New energy access risk assessment method and device, electronic equipment and storage medium

Abstract

The invention discloses a new energy access risk assessment method and device, electronic equipment and a storage medium. The method comprises the steps of S1, collecting multi-source heterogeneous data in real time; s2, through multi-source heterogeneous data fusion, calculating a new energy multi-station short-circuit ratio in real time; s3, extracting and constructing engineering practical risk feature vectors, wherein the engineering practical risk feature vectors comprise transient overvoltage features and corresponding network structure risk features; s4, constructing a nonlinear dynamic mapping model between the new energy multi-station short-circuit ratio and the transient overvoltage key features by using a deep learning model; s5, according to the new energy multi-station short-circuit ratio calculated according to the data collected in real time, risk assessment and grading are carried out through a nonlinear dynamic mapping model; and S6, when the risk level reaches an early warning threshold value or the transient overvoltage predicted value exceeds a limit value, the system automatically triggers early warning and generates a decision suggestion. According to the method, the efficiency, the accuracy and the engineering applicability of risk assessment are remarkably improved, and the automation level and the intelligence level are improved.

Description

Technical Field

[0001] This application relates to the field of safety and stability analysis and risk assessment technology for new energy power systems, and in particular, to methods, devices, electronic equipment and storage media for new energy access risk assessment. Background Technology

[0002] As the global energy structure transitions towards cleaner and lower-carbon energy, new energy power generation, such as wind and solar power, is being integrated into the power system at an unprecedented rate. This large-scale, high-proportion centralized grid connection of new energy sources has resulted in the power system exhibiting the "dual high" characteristics of a high proportion of new energy and a high proportion of power electronic equipment. The inherent volatility, intermittency, and randomness of new energy power generation, as well as the weak inertia, low damping, and low short-circuit capacity characteristics of their power electronic interfaces, pose severe challenges to the safe and stable operation of the power system. Among these challenges, the short-circuit ratio ( SCR The significant reduction in short-circuit ratio is one of the core issues caused by the high proportion of renewable energy integration. A low short-circuit ratio means a weakened grid strength, making the grid voltage more sensitive to reactive power disturbances, reducing voltage regulation sensitivity, lowering the system voltage stability margin, and making it highly susceptible to transient voltage instability and other problems. Furthermore, when grid faults occur, especially severe disturbances such as commutation failure or DC blocking in the DC transmission system, serious transient overvoltage problems may occur at renewable energy power plants. The dynamic control characteristics of the power electronic converters of renewable energy units during fault ride-through (such as current limiting and reactive power compensation strategies) and the reactive power compensation equipment within the plant (such as...) are crucial factors. SVC The nonlinear response of SVG / STATCOM may exacerbate the amplitude and duration of transient overvoltages, leading to large-scale grid disconnection of new energy units and seriously threatening the safe operation of the power grid.

[0003] Currently, to alleviate the problems of insufficient short-circuit capacity and transient overvoltage in "high-voltage and high-efficiency" power systems, the output level of renewable energy power plants is often limited to maintain system stability. This severely restricts the grid-connected power generation capacity and utilization efficiency of renewable energy. Therefore, there is an urgent need for a method and system that can assess the short-circuit ratio and transient overvoltage risk at renewable energy access points in real time, automatically, and quantitatively. This would improve assessment efficiency and accuracy, thereby guiding grid planning, operation, and the optimal allocation of supporting power sources (such as synchronous condensers and grid-connected energy storage), ensuring the safe and stable operation of the new power system and the efficient absorption of renewable energy.

[0004] In the existing field of renewable energy grid connection risk assessment, most studies focus on the multi-scenario output of renewable energy, clustering wind, solar, and load data based on their characteristics and selecting typical representative days to address the uncertainty and correlation issues of renewable energy grid connection. These methods estimate system indicators by enumerating system states (analytical methods) or by random sampling (Monte Carlo simulation).

[0005] Despite some progress in assessing the risks of renewable energy integration, existing technologies still have significant shortcomings: 1) Inefficient assessment and difficulty in real-time response: Most traditional risk assessment methods, especially Monte Carlo simulation and detailed manual simulation, involve huge computational loads and long calculation times, making it difficult to meet the real-time response requirements of rapidly changing power systems in renewable energy integration scenarios. This limits the timeliness of risk warning and decision-making; 2) Inability to effectively quantify the short-circuit ratio ( SCR ) and transient overvoltage ( TOV The nonlinear mapping relationship between renewable energy access and grid strength ( SCR The behavior of transient voltages and other energy sources has complex nonlinear effects. Traditional evaluation models often rely on simplified linear relationships or empirical rules, which are difficult to accurately reflect the situation under the background of multiple renewable energy power plants being connected. SCR and TOV The nonlinear relationship of dynamic coupling between them leads to insufficient accuracy in risk assessment; 3) Insufficient automation and intelligence: Existing assessment methods largely rely on manually setting models and parameters, lacking a unified framework that integrates intelligent algorithms such as big data analysis and machine learning. This makes it difficult to automatically extract risk characteristics and perform unified risk quantification across multiple time scales and scenarios. Summary of the Invention

[0006] This application provides a method for assessing the risk of renewable energy access, addressing the shortcomings of existing renewable energy access risk assessment technologies, such as low assessment efficiency, difficulty in real-time response, and inability to effectively quantify the short-circuit ratio. SCR ) and transient overvoltage ( TOV The technical problems include nonlinear mapping relationships, insufficient automation and intelligence levels.

[0007] This application is achieved through the following solution: The risk assessment method for renewable energy grid connection includes the following steps: S1. Real-time collection of multi-source heterogeneous data from SCADA / EMS, WAMS / PMU, new energy power station monitoring system, meteorological information system and equipment parameter database through data access module; S2. By fusing multi-source heterogeneous data, the short-circuit ratio of new energy power plants, a core indicator representing grid strength, is calculated in real time. MRSCR ; S3. Based on relevant standards, extract and construct practical risk feature vectors for engineering applications from different dimensions, including transient overvoltages. TOV Features and corresponding network structure risk characteristics; S4. Constructing the short-circuit ratio of multiple new energy power stations using deep learning models. MRSCR With transient overvoltage TOVNonlinear dynamic mapping model between key characteristics (such as peak value, duration, and excess energy); S5. Short-circuit ratio of new energy multi-stations calculated based on real-time collected data. MRSCR With transient overvoltage TOV A nonlinear dynamic mapping model between key features is used for real-time dynamic risk assessment and risk level classification. S6. When the risk level reaches the warning threshold or transient overvoltage... TOV When the predicted value exceeds the limit, the system automatically triggers an early warning and generates decision recommendations.

[0008] Further, step S1 specifically includes the following steps: S11. Real-time collection of multi-source heterogeneous data from SCADA / EMS, WAMS / PMU, renewable energy power station monitoring system, meteorological information system, and equipment parameter database via data access module. Key data collected includes: active power output of each renewable energy power station. Unproductive efforts and operating status, grid bus voltage System topology, power flow distribution, and meteorological information including wind speed and light intensity; S12. The collected raw multi-source heterogeneous data is normalized by the preprocessing module, including: time alignment (unified timestamp), anomaly detection and removal (such as using the 3σ criterion or Hampel filter), missing data repair (such as linear interpolation or K-nearest neighbor algorithm), and per-unit processing to eliminate the influence of dimensions and provide consistent and reliable data input for subsequent calculations and analysis.

[0009] Furthermore, step S2 specifically includes the following steps: S21. Calculate the equivalent impedance of the target convergence point based on the real-time power grid topology and operating status. The equivalent impedance is obtained through the network node impedance matrix and a multi-point network equivalent calculation engine (e.g., PSD-SCCP); S22. Calculate the equivalent short-circuit capacity of the target convergence point. The calculation formula is as follows: ; in, The reference voltage, The voltage phasor is conjugate; S23. Calculate the short-circuit ratio of multiple renewable energy power plants, a core indicator characterizing grid strength. MRSCR : ; in, and busbars and busbar The power injected by new energy sources busbar Multi-point Thevenin equivalent self-impedance, busbar and busbar The Thevenin equivalent mutual impedance at multiple points between them.

[0010] Furthermore, step S3 specifically includes the following steps: S31, Transient overvoltage TOV Feature extraction, based on real-time power grid topology and operating status, employs high-precision electromechanical transient simulation platforms (such as PSD-BPA, PSASP, PSS / E) to simulate various anticipated fault types (such as AC side short circuit, DC commutation failure / blocking), generating a large amount of system transient response data corresponding to different short-circuit ratio levels, and then within the disturbance window. Within this process, the peak value, duration, and over-limit energy of the transient overvoltage are extracted, including: Transient voltage peak (pu) means: ; In the formula, To evaluate the peak voltage within the window, For nodes Voltage timing curve, The transient voltage threshold is set according to national or industry standards, such as 1.3 pu. The detection time window range; Exceeding the limit duration (s) is: ; in, This is an indicator function; it takes the value 1 if the condition is met, and 0 otherwise. Excess Energy ( The calculation formula is: ; In the formula, To measure the combined damage extent of overvoltage intensity and duration. ; S32. Network structure risk feature extraction, including calculation of electrical distance, the calculation formula is: ; in, V i Indicates busbar i Voltage amplitude, Q j Indicates busbarj Injected reactive power; this electrical distance reflects the degree of electrical coupling between nodes.

[0011] Furthermore, step S4 specifically includes the following steps: S41. A nonlinear dynamic mapping model is constructed using a Long Short-Term Memory (LSTM) network suitable for time-series data processing to connect the short-circuit ratio (MRSCR) of multiple renewable energy power plants with key characteristics of transient overvoltage (TOV) (peak value, duration, and over-limit energy), where: The input sequence of the nonlinear dynamic mapping model The state characteristics within a window prior to the failure include: ; in, For new energy power plants, the short-circuit ratio is increased. For the first The active power output of each station; For the first The reactive power output of each power station; Electrical distance; Meteorological data (wind speed, light intensity, etc.); The network state update of the nonlinear dynamic mapping model is as follows: LSTM updates the cell state through its internal gating mechanism (input gate, forget gate, output gate). and hidden state This allows the network to capture the long-term dependencies between its operating state and subsequent transient responses. The state update formula for the LSTM network is as follows: ; ; ; ; ; ; in, , , These are the state updates for the forget gate, input gate, and output gate, respectively. Candidate memory units, For output status, , , , These are the weight matrices input to each gate, respectively. , , , These are the cyclic weight matrices from the previous hidden state to each gate. , , , These are the corresponding bias vectors; The output of the nonlinear dynamic mapping model is the predicted value of the TOV feature: ; in, For the predicted peak value of transient overvoltage, For duration, For the predicted excess energy; The training process of the nonlinear dynamic mapping model is performed by minimizing the following loss function: ; in, The weighting coefficients for the loss term are used to adjust the importance of different indicators. The nonlinear dynamic mapping model has online update capability, continuously absorbing new data through incremental learning to adapt to changes in the power grid structure and the integration of new equipment. The update formula is: ; in, For model parameters, For learning rate, This is the gradient of the loss function with respect to the model parameters.

[0012] Furthermore, step S5 specifically includes the following steps: S51. Based on the real-time collected data, the short-circuit ratio of multiple new energy power plants is calculated, and a nonlinear dynamic mapping model between the short-circuit ratio MRSCR of multiple new energy power plants and the key characteristics of transient overvoltage TOV is used to conduct real-time dynamic risk assessment and calculate the comprehensive risk index: ; in, w 1. w 2. w 3 indicates the weight of each sub-risk; MRSCR The formula for calculating sub-risk is: ; TOV The formula for calculating sub-risk is: ; in, β 1. β 2. β 3. β 4 represents the weighted portion of each risk indicator; The formula for calculating the value loss of wind and solar power curtailment is as follows: ; The formula for calculating the value loss due to wind and solar power curtailment is as follows: ; in: The amount of wind and solar power curtailed (MWh); for Available power output from new energy sources during the specified time period (wind and solar power can theoretically generate power); for Actual power output during the time period (constrained by TOV / SCR / channel); The duration is in hours (h). for Average on-grid tariff or market clearing price of renewable energy during the specified period; S52. Risk Level Classification: The Comprehensive Risk Index (RI) classifies the risk level of the power grid into different levels. The specific classification method is as follows: ; in, γ 1. γ 2. γ 3. γ 4 is a preset threshold set based on the power grid's safety standards, historical data, or expert experience. Dynamic risk classification is performed based on the preset threshold, dividing the risk level into 1 to 5 levels, corresponding to "safe", "attention", "early warning", "high alert" and "critical" states, respectively, to provide operators with a clear situational awareness.

[0013] Furthermore, step S6 specifically includes the following steps: S61. When the risk level reaches the warning threshold (e.g., Level ≥ 4) or TOV When the predicted value exceeds the limit, the system automatically triggers an early warning and generates decision recommendations. These recommendations include real-time control suggestions and supporting planning and configuration suggestions, among which: The real-time control recommendations, based on a rule base or a fast optimization algorithm, output executable control measures: (1) Recommendations for reactive power regulation: ; In the formula, Indicates the first Current reactive power setting value of each new energy power station / reactive power compensation device This indicates the suggested reactive power adjustment. , They represent the first The minimum / maximum allowable reactive power for an object. As a cutoff function, this formula provides an optimized strategy for reactive power regulation to ensure grid voltage stability; (2) Recommendation on the effectiveness limit: Based on the ranking of each station's sensitivity to the collection point voltage, the power output of the station with the weakest voltage support is restricted first. The aforementioned supportive planning and configuration recommendations aim to fundamentally enhance grid strength by providing capacity configuration suggestions for supportive power sources, including the required supplementary equivalent short-circuit support capacity. The calculation formula is: ; in, The minimum threshold required for safe operation. and busbars and busbar The power injected by new energy sources busbar Multi-point Thevenin equivalent self-impedance, busbar and busbar Thervenin equivalent mutual impedance at multiple points between them Equivalent short-circuit capacity at the target convergence point; This application also provides a new energy access risk assessment device, including: The real-time data acquisition and preprocessing module is used to acquire multi-source heterogeneous data from SCADA / EMS, WAMS / PMU, new energy power station monitoring system, meteorological information system and equipment parameter database in real time through the data access module; The online short-circuit ratio calculation module is used to calculate the short-circuit ratio of multiple new energy power plants in real time through multi-source heterogeneous data fusion, which is a core indicator representing the strength of the power grid. MRSCR ; The multi-dimensional risk feature extraction and structured characterization module extracts and constructs engineering-applicable risk feature vectors from different dimensions based on relevant standards, including transient overvoltage. TOV and the corresponding electrical distance; The mapping model building module is used to construct the short-circuit ratio of multiple new energy power plants using deep learning models. MRSCR A nonlinear dynamic mapping model between transient overvoltage (TOV) and key characteristics (peak value, duration, and overvoltage energy); The real-time risk assessment and dynamic grading module is used to calculate the short-circuit ratio of multiple new energy power plants based on real-time collected data. MRSCR With transient overvoltage TOV A nonlinear dynamic mapping model between key features is used for real-time dynamic risk assessment and risk level classification. An automated early warning and precise decision-making suggestion generation module is used to generate early warnings when the risk level reaches the early warning threshold or a transient overvoltage occurs. TOVWhen the predicted value exceeds the limit, the system automatically triggers an early warning and generates decision recommendations.

[0014] This application also provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the new energy access risk assessment method when executing the computer program.

[0015] This application also provides a computer-readable storage medium storing a computer program thereon, characterized in that the computer program, when executed by a processor, implements the new energy access risk assessment method.

[0016] Compared with the prior art, this application has the following advantages: The technical solution of this invention addresses the risk assessment problem of new energy grid integration. By integrating the physical mechanism of the power system with data-driven modeling methods, a closed-loop risk assessment mechanism of "grid strength index - transient overvoltage dynamic response - operational risk consequences" is constructed under a unified framework. Combined with online updates and automated decision support functions, the efficiency, accuracy, and engineering applicability of risk assessment are significantly improved, and the level of automation and intelligence is enhanced. Under the conditions of multiple stations being centrally connected to the grid in new energy bases and rapidly changing operating conditions, the risk assessment achieves real-time, automated, and quantitative risk identification and early warning effects.

[0017] In addition to the purposes, features, and advantages described above, this application has other purposes, features, and advantages. A further detailed description of this application will be provided below with reference to the figures. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating the new energy access risk assessment method according to a preferred embodiment of this application; Figure 2 This is a schematic diagram of the modules of the new energy access risk assessment device according to a preferred embodiment of this application; Figure 3 This is a schematic block diagram of an electronic device according to a preferred embodiment of this application; Figure 4 This is an internal structural diagram of a computer device according to a preferred embodiment of this application. Detailed Implementation

[0019] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0020] Definitions of abbreviations and key terms: 1) Short-circuit ratio of multiple new energy power plants (MRSCR): This is a comprehensive power grid strength index that characterizes the coupling of multiple new energy power plants at the same collection point or the same transmission channel. It is used to reflect the equivalent short-circuit capacity support capability under the grid connection of multiple power plants. 2) Transient overvoltage (TOV): The phenomenon that the voltage exceeds the normal range for a short period of time after a disturbance occurs in the power grid (short circuit fault, commutation failure, DC blocking, generator shedding and load shedding, etc.), which may trigger protection, damage equipment, and cause grid disconnection; 3) Synchronous Condenser: A type of synchronous motor that operates without mechanical load, used to provide short-circuit current support, dynamic reactive power compensation, and inertia, thereby improving grid stability; 4) Static Var Compensator (SVC): A fast-response power electronic reactive power compensation device; 5) Static Synchronous Compensator (STATCOM) / Static Var Generator (SVG): A power electronic reactive power compensation device based on a voltage source converter, which can quickly adjust reactive power and voltage; 6) Expected Energy Not Supplied (EENS): This measures the risk of power shortage due to insufficient capacity or constraints within a given time interval. 7) Electrical Distance: An indicator reflecting the degree of electrical coupling between nodes in a power system, used to assess the impact of faults on the voltage of different nodes; 8) SCADA (Supervisory Control And Data Acquisition): A monitoring and data acquisition system used to monitor and remotely control the operating status of primary and secondary equipment in a power system in real time. It mainly performs functions such as acquisition of switch and analog quantities, status monitoring, telemetry, remote signaling, remote control, and remote adjustment, providing basic real-time data support for dispatching operations and automated control. 9) EMS (Energy Management System): The energy management system is an advanced dispatching and analysis system built on SCADA data. It is mainly used for power system operation analysis and decision support, including functions such as power flow calculation, state estimation, short-term load forecasting, safety verification, accident analysis, and optimized dispatching. It is the core business system of the power grid dispatching center. 10) WAMS (Wide Area Measurement System): The wide area measurement system is a power system wide area monitoring system built on synchronous phasor measurement technology. By deploying PMUs at key nodes of the power grid, it can achieve high time synchronization and high sampling rate measurement of quantities such as voltage, current, phase angle, and frequency. It is used for power grid dynamic process monitoring, stability analysis and rapid fault identification. 11) PMU (Phasor Measurement Unit): A synchronous phasor measurement unit is a device that can perform high-precision synchronous measurements of voltage and current phasors, their phase angles, frequencies, and rates of change of frequency using a unified time reference (such as GPS / BeiDou). It is the basic measurement unit of WAMS and is widely used in power system dynamic monitoring, oscillation analysis, and transient stability assessment.

[0021] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a new energy access risk assessment device capable of performing the above functions. The following description uses a new energy access risk assessment device as the executing entity to illustrate this embodiment and the subsequent embodiments.

[0022] like Figure 1 As shown, a preferred embodiment of this application provides a method for assessing the risk of new energy access, including the following steps: S1. Real-time collection of multi-source heterogeneous data from SCADA / EMS, WAMS / PMU, new energy power station monitoring system, meteorological information system and equipment parameter database through data access module; S2. By fusing multi-source heterogeneous data, the short-circuit ratio of new energy power plants, a core indicator representing grid strength, is calculated in real time. MRSCR ; S3. Based on relevant standards, extract and construct practical risk feature vectors for engineering applications from different dimensions, including transient overvoltages. TOV Features and corresponding network structure risk characteristics; S4. Constructing the short-circuit ratio of multiple new energy power stations using deep learning models. MRSCR With transient overvoltage TOV A nonlinear dynamic mapping model between key characteristics (peak value, duration, and excess energy); S5. Short-circuit ratio of new energy multi-stations calculated based on real-time collected data. MRSCR With transient overvoltage TOV A nonlinear dynamic mapping model between key features is used for real-time dynamic risk assessment and risk level classification. S6. When the risk level reaches the warning threshold or transient overvoltage... TOVWhen the predicted value exceeds the limit, the system automatically triggers an early warning and generates decision recommendations.

[0023] The technical solution in this embodiment addresses the risk assessment problem of new energy grid access. By integrating the physical mechanisms of power systems with data-driven modeling methods, a closed-loop risk assessment mechanism of "grid strength index - transient overvoltage dynamic response - operational risk consequences" is constructed under a unified framework. Combined with online updates and automated decision support functions, the efficiency, accuracy, and engineering applicability of risk assessment are significantly improved, and the level of automation and intelligence is enhanced. Under the conditions of multiple stations being centrally connected to the grid in new energy bases and rapidly changing operating conditions, the risk assessment achieves real-time, automated, and quantitative risk identification and early warning effects.

[0024] Preferably, step S1 specifically includes the following steps: S11. Real-time collection of multi-source heterogeneous data from SCADA / EMS, WAMS / PMU, renewable energy power station monitoring system, meteorological information system, and equipment parameter database via data access module. Key data collected includes: active power output of each renewable energy power station. Unproductive efforts and operating status, grid bus voltage System topology, power flow distribution, and meteorological information including wind speed and light intensity; S12. The collected raw multi-source heterogeneous data is normalized by the preprocessing module, including: time alignment (unified timestamp), anomaly detection and removal (such as using the 3σ criterion or Hampel filter), missing data repair (such as linear interpolation or K-nearest neighbor algorithm), and per-unit processing to eliminate the influence of dimensions and provide consistent and reliable data input for subsequent calculations and analysis.

[0025] Preferably, the core of step S2 is to quantify the power grid's support capacity into a key indicator, specifically including the following steps: S21. Calculate the equivalent impedance of the target convergence point based on the real-time power grid topology and operating status. The equivalent impedance is obtained through the network node impedance matrix and a multi-point network equivalent calculation engine (e.g., PSD-SCCP); S22. Calculate the equivalent short-circuit capacity of the target convergence point. The calculation formula is as follows: ; in, The reference voltage, As voltage phasor conjugates, the equivalent short-circuit capacity physically characterizes the "rigidity" or support strength of the external power grid to disturbances. S23. Calculate the short-circuit ratio of multiple renewable energy power plants, a core indicator characterizing grid strength. MRSCR: ; in, and busbars and busbar The power injected by new energy sources busbar Multi-point Thevenin equivalent self-impedance, busbar and busbar The multi-point Thevenin equivalent mutual impedance between the two points is an indicator that has higher accuracy and representativeness in evaluating the system strength and voltage support capability in the scenario of centralized transmission of new energy from multiple power plants.

[0026] Preferably, to comprehensively assess the risk, step S3 extracts and constructs a risk feature vector from different dimensions, specifically including the following steps: S31, Transient overvoltage TOV Feature extraction, based on real-time power grid topology and operating status, employs high-precision electromechanical transient simulation platforms (such as PSD-BPA, PSASP, PSS / E) to simulate various anticipated fault types (such as AC side short circuit, DC commutation failure / blocking), generating a large amount of system transient response data corresponding to different short-circuit ratio levels, and then within the disturbance window. Within this process, the peak value, duration, and over-limit energy of the transient overvoltage are extracted, including: Transient voltage peak (pu) means: ; In the formula, To evaluate the peak voltage within the window, For nodes Voltage timing curve, The transient voltage threshold is set according to national or industry standards, such as 1.3 pu. The detection time window range; Exceeding the limit duration (s) is: ; in, This is an indicator function; it takes the value 1 if the condition is met, and 0 otherwise. Excess Energy ( The calculation formula is: ; In the formula, To measure the combined damage extent of overvoltage intensity and duration. The transient voltage peak value, over-limit duration, and over-limit energy comprehensively describe "how much higher + how long it lasts", distinguishing between peak and plateau overvoltages, which is more conducive to model learning and engineering evaluation; S32. Network structure risk feature extraction, including calculation of electrical distance, the calculation formula is: ; in, V i Indicates busbar i Voltage amplitude, Q j Indicates busbar j Injected reactive power, this electrical distance reflects the degree of electrical coupling between nodes, the same MRSCR The value may lead to different TOV responses under different network structures. This embodiment introduces this feature to enhance the model's generalization ability to different power grid structures.

[0027] Preferably, step S4 specifically includes the following steps: S41. A nonlinear dynamic mapping model is constructed using a Long Short-Term Memory (LSTM) network suitable for time-series data processing to establish a relationship between the short-circuit ratio (MRSCR) of multiple renewable energy power plants and the key characteristics (peak value, duration, and over-limit energy) of transient overvoltage (TOV). This embodiment is the core of the model, aiming to establish a rapid prediction channel from grid strength to transient consequences. The LSTM network, suitable for time-series data processing, is used as the mapping model, where: The input sequence of the nonlinear dynamic mapping model The state characteristics within a window prior to the failure include: ; in, For new energy power plants, the short-circuit ratio is increased. For the first The active power output of each station; For the first The reactive power output of each power station; Electrical distance; Meteorological data (wind speed, light intensity, etc.); The network state update of the nonlinear dynamic mapping model is as follows: LSTM updates the cell state through its internal gating mechanism (input gate, forget gate, output gate). and hidden state This allows the network to capture the long-term dependencies between its operating state and subsequent transient responses. The state update formula for the LSTM network is as follows: ; ; ; ; ; ; in, , , These are the state updates for the forget gate, input gate, and output gate, respectively. Candidate memory units, For output status, , , , These are the weight matrices input to each gate, respectively. , , , These are the cyclic weight matrices from the previous hidden state to each gate. , , , These are the corresponding bias vectors; The output of the nonlinear dynamic mapping model is the predicted value of the TOV feature: ; in, For the predicted peak value of transient overvoltage, For duration, For the predicted excess energy; The training process of the nonlinear dynamic mapping model is performed by minimizing the following loss function: ; in, The weighting coefficients for the loss term are used to adjust the importance of different indicators; The nonlinear dynamic mapping model has online update capability, continuously absorbing new data through incremental learning to adapt to changes in the power grid structure and the integration of new equipment. The update formula is: ; in, For model parameters, For learning rate, This is the gradient of the loss function with respect to the model parameters.

[0028] Preferably, step S5 specifically includes the following steps: S51. The short-circuit ratio of multiple new energy power stations calculated based on real-time collected data such as the output of new energy units and grid operating parameters. MRSCR With transient overvoltage TOV A nonlinear dynamic mapping model between key features is used for real-time dynamic risk assessment, and a comprehensive risk index is calculated. ; in, w 1. w 2. w 3 represents the weight of each sub-risk. To quantify and visually represent the risk, this application proposes a comprehensive risk index. RI Synthesis method, RI It is composed of a weighted average of three sub-risk indices: MRSCR The formula for calculating sub-risk is: ; The calculation formula uses an exponential form to reflect the nonlinear growth characteristics of the risk in the critical zone of the power grid. As the MRSCR decreases, the risk of the power grid increases. TOV The formula for calculating sub-risk is: ; in, β 1. β 2. β 3. β 4 represents the weighted portion of each risk indicator. This calculation formula comprehensively considers the impact of the peak value, duration, and over-limit energy of transient overvoltage on system safety. The weighted portion of each risk indicator ( β 2. β 3. β 4) Adjustments will be made based on actual project experience or historical data; The formula for calculating the value loss of wind and solar power curtailment is as follows: ; The formula for calculating the value loss due to wind and solar power curtailment is as follows: ; in: The amount of wind and solar power curtailed (MWh); for Available power output from new energy sources during the specified time period (wind and solar power can theoretically generate power); for Actual power output during the time period (constrained by TOV / SCR / channel); The duration is in hours (h). for The average on-grid price or market clearing price of renewable energy during a given period; this calculation formula measures the ratio of the expected value loss of renewable energy curtailment to the maximum value loss, reflecting the severity of curtailment. S52. Risk Level Classification: The Comprehensive Risk Index (RI) classifies the risk level of the power grid into different levels. The specific classification method is as follows: ; in, γ 1. γ 2. γ 3. γ 4 is a preset threshold set based on the power grid's safety standards, historical data, or expert experience. Dynamic risk classification is performed based on the preset threshold, dividing the risk level into 1 to 5 levels, corresponding to "safe", "attention", "early warning", "high alert" and "critical" states, respectively, to provide operators with a clear situational awareness.

[0029] Preferably, step S6 specifically includes the following steps: S61. When the risk level reaches the warning threshold (e.g., Level ≥ 4) or TOV When the predicted value exceeds the limit, the system automatically triggers an early warning and generates decision recommendations. These recommendations include real-time control suggestions and supporting planning and configuration suggestions, among which: The real-time control recommendations, based on a rule base or a fast optimization algorithm, output executable control measures: (1) Recommendations for reactive power regulation: ; In the formula, Indicates the first Current reactive power setting value of each new energy power station / reactive power compensation device This indicates the suggested reactive power adjustment. , They represent the first The minimum / maximum allowable reactive power for an object. As a cutoff function, this formula provides an optimized strategy for reactive power regulation to ensure grid voltage stability; (2) Recommendation on the effectiveness limit: Based on the ranking of each station's sensitivity to the collection point voltage, the power output of the station with the weakest voltage support is restricted first. The aforementioned supportive planning and configuration recommendations aim to fundamentally enhance grid strength by providing capacity configuration suggestions for supportive power sources, including the required supplementary equivalent short-circuit support capacity. The calculation formula is: ; in, The minimum threshold required for safe operation. and busbars and busbar The power injected by new energy sources busbar Multi-point Thevenin equivalent self-impedance, busbar and busbar Thervenin equivalent mutual impedance at multiple points between them The equivalent short-circuit capacity of the target convergence point; this result can directly guide the planning, site selection, and capacity determination of equipment such as synchronous condensers and grid-type energy storage.

[0030] The following example uses a renewable energy base that exports power (with local load approximately zero). The base includes 5 wind turbines (300 MW each) and 4 photovoltaic power plants (250 MW each), with a total installed capacity of... MW; transmitted via one collection station. High-output periods are selected. Available output MW. The coupled equivalent power is calculated from the real-time impedance matrix: ; During this period, due to external power grid maintenance and increased equivalent self-impedance, the equivalent short-circuit capacity was calculated. MVA, then: ; A "N-1 AC three-phase short circuit (0.12 s cut-off)" was applied to the 500 kV busbar of the substation, and simulation results were obtained. pu、 s、 pu s ( pu). This application's LSTM input predict pu、 s、 The risk level is determined by calculating the risk level using the aforementioned formula. Level =4 triggers an early warning. System recommendations: ① Add dynamic reactive power support (+60) Mvar to each of the two SVG sets and limit the amplitude (Equation (23)); ② Limit the power generation of each of the two power stations to 150 MW according to voltage sensitivity. Re-simulate after execution: pu、 Level 1 decreased to 2; external transmission power was reduced from... The MW capacity was increased to 2150 MW, and the amount of curtailed wind and solar power decreased by 300 MWh. Yuan / kWh, the value loss of abandoned electricity is reduced by approximately Yuan.

[0031] In summary, the core of the risk assessment method presented in this application lies in constructing an intelligent closed-loop process from data collection to decision-making recommendations. This method first calculates the short-circuit ratio (MRSCR) of multiple renewable energy power plants—a core indicator representing grid strength—in real time through multi-source data fusion. Then, based on relevant standards, it extracts practical risk characteristics for engineering applications. On this basis, it uses deep learning models (such as LSTM) to establish a nonlinear dynamic mapping relationship between MRSCR and key characteristics of transient overvoltage (TOV) (peak value, duration, and over-limit energy). Finally, it integrates multi-dimensional risk indicators to construct a comprehensive risk index (RI), achieving real-time quantitative classification of risks and automatically generating targeted early warning and control recommendations. This scheme deeply integrates the physical mechanisms of power systems with data-driven methods, realizing real-time, automated, and precise assessment processes to address the problem of limited renewable energy transmission, improve renewable energy utilization and grid safety and stability, and contribute to the construction of new power systems.

[0032] like Figure 2 As shown, another preferred embodiment of this application also provides a new energy access risk assessment device, including: The real-time data acquisition and preprocessing module is used to acquire multi-source heterogeneous data from SCADA / EMS, WAMS / PMU, new energy power station monitoring system, meteorological information system and equipment parameter database in real time through the data access module; The online short-circuit ratio calculation module is used to calculate the short-circuit ratio of multiple new energy power plants in real time through multi-source heterogeneous data fusion, which is a core indicator representing the strength of the power grid. MRSCR ; The multi-dimensional risk feature extraction and structured characterization module extracts and constructs engineering-applicable risk feature vectors from different dimensions based on relevant standards, including transient overvoltage. TOV and the corresponding electrical distance; The mapping model building module is used to construct the short-circuit ratio of multiple new energy power plants using deep learning models. MRSCR A nonlinear dynamic mapping model between transient overvoltage (TOV) and key characteristics such as peak value, duration, and overvoltage energy; The real-time risk assessment and dynamic grading module is used to calculate the short-circuit ratio of multiple new energy power plants based on real-time collected data. MRSCR With transient overvoltage TOV A nonlinear dynamic mapping model between key features is used for real-time dynamic risk assessment and risk level classification. An automated early warning and precise decision-making suggestion generation module is used to generate early warnings when the risk level reaches the early warning threshold or a transient overvoltage occurs. TOV When the predicted value exceeds the limit, the system automatically triggers an early warning and generates decision recommendations.

[0033] The new energy access risk assessment device provided in this embodiment adopts the new energy access risk assessment method in the above embodiment. It solves the technical problem in the prior art that the bandwidth allocation and loss compensation are lagging due to the discrete control mechanism, which makes it difficult to meet the power system's requirements for real-time and reliability of communication, and cannot synchronously respond to changes in service demand and line loss fluctuations, resulting in insufficient communication link stability and low resource utilization. Compared with the prior art, the beneficial effects of the new energy access risk assessment device provided in this embodiment are the same as those of the new energy access risk assessment method provided in the above embodiment. Moreover, other technical features in the new energy access risk assessment device are the same as those disclosed in the method of the above embodiment, and will not be repeated here.

[0034] like Figure 3 As shown, a preferred embodiment of this example also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the new energy access risk assessment method in the above embodiment.

[0035] This embodiment provides an electronic device that employs the new energy access risk assessment method described in the above embodiments. This addresses the technical problems in the prior art where bandwidth allocation and loss compensation, due to the lag of the discrete control mechanism, are unable to meet the power system's requirements for real-time communication and reliability, and cannot synchronously respond to changes in service demand and line loss fluctuations, resulting in insufficient communication link stability and low resource utilization. Compared with the prior art, the beneficial effects of the electronic device provided in this embodiment are the same as those of the new energy access risk assessment method provided in the above embodiments. Furthermore, other technical features of the electronic device are the same as those disclosed in the methods of the above embodiments, and will not be elaborated upon here.

[0036] like Figure 4 As shown in the preferred embodiment, this embodiment also provides a computer device, which may be a terminal or a liveness detection server, and its internal structure diagram may be as follows. Figure 4 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with other external computer devices via a network connection. When the computer program is executed by the processor, it implements the steps of the aforementioned new energy access risk assessment method.

[0037] Those skilled in the art will understand that Figure 4The structure shown is merely a block diagram of a portion of the structure related to the solution of this embodiment, and does not constitute a limitation on the computer device to which the solution of this embodiment is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0038] The computer equipment provided in this application adopts the new energy access risk assessment method in the above embodiments, which solves the technical problems in the prior art where bandwidth allocation and loss compensation are lagging due to the discrete control mechanism, making it difficult to meet the power system's requirements for real-time and reliable communication, and unable to synchronously respond to changes in business demand and line loss fluctuations, resulting in insufficient communication link stability and low resource utilization. Compared with the prior art, the beneficial effects of the computer equipment provided in this embodiment are the same as those of the new energy access risk assessment method provided in the above embodiments, and other technical features in the electronic equipment are the same as those disclosed in the method of the above embodiments, and will not be repeated here.

[0039] A preferred embodiment of this example also provides a storage medium, which includes a stored program that, when the program is executed, controls the device where the storage medium is located to perform the steps of the new energy access risk assessment method in the above embodiment.

[0040] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0041] If the functions described in this embodiment are implemented as software functional units and sold or used as independent products, they can be stored in one or more computing device-readable storage media. Based on this understanding, the parts of this embodiment that contribute to the prior art or the technical solution can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computing device (which may be a personal computer, server, mobile computing device, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this embodiment. The aforementioned storage media include: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0042] Those skilled in the art will understand that the embodiments of this example can be provided as methods, systems, or computer program products. Therefore, this example can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this example can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in this example can be implemented using various computer languages, such as the object-oriented programming language C++ and the embedded programming language C.

[0043] This embodiment is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this embodiment. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0044] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0045] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0046] This embodiment also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the new energy access risk assessment method described above.

[0047] The computer program product provided in this embodiment solves the technical problems of high testing and experimentation costs, delays, limited applicability, and slowdowns in scientific research progress in existing technologies. Compared with the prior art, the beneficial effects of the computer program product provided in this embodiment are the same as those of the new energy access risk assessment method provided in the above embodiments, and will not be repeated here.

[0048] It is evident that existing technologies for risk assessment of renewable energy grid integration typically only analyze the risks at a single level or in specific aspects, making it difficult to simultaneously characterize grid strength, transient overvoltage dynamic response, and their operational consequences within the same technical framework. Specifically, existing technologies have not yet established a comprehensive risk assessment system that uses the short-circuit ratio of multiple renewable energy plants as the core grid strength indicator, establishes a nonlinear dynamic mapping relationship between it and key characteristics of transient overvoltage, and further integrates it with operational consequences such as the loss of value from wind and solar power curtailment. Therefore, existing methods struggle to achieve the same real-time, automated, and quantitative risk identification and early warning effects as this application under conditions of concentrated grid connection of multiple renewable energy plants and rapidly changing operating conditions.

[0049] It should be noted that, without departing from the core technical concept of this invention, the specific form of the machine learning model used to construct the mapping relationship between short-circuit ratio and transient overvoltage is not unique. For example, deep learning models with time-series modeling capabilities, such as gated recurrent units (GRUs) and Transformers, can be used to equivalently replace the Long Short-Term Memory (LSTM) network. These substitutions are merely equivalent changes at the implementation level, and their purpose remains the same: to achieve efficient prediction, quantitative assessment, and decision support for the risk of renewable energy access, and do not constitute a substantial change to the technical solution of this invention.

[0050] Obviously, those skilled in the art can make various modifications and variations to this embodiment without departing from the spirit and scope of this embodiment. Therefore, if these modifications and variations of this embodiment fall within the scope of the claims of this embodiment and their equivalents, this embodiment is also intended to include these modifications and variations.

Claims

1. A risk assessment method for renewable energy grid connection, characterized in that, Including the following steps: S1. Real-time collection of multi-source heterogeneous data from SCADA / EMS, WAMS / PMU, new energy power station monitoring system, meteorological information system and equipment parameter database through data access module; S2. By fusing multi-source heterogeneous data, the short-circuit ratio of new energy power plants, a core indicator representing grid strength, is calculated in real time. MRSCR ; S3. Based on relevant standards, extract and construct practical risk feature vectors for engineering applications from different dimensions, including transient overvoltages. TOV Features and corresponding network structure risk characteristics; S4. Constructing the short-circuit ratio of multiple new energy power stations using deep learning models. MRSCR With transient overvoltage TOV Nonlinear dynamic mapping model between key features; S5. Short-circuit ratio of new energy multi-stations calculated based on real-time collected data. MRSCR With transient overvoltage TOV A nonlinear dynamic mapping model between key features is used for real-time dynamic risk assessment and risk level classification. S6. When the risk level reaches the warning threshold or transient overvoltage... TOV When the predicted value exceeds the limit, the system automatically triggers an early warning and generates decision recommendations.

2. The new energy access risk assessment method according to claim 1, characterized in that, Step S1 specifically includes the following steps: S11. Real-time collection of multi-source heterogeneous data from SCADA / EMS, WAMS / PMU, renewable energy power plant monitoring system, meteorological information system, and equipment parameter database via data access module. Key data collected includes: active power output of each renewable energy power plant. Unproductive efforts and operating status, grid bus voltage System topology, power flow distribution, and meteorological information including wind speed and light intensity; S12. The collected raw multi-source heterogeneous data is standardized by the preprocessing module, including: time alignment, anomaly detection and removal, missing data repair, and per-unit processing, in order to eliminate the influence of dimensions and provide consistent and reliable data input for subsequent calculations and analysis.

3. The new energy access risk assessment method according to claim 2, characterized in that, Step S2 specifically includes the following steps: S21. Calculate the equivalent impedance of the target convergence point based on real-time power grid topology and operating status. The equivalent impedance is obtained through the network node impedance matrix and the multi-point network equivalent calculation engine; S22. Calculate the equivalent short-circuit capacity of the target convergence point. The calculation formula is as follows: ； in, As the reference voltage, For voltage phasor conjugate; S23. Calculate the short-circuit ratio (MRSCR) of new energy multi-stations, a core indicator characterizing grid strength: ； in, and busbars and busbar The power injected by new energy sources busbar Multi-point Thevenin equivalent self-impedance, busbar and busbar The Thevenin equivalent mutual impedance at multiple points between them.

4. The new energy access risk assessment method according to claim 3, characterized in that, Step S3 specifically includes the following steps: S31, Transient overvoltage TOV Feature extraction, based on real-time power grid topology and operating status, employs a high-precision electromechanical transient simulation platform to simulate various anticipated fault types, generating a large amount of system transient response data corresponding to different short-circuit ratios, and then within the disturbance window. Within this process, the peak value, duration, and over-limit energy of the transient overvoltage are extracted, including: Transient voltage peak for: ； In the formula, To evaluate the peak voltage within the window, For nodes Voltage timing curve, This is the transient voltage threshold. The detection time window range; Exceeding the limit duration (s) is: ； in, This is an indicator function; it takes the value 1 if the condition is met, and 0 otherwise. Excess Energy for: ； In the formula, To measure the combined damage extent of overvoltage intensity and duration. ; S32. Network structure risk feature extraction, including calculation of electrical distance, the calculation formula is: ； in, V i Indicates busbar i Voltage amplitude, Q j Indicates busbar j Injected reactive power; this electrical distance reflects the degree of electrical coupling between nodes.

5. The new energy access risk assessment method according to claim 4, characterized in that, Step S4 specifically includes the following steps: S41. Constructing the short-circuit ratio of multiple new energy power plants using a Long Short-Term Memory (LSTM) network suitable for time-series data processing. MRSCR With transient overvoltage TOV A nonlinear dynamic mapping model between key features, wherein: The input sequence of the nonlinear dynamic mapping model The state characteristics within a window prior to the failure include: ； in, For new energy power plants, the short-circuit ratio is increased. For the first The active power output of each station; For the first The reactive power output of each power station; Electrical distance; For meteorological data; The network state update of the nonlinear dynamic mapping model is as follows: LSTM updates the cell state through its internal gating mechanism. and hidden state This allows the network to capture the long-term dependencies between the operating state and subsequent transient responses. The state update formula for the LSTM network is as follows: ； ； ； ； ； ； in, , , These are the state updates for the forget gate, input gate, and output gate, respectively. Candidate memory units, For output status, , , , These are the weight matrices input to each gate, respectively. , , , These are the cyclic weight matrices from the previous hidden state to each gate. , , , These are the corresponding bias vectors; The output of the nonlinear dynamic mapping model is the predicted value of the TOV feature: ； in, For the predicted peak value of transient overvoltage, For duration, The predicted excess energy; The training process of the nonlinear dynamic mapping model is performed by minimizing the following loss function: ； in, The weighting coefficients for the loss term are used to adjust the importance of different indicators. The nonlinear dynamic mapping model has online update capability, continuously absorbing new data through incremental learning to adapt to changes in power grid structure and the integration of new equipment. The update formula is: ； in, For model parameters, For learning rate, This is the gradient of the loss function with respect to the model parameters.

6. The new energy access risk assessment method according to claim 5, characterized in that, Step S5 specifically includes the following steps: S51. Based on the real-time collected data, the short-circuit ratio of multiple new energy power plants is calculated, and a nonlinear dynamic mapping model between the short-circuit ratio MRSCR of multiple new energy power plants and the key characteristics of transient overvoltage TOV is used to conduct real-time dynamic risk assessment and calculate the comprehensive risk index: ； in, w 1. w 2. w 3 indicates the weight of each sub-risk; MRSCR The formula for calculating sub-risk is: ； TOV The formula for calculating sub-risk is: ； in, β 1. β 2. β 3. β 4 represents the weighted portion of each risk indicator; The formula for calculating the value loss of wind and solar power curtailment is as follows: ； The formula for calculating the value loss due to wind and solar power curtailment is as follows: ； in: This refers to the amount of electricity that has been wasted from wind and solar power. for Available power output from renewable energy sources during certain periods; for Actual power output during the time period; The duration is in hours (h). for Average on-grid tariff or market clearing price of renewable energy during the specified period; S52. Risk Level Classification: The Comprehensive Risk Index (RI) classifies the risk level of the power grid into different levels. The specific classification method is as follows: ； in, γ 1. γ 2. γ 3. γ 4 is a preset threshold set based on the power grid's safety standards, historical data, or expert experience. Dynamic risk classification is performed based on the preset threshold, dividing the risk level into 1 to 5 levels, corresponding to "safe", "attention", "early warning", "high alert" and "critical" states, respectively, to provide operators with a clear situational awareness.

7. The new energy access risk assessment method according to claim 6, characterized in that, Step S6 specifically includes the following steps: S61. When the risk level reaches the warning threshold or TOV When the predicted value exceeds the limit, the system automatically triggers an early warning and generates decision recommendations. These recommendations include real-time control suggestions and supporting planning and configuration suggestions, among which: The real-time control recommendations, based on a rule base or a fast optimization algorithm, output executable control measures: (1) Recommendations for reactive power regulation: ； In the formula, Indicates the first Current reactive power setting value of each new energy power station / reactive power compensation device This indicates the suggested reactive power adjustment. , They represent the first The minimum / maximum allowable reactive power for each object. As a cutoff function, this formula provides an optimized strategy for reactive power regulation to ensure grid voltage stability; (2) Recommendation on the effectiveness limit: Based on the ranking of each station's sensitivity to the collection point voltage, the power output of the station with the weakest voltage support is restricted first. The aforementioned supportive planning and configuration recommendations aim to fundamentally enhance grid strength by providing capacity configuration suggestions for supportive power sources, including the required supplementary equivalent short-circuit support capacity. The calculation formula is: ； in, The minimum threshold required for safe operation. and busbars and busbar The power injected by new energy sources busbar Multi-point Thevenin equivalent self-impedance, busbar and busbar Thervenin equivalent mutual impedance at multiple points between them Equivalent short-circuit capacity at the target convergence point.

8. A new energy access risk assessment device, characterized in that, include: The real-time data acquisition and preprocessing module is used to acquire multi-source heterogeneous data from SCADA / EMS, WAMS / PMU, new energy power station monitoring system, meteorological information system and equipment parameter database in real time through the data access module; The online short-circuit ratio calculation module is used to calculate the short-circuit ratio of new energy multi-stations, a core indicator representing grid strength, in real time through multi-source heterogeneous data fusion. MRSCR ; The multi-dimensional risk feature extraction and structured characterization module extracts and constructs engineering-applicable risk feature vectors from different dimensions based on relevant standards, including transient overvoltage. TOV and the corresponding electrical distance; The mapping model building module is used to construct the short-circuit ratio of multiple new energy power plants using deep learning models. MRSCR With transient overvoltage TOV Nonlinear dynamic mapping model between key features; The real-time risk assessment and dynamic grading module is used to calculate the short-circuit ratio of multiple new energy power plants based on real-time collected data. MRSCR With transient overvoltage TOV A nonlinear dynamic mapping model between key features is used for real-time dynamic risk assessment and risk level classification. An automated early warning and precise decision-making suggestion generation module is used to generate early warnings when the risk level reaches the early warning threshold or a transient overvoltage occurs. TOV When the predicted value exceeds the limit, the system automatically triggers an early warning and generates decision recommendations.

9. An electronic device, the electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the new energy access risk assessment method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the new energy access risk assessment method as described in any one of claims 1 to 7.

Images