A new energy power production auxiliary monitoring system

Abstract

The application discloses a new energy power production auxiliary monitoring system, and relates to the technical field of power system monitoring.The system comprises a data collection module, a voltage stability evaluation module, a trend analysis module, a hierarchical early warning module and an early warning pushing module.The data collection module collects real-time data such as voltage, current and power of each new energy power station and performs preprocessing;the voltage stability evaluation module quantifies the voltage stability margin index based on power flow calculation;the trend analysis module predicts the voltage change trend by using ARIMA or LSTM algorithm;the hierarchical early warning module triggers primary or advanced early warning according to double threshold;and the early warning pushing module pushes early warning information to dispatchers in real time and provides visual display.The application can realize functional upgrade from post-event alarm to pre-event early warning, provide sufficient response time window for dispatchers and comprehensively improve the intelligent level of new energy power system voltage stability monitoring.

Description

Technical Field

[0001] This invention relates to the field of power system monitoring technology, specifically a new energy power production auxiliary monitoring system. Background Technology

[0002] As the scale of new energy power systems continues to expand, power plants are widely distributed and operate in complex environments, leading to increasingly stringent requirements for voltage stability monitoring. Current technologies primarily employ a "post-event response" model, using power forecast data to plan maintenance schedules in advance, which can ensure the reliable operation of power equipment to a certain extent. However, existing technologies lack a proactive early warning mechanism for voltage stability, lack the ability to quantitatively assess voltage stability margins in real time, and cannot provide early warning information before the voltage actually drops to the alarm threshold.

[0003] Specifically, existing monitoring methods have the following limitations: First, they lack voltage stability assessment methods based on real-time operating data, making it impossible to calculate voltage stability margin indicators to quantitatively reflect the voltage stability status; second, they do not introduce voltage change trend prediction and analysis functions, and can only provide post-event alarms without predicting the direction of voltage changes; third, they lack a tiered early warning mechanism, making it impossible to provide differentiated early warning information based on the urgency of voltage stability, resulting in dispatchers having difficulty obtaining sufficient response time windows. Summary of the Invention

[0004] This invention provides a new energy power production auxiliary monitoring system, which solves the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A new energy power production auxiliary monitoring system includes: a data collection module for collecting real-time operating data such as voltage, current, and power of various new energy power plants within a target area, and preprocessing and verifying the data quality; a voltage stability assessment module for calculating a voltage stability margin index based on a power flow calculation-based voltage stability margin assessment method using real-time operating data, quantitatively reflecting the voltage stability status; a trend analysis module for predicting voltage change trends using a time-series prediction algorithm based on real-time operating data and short-term historical data; a graded early warning module for triggering primary or advanced early warnings based on the comparison results of the voltage stability margin with a first and a second early warning threshold; and an early warning push module for pushing graded early warning information to dispatchers in real time.

[0007] This implementation method achieves a functional upgrade of the new energy power system from post-event alarm to pre-event early warning through the systematic integration of five core modules: data collection, voltage stability assessment, trend analysis, hierarchical early warning, and early warning push. The data collection module can uniformly collect real-time operating data such as voltage, current, and power from various power stations, providing accurate data support for subsequent modules. The voltage stability assessment module quantifies and outputs voltage stability margin indicators based on power flow calculations, which can reflect the voltage stability status of the power grid in real time. The trend analysis module introduces time-series prediction algorithms to analyze short-term voltage change trends, which can predict voltage trends before voltage exceeds limits. The hierarchical early warning module sets up two levels: primary early warning and advanced early warning, providing differentiated early warning information according to the urgency of voltage stability. The early warning push module pushes early warning information to dispatchers in real time, providing them with sufficient response time windows. The five modules have clear division of labor and interconnected data, which not only breaks through the limitations of post-event response in existing technologies, but also achieves proactive early warning before voltage exceeds limits through the integration of quantitative assessment and trend prediction, comprehensively improving the intelligence level of voltage stability monitoring and dispatch efficiency of the new energy power system.

[0008] In one possible implementation, the data collection module is used to synchronously collect real-time operating data such as voltage, current, and power of each new energy power station in the target area, establish a data quality verification mechanism, filter abnormal and invalid data, and ensure the accuracy and completeness of the data input to the voltage stability assessment module and trend analysis module.

[0009] In one possible implementation, the voltage stability assessment module is used to comprehensively consider multiple factors such as active power, reactive power, power factor, and load fluctuations to construct a comprehensive voltage stability margin index. The calculation formula for the voltage stability margin index is as follows:

[0010]

[0011] in, This indicates the voltage stability margin index. This indicates the maximum transmittable power under the current operating conditions. Indicates the current actual transmission power. Indicates available reactive power. This represents the minimum reactive power required to maintain voltage stability. This represents the power factor.

[0012] In this implementation, the voltage stability assessment module introduces a multi-dimensional factor fusion calculation method to construct a comprehensive voltage stability margin index, which can comprehensively reflect the voltage stability status of the new energy power system, avoid the limitations of single index assessment, significantly improve the accuracy and reliability of voltage stability assessment, and provide a reliable basis for the accurate triggering of the subsequent graded early warning module.

[0013] In one possible implementation, the trend analysis module is used to predict voltage change trends based on real-time operating data and short-term historical data within a preset time window, employing an ARIMA model or an LSTM neural network, and outputting a sequence of predicted voltage values ​​for the future preset time period. The prediction formula is as follows:

[0014]

[0015] in, express Time prediction Voltage value at any time express Real-time voltage value at any given moment. Indicates the length of the historical data window. Indicates model parameters.

[0016] In this implementation, the trend analysis module introduces a time-series prediction algorithm to make short-term trend predictions based on recent voltage fluctuation patterns. This allows the module to predict voltage changes before the voltage actually drops to the alarm threshold, overcoming the limitation of existing technologies that can only provide post-event alarms and giving dispatchers a sufficient response time window.

[0017] In one possible implementation, the hierarchical early warning module is used to set a first early warning threshold and a second early warning threshold, wherein the first early warning threshold is less than the second early warning threshold; when the voltage stability margin index is lower than the first early warning threshold, a primary early warning is triggered, and when the voltage stability margin index continues to deteriorate or the difference between the real-time voltage value and the alarm threshold is less than a preset difference, a higher-level early warning is triggered.

[0018] In one possible implementation, the graded early warning module is also used to introduce a trend deterioration judgment mechanism, which triggers an advanced early warning when the voltage stability margin shows a downward trend and falls below a preset deterioration threshold over multiple consecutive calculation cycles.

[0019] In this implementation, the graded early warning module achieves graded early warning function by setting dual early warning thresholds and corresponding triggering logic. It can provide differentiated early warning information according to the urgency of voltage stability, which can avoid the fatigue of dispatchers caused by excessive early warning, and ensure that faults can be responded to and dealt with quickly in emergency situations, significantly improving the pertinence and practicality of early warning information.

[0020] In one possible implementation, the early warning push module is used to establish a formatted output mechanism for early warning information, pushing the early warning information to the dispatcher's terminal. The early warning information includes key information such as the early warning level, voltage stability margin index value, real-time voltage value, expected over-limit time, and suggested control measures.

[0021] In one possible implementation, the early warning push module is also used in conjunction with the early warning information visualization module to intuitively display the voltage stability margin change trend and early warning status using dynamic curves, color grading, heat maps, and other forms.

[0022] In this implementation, the early warning push module establishes a formatted output mechanism for early warning information, pushing tiered early warning information to dispatchers in real time. This includes key information such as the early warning level, the expected time of exceeding the limit, and suggested control measures. It can not only quickly convey the early warning content but also provide dispatchers with clear control guidance. At the same time, the visualization module uses dynamic curves, color grading, heat maps, and other forms to intuitively present the voltage stability margin change trend and early warning status, which greatly improves the efficiency of dispatchers' understanding of early warning information and their response speed.

[0023] In one possible implementation, the active early warning monitoring system for voltage stability of the new energy power system further includes an adaptive adjustment module for early warning thresholds, used to dynamically adjust the first and second early warning thresholds based on historical power grid operating data and seasonal load characteristics, wherein the dynamic adjustment formula is:

[0024]

[0025] in, Indicates the adjusted number Level 1 warning threshold Indicates the first The base value of the level warning threshold, Indicates the standard deviation of voltage. Indicates the average voltage value. Indicates seasonal load characteristic factors, and This represents the adjustment factor.

[0026] In this implementation, the early warning threshold adaptive adjustment module introduces a dynamic adjustment mechanism to dynamically adjust the early warning threshold based on historical power grid operation data and seasonal load characteristics. This allows it to adapt to changes in the power grid's operating status, avoiding the problem that fixed thresholds cannot adapt to different operating scenarios, and significantly improving the applicability and accuracy of the early warning mechanism.

[0027] In one possible implementation, the active early warning monitoring system for voltage stability of the new energy power system also includes an early warning history module, which is used to establish an early warning event database and record data such as the time of each early warning, early warning level, voltage stability margin index value, actual voltage trend, and dispatch response status, for subsequent early warning effect evaluation and algorithm optimization.

[0028] In this implementation, the early warning history module establishes an early warning event database to record detailed data and scheduling response for each early warning. This provides data support for the quantitative evaluation of early warning effectiveness, provides a basis for subsequent algorithm optimization and continuous improvement of the early warning mechanism, and forms a closed-loop management of early warning.

[0029] This invention offers the following advantages: A data collection module enables synchronous acquisition and preprocessing of multi-source data, ensuring the accuracy and completeness of input data; a voltage stability assessment module employs a voltage stability margin assessment method based on power flow calculation to achieve quantitative assessment of voltage stability; a trend analysis module introduces a time-series prediction algorithm to predict voltage change trends, overcoming the limitations of existing technologies that rely on post-event response; a tiered early warning module sets up two levels—primary and advanced—providing differentiated early warning information based on the urgency of voltage stability; and an early warning push module pushes tiered early warning information to dispatchers in real time, providing a visual display function and offering dispatchers sufficient response time and clear control guidance, thus comprehensively enhancing the proactive voltage stability control capabilities of new energy power systems. Attached Figure Description

[0030] Figure 1 This is a modular structure diagram of a new energy power production auxiliary monitoring system.

[0031] Figure 2 This is a schematic diagram of the interface for visualizing early warning information. Detailed Implementation

[0032] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0033] Existing voltage monitoring methods in new energy power systems primarily employ a "post-event response" approach, failing to provide early warning information before voltage limits are exceeded. Specifically, current technologies lack voltage stability assessment methods based on real-time operational data, making it impossible to calculate voltage stability margin indicators to quantify voltage stability status; they also lack voltage change trend prediction and analysis functions, only providing post-event alarms and unable to predict voltage change trends; furthermore, they lack a tiered early warning mechanism, failing to provide differentiated early warning information based on the urgency of voltage stability issues, resulting in insufficient response time windows for dispatchers. These technical problems make existing monitoring methods inadequate to meet the proactive voltage stability control needs of new energy power systems.

[0034] To address the aforementioned issues, this disclosure provides a new energy power production auxiliary monitoring system, comprising: a data collection module for collecting real-time operating data such as voltage, current, and power of various new energy power plants within a target area, and preprocessing and verifying the data quality; a voltage stability assessment module for calculating a voltage stability margin index based on a power flow calculation-based voltage stability margin assessment method using real-time operating data, quantitatively reflecting the voltage stability status; a trend analysis module for predicting voltage change trends using a time-series prediction algorithm based on real-time operating data and short-term historical data; a tiered early warning module for triggering primary or advanced early warnings based on the comparison results of the voltage stability margin with a first and a second early warning threshold; and an early warning push module for pushing tiered early warning information to dispatchers in real time. Through the systematic integration of five core modules—data collection, voltage stability assessment, trend analysis, tiered early warning, and early warning push—the system upgrades the new energy power system from post-event alarms to pre-event early warnings. The five modules have clear divisions of labor and interconnected data, overcoming the limitations of post-event response in existing technologies and enabling proactive early warnings before voltage limits are exceeded through the fusion of quantitative assessment and trend prediction, comprehensively improving the intelligence level and dispatch efficiency of voltage stability monitoring in the new energy power system.

[0035] The system will now be described in detail with reference to specific embodiments.

[0036] Figure 1 This is a schematic diagram of the module structure of a new energy power production auxiliary monitoring system provided in an embodiment of this disclosure. The system can be implemented using software or hardware, and is generally integrated into a computing device. Figure 1 As shown, it includes a data collection module, a voltage stability assessment module, a trend analysis module, a graded early warning module, and an early warning push module.

[0037] The data collection module is used to collect real-time operating data such as voltage, current, and power of various new energy power plants in the target area, and to preprocess and verify the data quality of the real-time operating data.

[0038] The new energy power system voltage stability proactive early warning and monitoring system of this invention delineates target areas based on new energy business, and multiple new energy power plants, including photovoltaic power plants and wind power plants, are built within these target areas. Each new energy power plant periodically reports various real-time operating data to the new energy power system voltage stability proactive early warning and monitoring system.

[0039] In one possible implementation, the data collection module is used to synchronously collect real-time operating data such as voltage, current, and power from various new energy power plants within the target area. Specifically, each new energy power plant is equipped with a data acquisition terminal, which collects voltage and current values ​​of primary equipment through voltage and current transformers deployed within the power plant, and simultaneously collects active and reactive power data through power meters. The generated real-time operating data is then reported to the data collection module of the new energy power system voltage stability active early warning monitoring system. For example, the data acquisition terminal collects voltage, current, and power data once per second, reporting 86,400 data points per day or aggregated minute-level and hourly statistical values.

[0040] In one possible implementation, the data collection module is also used to establish a data quality verification mechanism to filter out abnormal and invalid data. Specifically, the data quality verification mechanism includes rationality verification, integrity verification, and consistency verification. Rationality verification is used to determine whether the collected voltage, current, and power values ​​are within a preset reasonable range, such as whether the voltage value is within the range of 0.9 to 1.1 times the rated voltage; integrity verification is used to determine whether each type of data is completely reported in each collection cycle; consistency verification is used to compare data collected from different data sources at the same time to see if there are any obvious contradictions.

[0041] Furthermore, the data collection module preprocesses the real-time operational data that has passed quality verification. Preprocessing operations include data standardization, time-scale alignment, and missing value imputation. Data standardization unifies data from different sampling frequencies into a standard format with the same time scale; time-scale alignment aligns the data reported by each power station according to a unified time scale; and missing value imputation uses interpolation algorithms or historical averages to fill in data gaps caused by communication failures.

[0042] In one possible implementation, the data collection module sends the preprocessed real-time operating data to the voltage stability assessment module and the trend analysis module respectively, ensuring the accuracy and completeness of the data input to the voltage stability assessment module and the trend analysis module.

[0043] The voltage stability assessment module is used to calculate the voltage stability margin index based on real-time operating data and a voltage stability margin assessment method based on power flow calculation, thereby quantitatively reflecting the voltage stability status.

[0044] In one possible implementation, the voltage stability assessment module comprehensively considers multiple factors such as active power, reactive power, power factor, and load fluctuations to construct a comprehensive voltage stability margin index. The specific formula for calculating the voltage stability margin index is as follows:

[0045]

[0046] in, This represents the voltage stability margin index, with a value ranging from 0 to 1. The closer the value is to 1, the better the voltage stability; the closer the value is to 0, the worse the voltage stability. This indicates the maximum transmittable power under the current operating conditions, in megawatts (MW). This indicates the current actual transmission power, in megawatts (MW). This indicates available reactive power, measured in megavars (MVar). This represents the minimum reactive power required to maintain voltage stability, measured in megavars (MVar). This represents the power factor.

[0047] In one possible implementation, the voltage stability assessment module determines the maximum transmittable power based on power flow calculation methods. Specifically, starting from the current power grid operating state, the load power is gradually increased and the power flow equations are iteratively solved until the system experiences voltage collapse or power flow non-convergence. The load power at this point is then determined as the maximum transmittable power. The power flow calculation employs the Newton-Raphson method or a fast decoupling method, considering constraints such as generator output limitations, transformer tap positions, and reactive power compensation device capacity. In one possible implementation, the voltage stability assessment module calculates the minimum reactive power required to maintain voltage stability. .

[0048] Specifically, the impact of each node on voltage stability is determined by sensitivity analysis. After identifying key nodes, the minimum reactive power support required to maintain the voltage level at the key nodes is calculated. Based on this, the minimum reactive power requirement of the entire system is obtained.

[0049] In this implementation, the voltage stability assessment module introduces a multi-dimensional factor fusion calculation method to construct a comprehensive voltage stability margin index, which can comprehensively reflect the voltage stability status of the new energy power system, avoid the limitations of single index assessment, significantly improve the accuracy and reliability of voltage stability assessment, and provide a reliable basis for the accurate triggering of the subsequent graded early warning module.

[0050] The trend analysis module is used to predict voltage change trends based on real-time operating data and short-term historical data using time-series prediction algorithms.

[0051] In one possible implementation, the trend analysis module is used to predict voltage change trends using an ARIMA model or an LSTM neural network, based on real-time operational data and short-term historical data within a preset time window. Specifically, the trend analysis module first constructs a time-series prediction model, trains the model parameters using historical data such as voltage, current, and power within a past time window, and then predicts the voltage value sequence within a future preset time period based on the trained model.

[0052] In one possible implementation, the prediction formula for the time series forecasting model is:

[0053]

[0054] in, express Time prediction Voltage value at any given time, in kilovolts (kV); express The real-time voltage value at any given moment, in kilovolts (kV). express The voltage value at any given time, in kilovolts (kV). express The voltage value at any given time, in kilovolts (kV).

[0055] n represents the length of the historical data window, which is usually between 12 and 48, corresponding to the data of the past 12 to 48 sampling periods; h represents the prediction step size, which is usually between 1 and 12, that is, predicting the voltage value 1 to 12 sampling periods later; θ represents the model parameters, including the autoregressive coefficients of the ARIMA model, the moving average coefficients, or the weights and biases of the LSTM neural network.

[0056] In one possible implementation, when the trend analysis module uses the ARIMA model to predict voltage trends, it first performs a stationarity test on the historical voltage data. If the data is not stationary, it performs differencing to make it stationary. Then, it determines the model order through the autocorrelation function (ACF) and partial autocorrelation function (PACF). Finally, it uses the least squares method to estimate the model parameters and make predictions.

[0057] In one possible implementation, when the trend analysis module uses an LSTM neural network to predict voltage trends, it first constructs a supervised learning dataset from historical voltage data, with the input being the voltage values ​​of the past n times and the output being the predicted voltage values ​​of the next h times. Then, it constructs a multi-layer LSTM network structure, trains the network weights through the backpropagation algorithm, and uses the trained network to predict voltage trends.

[0058] In one possible implementation, after the trend analysis module outputs a sequence of predicted voltage values ​​for a preset time period, it sends the sequence to the hierarchical early warning module as an important basis for the hierarchical early warning module to judge the voltage change trend.

[0059] In this implementation, the trend analysis module introduces a time-series prediction algorithm to make short-term trend predictions based on recent voltage fluctuation patterns. This allows the module to predict voltage changes before the voltage actually drops to the alarm threshold, overcoming the limitation of existing technologies that can only provide post-event alarms and giving dispatchers a sufficient response time window.

[0060] The graded early warning module is used to trigger a primary or advanced early warning based on the comparison result between the voltage stability margin and the first and second early warning thresholds.

[0061] In one possible implementation, the tiered early warning module is used to set a first early warning threshold and a second early warning threshold, wherein the first early warning threshold is less than the second early warning threshold. Specifically, the first early warning threshold can be set to 0.3, and the second early warning threshold can be set to 0.5. That is, a primary early warning is triggered when the voltage stability margin index is lower than 0.3, and a higher-level early warning is triggered when the voltage stability margin index is lower than 0.5. It should be understood that the specific values ​​of the first and second early warning thresholds can be adjusted according to the actual operation of the power grid and voltage stability requirements, and this embodiment does not limit this.

[0062] In one possible implementation, the warning triggering logic of the tiered warning module is as follows: a primary warning is triggered when the voltage stability margin indicator is lower than the first warning threshold; a higher-level warning is triggered when the voltage stability margin indicator continues to deteriorate or the difference between the real-time voltage value and the alarm threshold is less than a preset difference. The mechanism for determining continuous deterioration is that the voltage stability margin shows a downward trend over multiple consecutive calculation cycles; the preset difference can be set according to actual needs, typically set to 5% to 10% of the rated voltage.

[0063] In one possible implementation, the tiered early warning module also introduces a trend deterioration judgment mechanism. When the voltage stability margin shows a downward trend and falls below a preset deterioration threshold for multiple consecutive calculation cycles, an advanced early warning is triggered. Specifically, the preset deterioration threshold can be set to 0.25, and the number of consecutive calculation cycles can be set to 3 to 5. That is, when the voltage stability margin continues to decline and falls below 0.25 for 3 to 5 consecutive cycles, an advanced early warning is forcibly triggered to draw the attention of dispatchers.

[0064] In one possible implementation, please refer to Table 1, which is a table of early warning level classification and response measures for the graded early warning module.

[0065] Table 1. Classification of Early Warning Levels and Response Measures for the Tiered Early Warning Module

[0066] Primary warning yellow SMS and app push notifications Confirm within 30 minutes Advanced warning Or the trend is deteriorating red Phone calls, text messages, and app push notifications Confirm within 10 minutes Emergency Warning Or voltage exceeds limit Red flashing Telephone call Immediate response

[0067] in, This indicates the first warning threshold. This indicates the second warning threshold, and .

[0068] In this implementation, the graded early warning module achieves graded early warning function by setting dual early warning thresholds and corresponding triggering logic. It can provide differentiated early warning information according to the urgency of voltage stability, which can avoid the fatigue of dispatchers caused by excessive early warning, and ensure that faults can be responded to and dealt with quickly in emergency situations, significantly improving the pertinence and practicality of early warning information.

[0069] The early warning push module is used to push tiered early warning information to dispatchers in real time.

[0070] In one possible implementation, the early warning push module is used to establish a formatted output mechanism for early warning information, pushing the early warning information to the dispatcher's terminal. The early warning information includes key information such as the early warning level, voltage stability margin index value, real-time voltage value, estimated over-limit time, and recommended control measures.

[0071] Specifically, the formatted output of the early warning information includes fields such as: early warning number, early warning level, early warning time, region, affected power plants, current value of voltage stability margin index, real-time voltage value, predicted voltage exceedance time, trend analysis results, and suggested control measures. The early warning push module encapsulates the above fields into a standard format early warning message and pushes it to the dispatcher's terminal through a message queue.

[0072] In one possible implementation, the early warning push module is also used in conjunction with the early warning information visualization module to intuitively display the voltage stability margin change trend and early warning status using dynamic curves, color grading, heat maps, and other methods. Specifically, dynamic curves are used to show the trend of voltage stability margin indicators changing over time; color grading is used to use different colors to indicate the early warning level, such as green for normal operation, yellow for primary early warning, and red for advanced early warning; and heat maps are used to show the spatial distribution of voltage stability of each power station within the target area.

[0073] For example, please refer to Figure 2 , Figure 2 This is a schematic diagram of the interface for visually displaying early warning information. For example... Figure 2As shown, the visualization interface includes a real-time voltage stability margin curve, a regional voltage heat map, a list of early warning information, and a control suggestion panel. The real-time voltage stability margin curve displays the changing trend of the voltage stability margin index over the past 24 hours, and marks the early warning trigger points and predicted over-limit points on the curve; the regional voltage heat map uses a Geographic Information System (GIS) as the base map, and uses color depth to show the voltage stability margin distribution of each new energy power station in the target area; the early warning information list is sorted by early warning level and occurrence time, displaying currently valid early warning information; the control suggestion panel automatically generates control suggestions based on the current early warning situation, such as "It is recommended to adjust the output of the reactive power compensation device of XX power station" or "It is recommended to reduce the load in XX area".

[0074] In this implementation, the early warning push module establishes a formatted output mechanism for early warning information, pushing tiered early warning information to dispatchers in real time. This includes key information such as the early warning level, the expected time of exceeding the limit, and suggested control measures. It can not only quickly convey the early warning content but also provide dispatchers with clear control guidance. At the same time, the visualization module uses dynamic curves, color grading, heat maps, and other forms to intuitively present the voltage stability margin change trend and early warning status, which greatly improves the efficiency of dispatchers' understanding of early warning information and their response speed.

[0075] The active early warning monitoring system for voltage stability of new energy power systems also includes an adaptive adjustment module for early warning thresholds, which dynamically adjusts the first and second early warning thresholds based on historical power grid operation data and seasonal load characteristics.

[0076] In one possible implementation, the adaptive adjustment module for the early warning threshold dynamically adjusts the first and second early warning thresholds based on historical power grid operating data and seasonal load characteristics. The specific dynamic adjustment formula is as follows:

[0077]

[0078] in, Indicates the adjusted number Level 1 warning threshold The value is 1 or 2, corresponding to the first warning threshold and the second warning threshold, respectively. Indicates the first The base value for the level-one early warning threshold; This represents the standard deviation of voltage, in kilovolts (kV). This represents the average voltage value, in kilovolts (kV). This represents the seasonal load characteristic factor, with a value range of -0.2 to 0.2, and -0.1 for spring, 0.15 for summer, 0 for autumn, and -0.15 for winter. and This represents the adjustment factor, which can be set based on actual operating experience, and is usually taken as 0.1 to 0.5.

[0079] In one possible implementation, the early warning threshold adaptive adjustment module periodically updates the voltage standard deviation and average voltage value. Specifically, using real-time voltage data from the past week as a sample, it calculates the voltage standard deviation Vstd and the average voltage value Vavg, and updates the adjustment coefficient accordingly.

[0080] In one possible implementation, the early warning threshold adaptive adjustment module also considers the impact of load characteristics and the fluctuation of renewable energy output. Specifically, when a period of high renewable energy generation or a period of severe load fluctuation is detected, the early warning threshold is automatically tightened to improve early warning sensitivity; when the system is operating relatively smoothly, the early warning threshold is appropriately relaxed to reduce false alarms.

[0081] In this implementation, the early warning threshold adaptive adjustment module introduces a dynamic adjustment mechanism to dynamically adjust the early warning threshold based on historical power grid operation data and seasonal load characteristics. This allows it to adapt to changes in the power grid's operating status, avoiding the problem that fixed thresholds cannot adapt to different operating scenarios, and significantly improving the applicability and accuracy of the early warning mechanism.

[0082] The active early warning and monitoring system for voltage stability of new energy power systems also includes an early warning history module, which is used to establish an early warning event database and record data such as the time of each early warning, early warning level, voltage stability margin index value, actual voltage trend, and dispatch response status, for subsequent early warning effect evaluation and algorithm optimization.

[0083] In one possible implementation, the early warning history module records detailed information for each early warning. Specifically, each early warning event records the following fields: early warning number, early warning generation time, early warning cancellation time, early warning level, triggering condition, voltage stability margin index value sequence, real-time voltage value sequence, predicted over-limit time, actual over-limit situation, dispatcher confirmation time, dispatch response measures, and response effect evaluation.

[0084] In one possible implementation, the early warning history module provides an early warning effectiveness evaluation function. Specifically, by comparing the deviation between the time difference between the early warning and the actual voltage exceeding the limit with the early warning lead time setting, the accuracy and timeliness of the early warning are evaluated; by statistically analyzing the response time and response measures of dispatchers to different levels of early warnings, the practicality and guidance of the early warning information are evaluated.

[0085] In one possible implementation, the early warning history module provides data support for algorithm optimization. Specifically, using the recorded early warning history data, machine learning methods are employed to continuously optimize the parameters of the voltage stability assessment model, improving assessment accuracy; optimize the hyperparameters of the time series prediction model, improving prediction accuracy; and adjust the early warning threshold setting and grading strategy based on the early warning effect evaluation results.

[0086] Furthermore, while the modules are described in a specific order, this should not be construed as requiring these modules to be executed in the specific order shown or in a sequential order. Multitasking and parallel processing may be advantageous in certain environments. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

Claims

1. A new energy power production auxiliary monitoring system, characterized in that, include: The data collection module is used to collect real-time operating data such as voltage, current, and power of each new energy power station in the target area, and to preprocess and verify the data quality of the real-time operating data. The voltage stability assessment module is used to calculate the voltage stability margin index based on the real-time operating data using a voltage stability margin assessment method based on power flow calculation, and to quantitatively reflect the voltage stability status. The trend analysis module is used to predict voltage change trends based on the real-time operating data and short-term historical data using a time-series prediction algorithm. A graded early warning module is used to trigger a primary or advanced early warning based on the comparison result between the voltage stability margin and the first and second early warning thresholds. The early warning push module is used to push tiered early warning information to dispatchers in real time.

2. The new energy power production auxiliary monitoring system according to claim 1, characterized in that, The data collection module is used to synchronously collect real-time operating data such as voltage, current, and power of each new energy power station in the target area, establish a data quality verification mechanism, filter abnormal and invalid data, and ensure the accuracy and completeness of the data input to the voltage stability assessment module and the trend analysis module.

3. The new energy power production auxiliary monitoring system according to claim 1, characterized in that, The voltage stability assessment module comprehensively considers multiple factors such as active power, reactive power, power factor, and load fluctuations to construct a comprehensive voltage stability margin index. The calculation formula for the voltage stability margin index is as follows: in, This indicates the voltage stability margin index. This indicates the maximum transmittable power under the current operating conditions. Indicates the current actual transmission power. Indicates available reactive power. This represents the minimum reactive power required to maintain voltage stability. This represents the power factor.

4. The new energy power production auxiliary monitoring system according to claim 1, characterized in that, The trend analysis module is used to predict voltage change trends based on real-time operating data and short-term historical data within a preset time window, employing an ARIMA model or an LSTM neural network. It outputs a sequence of predicted voltage values ​​for a future preset time period. The prediction formula is as follows: in, express Time prediction Voltage value at any time express Real-time voltage value at any given moment. Indicates the length of the historical data window. Indicates model parameters.

5. The new energy power production auxiliary monitoring system according to claim 1, characterized in that, The graded early warning module is used to set a first early warning threshold and a second early warning threshold, wherein the first early warning threshold is less than the second early warning threshold; A primary warning is triggered when the voltage stability margin indicator is lower than the first warning threshold. An advanced warning is triggered when the voltage stability margin indicator continues to deteriorate or the difference between the real-time voltage value and the alarm threshold is less than the preset difference.

6. The new energy power production auxiliary monitoring system according to claim 5, characterized in that, The graded early warning module is also used to introduce a trend deterioration judgment mechanism. When the voltage stability margin shows a downward trend and is lower than the preset deterioration threshold in multiple consecutive calculation cycles, an advanced early warning is triggered.

7. The new energy power production auxiliary monitoring system according to claim 1, characterized in that, The early warning push module is used to establish a formatted output mechanism for early warning information, which pushes the early warning information to the dispatcher's terminal. The early warning information includes key information such as early warning level, voltage stability margin index value, real-time voltage value, expected over-limit time, and suggested control measures.

8. The new energy power production auxiliary monitoring system according to claim 7, characterized in that, The early warning push module is also used in conjunction with the early warning information visualization module to intuitively display the voltage stability margin change trend and early warning status using dynamic curves, color grading, heat maps, and other forms.

9. The new energy power production auxiliary monitoring system according to claim 1, characterized in that, The active early warning monitoring system for voltage stability of the new energy power system also includes an adaptive adjustment module for early warning thresholds, used to dynamically adjust the first and second early warning thresholds based on historical power grid operation data and seasonal load characteristics. The dynamic adjustment formula is as follows: in, Indicates the adjusted number Level 1 warning threshold Indicates the first The base value of the level warning threshold, Indicates the standard deviation of voltage. Indicates the average voltage value. Indicates seasonal load characteristic factors, and This represents the adjustment factor.

10. A new energy power production auxiliary monitoring system according to claim 1, characterized in that, The active early warning monitoring system for voltage stability of the new energy power system also includes an early warning history module, which is used to establish an early warning event database and record data such as the time of each early warning, early warning level, voltage stability margin index value, actual voltage trend, and dispatch response status, for subsequent early warning effect evaluation and algorithm optimization.

Images