfies the constraint within a second preset range. The reward function is as follows: ; in, This refers to the stability margin of the power angle; This refers to the voltage stability margin; The control cost of the intraday resource adjustment plan; To maximize allowable cost control, This is the reward value.

5. The method according to claim 2, characterized in that, The intraday resource adjustment plan, based on the risk assessment results, includes: Based on the risk assessment results, intraday resources are adjusted using an optimization model to obtain an intraday resource adjustment plan; The determination of the corresponding control strategy based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time includes: Based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time, the corresponding control strategy is determined through a collaborative control model. The method further includes: Obtain control effect evaluation indicators, and adjust the parameters of the new energy output prediction model, the optimization model, and the collaborative control model based on the control effect evaluation indicators; wherein, the control effect evaluation indicators include stability evaluation indicators and economic evaluation indicators.

6. A multi-timescale transient stability control device for new energy power output fluctuations, characterized in that, include: The data preprocessing module is used to determine the historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics of new energy output, and to construct a feature matrix based on the historical output sequence, meteorological characteristics, temporal characteristics, and historical fluctuation characteristics. The power output prediction module is used to determine the predicted value of new energy power output at each moment in a preset time period based on the feature matrix. The correction module is used to correct the predicted value of new energy output after the target time based on the actual value of new energy output at the target time if the deviation between the predicted value of new energy output at the target time and the actual value of new energy output at the target time does not meet the preset conditions, so as to obtain the corrected predicted value of new energy output. The transient risk assessment module is used to conduct a system transient risk assessment based on the corrected renewable energy output forecast and the fluctuation characteristics of renewable energy output at the target time, and obtain the risk assessment result. The adjustment control module is used to adjust intraday resources based on the risk assessment results, obtain an intraday resource adjustment plan, and determine corresponding control measures based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time. The system transient risk assessment based on the corrected renewable energy output forecast and the fluctuation characteristics of renewable energy output at the target time includes: The power angle stability margin and voltage stability margin are determined based on the corrected new energy output prediction values. The risk level is determined based on the power angle stability margin, the voltage stability margin, and the fluctuation characteristics of the new energy output at the target time. The control measures determined based on the intraday resource adjustment plan and the new energy fluctuation scenario at the target time include: If the new energy fluctuation scenario at the target time is a small fluctuation scenario, calculate the virtual inertia of the wind power converter or the photovoltaic converter, and control the wind power converter or the photovoltaic converter based on the virtual inertia; If the new energy fluctuation scenario at the target time is a medium fluctuation scenario, energy storage discharge is performed at a first rate based on the energy storage reserve capacity and load shedding is performed based on the load shedding reserve. If the new energy fluctuation scenario at the target time is a high-fluctuation scenario, energy storage discharge is performed at a second rate based on the energy storage reserve capacity and load shedding is performed based on the load shedding reserve; wherein, the second rate is greater than the first rate.

7. An electronic device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed in a computer, causes the computer to perform the method described in any one of claims 1-5.

Images