Substation 3D Simulation System

Abstract

The invention discloses a three-dimensional simulation system for a substation, and relates to the technical field of three-dimensional simulation. An update frequency monitoring module is used to monitor the frequency of equipment state changes in real time, and compares it with the update frequency of a simulation system to evaluate whether an update mechanism needs to be adjusted. A transmission delay analysis module evaluates data transmission delay through time series analysis to ensure synchronization between the simulation system and field data. A real-time evaluation module evaluates the update real-time of a simulation model in combination with equipment state changes and transmission delays, and divides it into high, medium and low real-time levels through a real-time classification module. For different levels, an optimization module adjusts the update cycle of the simulation system, optimizes the frequency and transmission efficiency of the low real-time level, and a dynamic adjustment module performs in-depth analysis and early warning processing on the medium real-time level to ensure that the simulation model reflects the actual state of the substation in a timely and accurate manner, thereby improving the decision-making quality of equipment scheduling, fault location and system optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional simulation, and in particular to a three-dimensional simulation system for a transformer substation. Background Art

[0002] Substation 3D simulation refers to the use of computer technology to digitally display the actual facilities, equipment and environmental information of the substation through 3D modeling technology to form a virtual 3D model. This model can simulate various operating conditions, equipment configurations and their relationships inside the substation, helping staff to more intuitively understand the structure and function of the substation, conduct operation drills, troubleshooting, etc. Through 3D simulation technology, the design, construction, operation and maintenance process of the substation can be managed and optimized more efficiently. It can not only perform virtual scheduling and simulated operation of equipment, but also conduct accident emergency drills, personnel training and safety assessments, etc., to improve work efficiency and safety. In addition, 3D simulation can also be combined with real-time data to achieve dynamic monitoring and early warning of the real-time status of the substation.

[0003] The prior art has the following deficiencies:

[0004] The equipment and facilities of the substation will be replaced, upgraded and maintained over time. If the information in the model cannot be updated in time, it may lead to a large difference between the 3D simulation model and the actual substation. Especially after equipment failure, shutdown or reconfiguration, if the simulation system cannot update the model in time, it will lead to wrong decisions or the system cannot correctly reflect the real situation of the substation. This delay may affect equipment scheduling, fault location, system optimization and other aspects of work. Summary of the invention

[0005] The purpose of the present invention is to provide a three-dimensional simulation system for a substation to solve the deficiencies in the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solutions: a three-dimensional simulation system for a substation, comprising an update frequency monitoring module, a transmission delay analysis module, a real-time evaluation module, a real-time division module, an optimization module and a dynamic adjustment module;

[0007] Update frequency monitoring module: through the real-time monitoring system of the substation, the dynamic state change frequency of the substation equipment in several time periods is monitored. The several time periods are divided according to the sampling intervals of the equipment state changes, and the average frequency of the equipment state changes is calculated, and the degree of deviation from the update frequency of the 3D simulation system is analyzed to evaluate whether the update mechanism needs to be adjusted;

[0008] Transmission delay analysis module: When the adjustment and update mechanism is needed, the data transmission path from the field to the simulation system is monitored, the data transmission time is measured and the synchronization error is recorded. The data transmission delay in different time periods is evaluated by time series analysis.

[0009] Real-time evaluation module: evaluates the real-time update of the 3D simulation model based on the deviation between the average frequency of device status changes and the update frequency of the 3D simulation system and the data transmission delay in different time periods;

[0010] Real-time classification module: according to the evaluation results, the update real-time of the 3D simulation model is classified into different levels, namely, high real-time update level, medium real-time update level and low real-time update level;

[0011] Optimization module: For high real-time update levels, adjust the update cycle of the simulation system according to the frequency of device status changes; for low real-time update levels, increase the model update frequency and optimize the response time of data acquisition devices and transmission systems;

[0012] Dynamic adjustment module: For the medium real-time update level, the real-time update of the 3D simulation model within a fixed time period is deeply analyzed, and the update frequency of the model is dynamically adjusted according to the analysis results, and timely warning processing is carried out.

[0013] Preferably, in the update frequency monitoring module, a frequency synchronization deviation index is generated according to a comparison result between an average frequency of device state changes and an update frequency of the three-dimensional simulation system. The frequency synchronization deviation index is obtained by:

[0014] From the substation real-time monitoring system, obtain the state change frequency of the equipment in n time periods i, and calculate the average frequency of equipment state changes , records the update frequency of the 3D simulation system in the corresponding time period i ; Assign a weight to each time period i , calculate the absolute deviation for each time period , that is, the difference between the device state change frequency and the simulation system update frequency, and the frequency synchronization deviation index is calculated using the weighted average formula, which is expressed as: ; In the formula, is the frequency synchronization deviation index, and n is the total number of time periods.

[0015] Preferably, in the transmission delay analysis module, a data transmission delay anomaly index is generated after comparative analysis of the data transmission delays in each time period by using an autoregressive integral moving average model. The method for obtaining the data transmission delay anomaly index is:

[0016] Collect the substation data transmission delay values ​​within the T time period to form a time series data set ; Stabilize the collected data and determine the parameters p, d, and q of the autoregressive integrated moving average model ARIMA; p represents the number of lagged data used to predict the current value, d represents the number of differences required to make the time series stable, and q represents the impact of current and past error terms on the current value; use the selected p, d, q parameters to fit the time series of data transmission delay using the ARIMA model, the expression is: ; The delay value at the current time point, α is a constant term, is the autoregression coefficient, is the sliding average coefficient, is the white noise term;

[0017] Use the ARIMA model to predict the data transmission delay in the future period and obtain the predicted value ; Then, calculate the forecast error for each time period , the expression is: ; is the actual delay value, is the predicted value of the ARIMA model; the data transmission delay anomaly index reflects the abnormal degree of the prediction error. The data transmission delay anomaly index is calculated as follows: ; is the data transmission delay anomaly index, The error sequence The standard deviation of .

[0018] Preferably, in the real-time evaluation module, the real-time update of the three-dimensional simulation model is evaluated according to the deviation degree between the average frequency of the device state change and the update frequency of the three-dimensional simulation system and the data transmission delay in different time periods, specifically:

[0019] The frequency synchronization deviation index and the data transmission delay anomaly index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model predicts the updated real-time value label of the three-dimensional simulation model with each group of comprehensive feature vectors as the prediction target, and minimizes the sum of prediction errors of the updated real-time value labels of all three-dimensional simulation models as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The updated real-time value of the three-dimensional simulation model is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0020] Preferably, in the real-time classification module, the update real-time of the three-dimensional simulation model is divided into different levels according to the evaluation results, and is divided into a high real-time update level, a medium real-time update level and a low real-time update level, specifically:

[0021] The updated real-time value of the three-dimensional simulation model obtained is compared with a gradient standard threshold, wherein the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the updated real-time value of the three-dimensional simulation model is compared with the first standard threshold and the second standard threshold respectively;

[0022] If the update real-time value of the three-dimensional simulation model is greater than the second standard threshold, it means that the update real-time of the three-dimensional simulation model is high, and a high real-time signal is generated, and the update real-time of the three-dimensional simulation model is classified into a high real-time update level;

[0023] If the update real-time value of the three-dimensional simulation model is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the update real-time of the three-dimensional simulation model is general, and a medium real-time signal is generated at this time, and the update real-time of the three-dimensional simulation model is classified as a medium real-time update level;

[0024] If the update real-time value of the 3D simulation model is less than the first standard threshold, it indicates that the update real-time of the 3D simulation model is low. In this case, a low real-time signal is generated and the update real-time of the 3D simulation model is classified into a low real-time update level.

[0025] Preferably, in the dynamic adjustment module, for the medium real-time update level, the real-time update of the three-dimensional simulation model within a fixed time period is deeply analyzed, and the update frequency of the model is dynamically adjusted according to the analysis results, and timely warning processing is performed, specifically:

[0026] For the medium real-time update level, that is, the update real-time value of the three-dimensional simulation model generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the update real-time values ​​of the three-dimensional simulation model generated within a subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and a corresponding data set is established, the mean and standard deviation of the data set are calculated, and after analyzing them, the update frequency of the model is dynamically adjusted according to the analysis results, and timely early warning processing is performed.

[0027] Preferably, if the mean of the update real-time values ​​in the data set is greater than or equal to the reference threshold of the update real-time value mean, and the standard deviation of the update real-time value is less than the reference threshold of the standard deviation of the update real-time value, a third-level warning signal is generated at this time, and the update frequency remains unchanged;

[0028] If the mean of the updated real-time values ​​is greater than or equal to the reference threshold of the mean of the updated real-time values, and the standard deviation of the updated real-time values ​​is greater than or equal to the reference threshold of the standard deviation of the updated real-time values, a secondary warning signal is generated at this time, and the update frequency of the simulation model needs to be increased and the update cycle needs to be reduced;

[0029] If the mean of the updated real-time value is less than the reference threshold of the mean of the updated real-time value, and the standard deviation of the updated real-time value is greater than or equal to the reference threshold of the standard deviation of the updated real-time value, a first-level warning signal is generated, the update frequency is increased, and the response time of the data acquisition device and the data transmission system is optimized first;

[0030] If the updated real-time value mean is less than the reference threshold of the updated real-time value mean, and the updated real-time value standard deviation is less than the reference threshold of the updated real-time value standard deviation, no warning signal is generated and no additional adjustment is required.

[0031] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0032] 1. The present invention solves the problem of mismatch between the three-dimensional simulation model and the actual state during the replacement, upgrade and maintenance of substation equipment by introducing an update frequency monitoring module, a transmission delay analysis module, a real-time evaluation module, a real-time division module, an optimization module and a dynamic adjustment module, ensuring that the simulation system can reflect the equipment status changes in real time. By monitoring the equipment status change frequency and transmission delay, the frequency synchronization deviation index and the data transmission delay anomaly index are generated, and the machine learning model is used to comprehensively evaluate the update real-time value of the simulation model. According to the real-time division results, the update frequency is dynamically adjusted and the data transmission system is optimized for high, medium and low real-time levels, thereby improving the system's responsiveness and decision-making accuracy.

[0033] 2. The present invention can generate early warning signals according to the fluctuation of real-time values, and implement precise optimization measures through hierarchical processing. At high real-time levels, the update cycle is optimized to reduce resource consumption; at low real-time levels, the update frequency is increased, and data transmission response capabilities are optimized first; at medium real-time levels, the update frequency is dynamically adjusted and early warnings are issued through analysis of the mean and standard deviation of real-time data to ensure the stability and accuracy of the simulation model. The reliability and efficiency of the substation three-dimensional simulation system in equipment scheduling, fault location and operation optimization are improved as a whole, providing a strong guarantee for the continuous and stable operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0035] Figure 1 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0036] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] For examples, see Figure 1 As shown, the substation three-dimensional simulation system described in this embodiment includes an update frequency monitoring module, a transmission delay analysis module, a real-time evaluation module, a real-time division module, an optimization module and a dynamic adjustment module;

[0038] Update frequency monitoring module: through the real-time monitoring system of the substation, the dynamic state change frequency of the substation equipment in several time periods is monitored. The several time periods are divided according to the sampling intervals of the equipment state changes, and the average frequency of the equipment state changes is calculated, and the degree of deviation from the update frequency of the 3D simulation system is analyzed to evaluate whether the update mechanism needs to be adjusted;

[0039] Transmission delay analysis module: When the adjustment and update mechanism is needed, the data transmission path from the field to the simulation system is monitored, the data transmission time is measured and the synchronization error is recorded. The data transmission delay in different time periods is evaluated by time series analysis.

[0040] Real-time evaluation module: evaluates the real-time update of the 3D simulation model based on the deviation between the average frequency of device status changes and the update frequency of the 3D simulation system and the data transmission delay in different time periods;

[0041] Real-time classification module: according to the evaluation results, the update real-time of the 3D simulation model is classified into different levels, namely, high real-time update level, medium real-time update level and low real-time update level;

[0042] Optimization module: For high real-time update levels, adjust the update cycle of the simulation system according to the frequency of device status changes; for low real-time update levels, increase the model update frequency and optimize the response time of data acquisition devices and transmission systems;

[0043] Dynamic adjustment module: For the medium real-time update level, the real-time update of the 3D simulation model within a fixed time period is deeply analyzed, and the update frequency of the model is dynamically adjusted according to the analysis results, and timely warning processing is carried out.

[0044] In the update frequency monitoring module, first, the substation's real-time monitoring system (such as SCADA system, equipment sensor network, etc.) continuously collects status data of various equipment (such as transformers, circuit breakers, switches, protection devices, etc.). These status data usually include equipment start and stop, load changes, fault information, operating parameters, etc. The data collection is divided into several fixed time periods (such as every minute, every hour, or every work shift) for subsequent analysis.

[0045] Detect changes in device status through real-time monitoring data, such as the start and stop of device switches, changes in load, and the occurrence of faults. These changes can be represented by signal changes, event triggers, etc. Calculate the frequency of device status changes in each time period. Specifically, if a device undergoes several changes in a period of time (such as the number of starts and stops, the number of load fluctuations, and the number of fault recovery times), the frequency of the device status changes can be counted. Calculate the average frequency of all device status changes in a period of time, that is, the number of device status changes divided by the total number of time periods (for example, the number of changes per unit time).

[0046] The update frequency of the 3D simulation system may be fixed or it may be adjusted dynamically according to demand. For example, some systems update every hour, while others may update only when changes are detected in key equipment. Record the actual update frequency of the simulation system, that is, how often the simulation system updates the model. This usually depends on the simulation system configuration and actual operational requirements.

[0047] Compare the average frequency of device state changes with the update frequency of the simulation system. Common measurement methods are to calculate the absolute difference or relative deviation between the two. The size of the deviation reflects whether the simulation system can respond to changes in device state in a timely manner. If the deviation is large, it means that the simulation system may be updated lagging and fails to fully reflect the actual state of the substation. If the deviation is small, it means that the synchronization between the simulation system and the actual device state changes is good.

[0048] The frequency synchronization deviation index is generated based on the comparison result between the average frequency of the device state change and the update frequency of the three-dimensional simulation system. The method for obtaining the frequency synchronization deviation index is as follows:

[0049] From the substation real-time monitoring system, obtain the state change frequency of the equipment in n time periods i (such as the number of changes per hour), and calculate the average frequency of equipment state changes , records the update frequency of the 3D simulation system in the corresponding time period i ; Assign a weight to each time period i ,The weight assigned can include: the importance of the equipment status change (e.g. key equipment has a higher weight).,The total number of changes in a time period (time periods with a higher frequency of changes have a higher weight).

[0050] Calculate the absolute deviation for each time period , that is, the difference between the device state change frequency and the simulation system update frequency, and the frequency synchronization deviation index is calculated using the weighted average formula, which is expressed as: ; In the formula, is the frequency synchronization deviation index, and n is the total number of time periods.

[0051] The larger the frequency synchronization deviation index (FSDI), the greater the deviation between the average frequency of device state changes and the update frequency of the 3D simulation system. In other words, if the frequency of device state changes is much higher or lower than the update frequency of the simulation system, the simulation system may fail to reflect the state changes of the actual device in a timely manner, thus affecting functions such as fault location, device scheduling, and system optimization. In this case, it is necessary to adjust the update mechanism of the simulation system, such as increasing the update frequency or introducing a dynamic update strategy, to ensure the synchronization of the simulation model with the actual device state.

[0052] The smaller the frequency synchronization deviation index is, the closer the average frequency of equipment status changes is to the update frequency of the three-dimensional simulation system, the higher the synchronization between the two, and the simulation model can more accurately reflect the actual operation status of the substation. If the index is small within a certain range (such as below the set threshold), it means that the current update mechanism is sufficient to meet the system requirements. At this time, there is usually no need to further adjust the update strategy, but the system still needs to be monitored regularly to prevent the deviation index from increasing again due to sudden changes in the equipment status change pattern.

[0053] In the transmission delay analysis module, the data transmission path from the field equipment to the simulation system is monitored to ensure that every link in the data transmission process is within the controllable range. The various network nodes, transmission media, and data format conversions that the data passes through from field collection to simulation system update are recorded to identify possible sources of delay.

[0054] Accurately measure the transmission time of each data packet. Calculate the delay of each data transmission by comparing the timestamp of data collected by the field equipment with the timestamp of data received by the simulation system. Record the transmission time in different time periods, and calculate the average and variance of the transmission time to understand the stability and fluctuation of data transmission.

[0055] Synchronization error refers to the difference between the time when field data is collected and the time when the simulation system updates the data. The synchronization error is calculated by comparing the actual time of each device status change with the time when the simulation system updates. On this basis, the synchronization error of different time periods is recorded, and the size and distribution characteristics of the error are analyzed to evaluate whether there is a synchronization problem in the system.

[0056] Perform time series analysis on data transmission delays in different time periods to evaluate the regularity, periodicity, and volatility of the delays. Specific methods include: Stationarity test: Determine whether the transmission delay time series is a stationary series. If there is a trend or seasonal fluctuation, the parameters of the update mechanism may need to be adjusted. Autocorrelation analysis: Analyze the autocorrelation function of the transmission delay to see if there are periodic changes or abnormal fluctuations in the delay. Prediction model: Build a prediction model for transmission delay based on historical data (such as the autoregressive integrated moving average model ARIMA) to predict possible future delay trends to guide the optimization of simulation system updates.

[0057] The data transmission delay anomaly index is generated by comparing and analyzing the data transmission delay in each time period through the autoregressive integral moving average model. The method for obtaining the data transmission delay anomaly index is as follows:

[0058] Collect the substation data transmission delay values ​​within the T time period to form a time series data set ; Stabilize the collected data, usually by using the difference method to convert the non-stationary series into a stationary series. The autoregressive integrated moving average model ARIMA consists of three main parameters (p, d, q): p (autoregressive term): indicates how many lagged data (i.e. past values) are used to predict the current value. d (difference order): indicates how many times the difference is required to make the time series stationary. q (moving average term): indicates the impact of the current and past error terms (residuals) on the current value.

[0059] Use the autocorrelation function (ACF) and partial autocorrelation function (PACF) plots to identify the appropriate order of AR and MA. ACF helps determine the order of the MA part, and PACF helps determine the order of the AR part. Use unit root tests (such as the ADF test) to determine whether the data is stationary and decide whether differencing is necessary. The partial autocorrelation function represents the linear relationship between a lagged variable and the current variable after removing the effects of the intermediate lags. PACF is used to identify the appropriate order of the AR (autoregressive) part of the ARIMA model, that is, how many lagged values ​​to choose to predict the current value. For example, if the PACF plot shows that the partial autocorrelation coefficient is significantly higher than the confidence interval at a lag order of 2 and quickly approaches 0 after the lag order exceeds 2, then the order p=2 of the AR part can be selected.

[0060] Using the selected p, d, q parameters, the ARIMA model is used to fit the time series of data transmission delays. The expression is: ; The delay value at the current time point, α is a constant term, is the autoregression coefficient (AR), is the moving average coefficient (MA), is the white noise term (error term);

[0061] Use the ARIMA model to predict the data transmission delay in the future period and obtain the predicted value ; Then, calculate the forecast error for each time period (i.e. the difference between the actual value and the predicted value), expressed as: ; is the actual delay value, is the predicted value of the ARIMA model;

[0062] The data transmission delay anomaly index reflects the degree of anomaly of the prediction error, usually by quantifying the size and volatility of the prediction error. The data transmission delay anomaly index is calculated as follows: ; is the data transmission delay anomaly index, The error sequence The standard deviation of the forecast reflects the volatility of the forecast error.

[0063] The larger the data transmission delay anomaly index (DTAI), the more serious the deviation of the data transmission delay from the normal range during this period. A larger DTAI indicates that the prediction error is significantly higher than expected, which may mean that the transmission delay is abnormal due to network congestion, equipment failure or other emergencies. At this time, the system may face performance bottlenecks, affecting the timely update of data and real-time decision-making, and emergency measures need to be taken, such as optimizing network bandwidth, checking device status or adjusting the update frequency of the simulation system.

[0064] On the contrary, the smaller the data transmission delay anomaly index is, the more stable the data transmission delay is during this period, the smaller the error with the predicted value is, and it is within the normal fluctuation range. A smaller DTAI value means that the delay variation during the data transmission process is small, in line with expectations, and there are no significant anomalies. At this time, the update frequency of the simulation system and the real-time monitoring system can remain unchanged and continue to operate according to the established plan.

[0065] Real-time evaluation module: evaluates the real-time update of the 3D simulation model based on the deviation between the average frequency of device status changes and the update frequency of the 3D simulation system and the data transmission delay in different time periods.

[0066] The frequency synchronization deviation index and the data transmission delay anomaly index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model predicts the updated real-time value label of the three-dimensional simulation model with each group of comprehensive feature vectors as the prediction target, and minimizes the sum of prediction errors of the updated real-time value labels of all three-dimensional simulation models as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The updated real-time value of the three-dimensional simulation model is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0067] The method for obtaining the update real-time value of the three-dimensional simulation model is as follows: from the comprehensive feature vector training data of the trained machine learning model, the corresponding function expression is obtained: ; In the formula, is the output function of the model, is the frequency synchronization deviation index, DTAI is the data transmission delay anomaly index, It is the real-time value for updating the 3D simulation model.

[0068] Real-time classification module: According to the evaluation results, the update real-time of the three-dimensional simulation model is divided into different levels, which are divided into a high real-time update level, a medium real-time update level and a low real-time update level.

[0069] The updated real-time value of the three-dimensional simulation model obtained is compared with a gradient standard threshold, wherein the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the updated real-time value of the three-dimensional simulation model is compared with the first standard threshold and the second standard threshold respectively;

[0070] If the update real-time value of the three-dimensional simulation model is greater than the second standard threshold, it means that the update real-time of the three-dimensional simulation model is high, and a high real-time signal is generated, and the update real-time of the three-dimensional simulation model is classified into a high real-time update level;

[0071] If the update real-time value of the three-dimensional simulation model is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the update real-time of the three-dimensional simulation model is general, and a medium real-time signal is generated at this time, and the update real-time of the three-dimensional simulation model is classified as a medium real-time update level;

[0072] If the update real-time value of the 3D simulation model is less than the first standard threshold, it indicates that the update real-time of the 3D simulation model is low. In this case, a low real-time signal is generated and the update real-time of the 3D simulation model is classified into a low real-time update level.

[0073] It should be noted that the first standard threshold and the second standard threshold are determined through statistical analysis, experimental verification and the experience of those skilled in the art. The specific method is as follows:

[0074] Collect historical data on the status changes of substation equipment and analyze the distribution characteristics of the real-time update value of the 3D simulation model; use statistical methods, such as using the 25th percentile of the real-time update value as the first standard threshold and the 75th percentile as the second standard threshold; further verify in the experiment and optimize the threshold setting to meet the actual needs of the system. For example, in a specific application, statistical analysis shows that the mean of the real-time update value is 0.75 and the standard deviation is 0.15. Combined with the experimental results, the first standard threshold is finally determined to be 0.60 and the second standard threshold is 0.90.

[0075] Optimization module: For high real-time update levels, adjust the update cycle of the simulation system according to the frequency of device status changes; for low real-time update levels, increase the model update frequency and optimize the response time of data acquisition devices and transmission systems.

[0076] High real-time update level (high real-time value) ensures that the simulation system maintains a high real-time level and avoids unnecessary frequent updates, thereby saving computing resources and network bandwidth.

[0077] Optimization measures include: For high real-time update levels, the update cycle of the simulation system can be appropriately extended. Because the frequency of device status changes is low, the system can be updated based on a longer time interval without affecting the accuracy and timeliness of decision-making. If the average frequency of device status changes is lower than a certain threshold, the update interval of the simulation system can be extended. For example, the update cycle can be adjusted from once a minute to once every 5 minutes or every 10 minutes. By optimizing the update interval, unnecessary calculations and data transmission can be reduced, reducing the burden on the system.

[0078] Change frequency according to device status Dynamically calculate the reasonable update cycle according to the real-time requirements of the 3D simulation model ,For example: ; In addition, a prediction model is used to estimate the changes in equipment status in the future, avoiding frequent updates of simulation models and reducing the waste of computing resources.

[0079] Low real-time update level (low real-time value) increases the update frequency of the simulation system to reflect changes in device status and data transmission delays more promptly, thereby ensuring that the system can cope with higher dynamic changes.

[0080] Optimization measures include: For low real-time update levels, the frequency of device status changes is high, or there is a large delay in data transmission, resulting in a lag in simulation model updates, affecting the real-time performance of the system. At this time, increasing the update frequency of the simulation model is the key to improving real-time performance. Increase the update frequency of the simulation model and shorten the model update cycle. For example, if the original update cycle is 5 minutes, it can be shortened to an update every 1 minute or every 30 seconds. This approach enables the simulation system to reflect changes in device status and real-time data more quickly, thereby reducing decision errors caused by lags.

[0081] Based on the frequency of device status changes Comprehensive evaluation of data transmission delay and dynamic adjustment of update cycle. For example: ;in, This is the minimum update period to ensure that the simulation system remains responsive.

[0082] In addition to increasing the frequency of simulation model updates, it is also necessary to optimize data acquisition equipment and data transmission systems to reduce delays and improve system response speed. Monitor the equipment in real time to ensure that the acquisition equipment can collect equipment status data in real time to avoid delays in the data acquisition process.

[0083] Optimize data transmission paths, adopt more efficient communication protocols, and reduce network latency. Enhance data compression and transmission algorithms to reduce latency during data packet transmission.

[0084] Dynamic adjustment module: For the medium real-time update level, the real-time update of the 3D simulation model within a fixed time period is deeply analyzed, and the update frequency of the model is dynamically adjusted according to the analysis results, and timely warning processing is carried out.

[0085] For the medium real-time update level, that is, the update real-time value of the three-dimensional simulation model generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the update real-time values ​​of the three-dimensional simulation model generated within a subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and a corresponding data set is established, the mean and standard deviation of the data set are calculated, and after analyzing them, the update frequency of the model is dynamically adjusted according to the analysis results, and timely early warning processing is performed.

[0086] When the mean of the update real-time values ​​in the data set is greater than or equal to the reference threshold of the update real-time value mean, and the standard deviation of the update real-time value is less than the reference threshold of the update real-time value standard deviation, a third-level warning signal is generated and the update frequency remains unchanged;

[0087] If the mean of the updated real-time values ​​is greater than or equal to the reference threshold of the mean of the updated real-time values, and the standard deviation of the updated real-time values ​​is greater than or equal to the reference threshold of the standard deviation of the updated real-time values, a secondary warning signal is generated at this time, and the update frequency of the simulation model needs to be increased and the update cycle needs to be reduced;

[0088] If the mean of the updated real-time value is less than the reference threshold of the mean of the updated real-time value, and the standard deviation of the updated real-time value is greater than or equal to the reference threshold of the standard deviation of the updated real-time value, a first-level warning signal is generated, the update frequency is increased, and the response time of the data acquisition device and the data transmission system is optimized first;

[0089] If the updated real-time value mean is less than the reference threshold of the updated real-time value mean, and the updated real-time value standard deviation is less than the reference threshold of the updated real-time value standard deviation, no warning signal is generated and no additional adjustment is required.

[0090] It should be noted here that the importance of the first-level warning signal is greater than that of the second-level warning signal, and the importance of the second-level warning signal is greater than that of the third-level warning signal. Relevant personnel can take corresponding handling measures according to different warning signal levels.

[0091] It should be noted that the reference threshold of the mean value of the updated real-time value and the reference threshold of the standard deviation are determined through statistical analysis, experimental verification and the experience of those skilled in the art: the reference threshold of the mean value of the updated real-time value reflects the basic requirement of the system for updating real-time, and is set based on the mean value of historical data, for example, the historical mean value obtained by statistics is 0.75; the reference threshold of the standard deviation of the updated real-time value reflects the stability of the system operation, and is set based on the fluctuation range of historical data, for example, the historical standard deviation obtained by statistics is 0.08, and the final value is 0.1. In the actual system, these two thresholds are dynamically optimized in combination with historical data, experimental test results and real-time requirements to ensure the stability and accuracy of the system operation.

[0092] In this embodiment, multiple modules work together to optimize the real-time update of the substation three-dimensional simulation model. First, the update frequency monitoring module monitors the frequency of device state changes and analyzes its deviation from the update frequency of the three-dimensional simulation system to evaluate whether the update mechanism needs to be adjusted. If adjustment is required, the transmission delay analysis module measures the delay and synchronization error of the data transmission path through time series analysis to evaluate the data transmission delay. Next, the real-time evaluation module comprehensively evaluates the update real-time of the three-dimensional simulation model based on the device state change frequency and transmission delay, and divides it into high, medium and low real-time levels through the real-time classification module. For different levels, the optimization module adjusts the update cycle of the simulation system according to the frequency of device state changes, optimizes the model update frequency of the low real-time level and optimizes the data transmission system. The dynamic adjustment module conducts an in-depth analysis of the medium real-time level, dynamically adjusts the update frequency according to the analysis results, and performs early warning processing in a timely manner to ensure that the simulation model can reflect the actual situation of the substation in a timely manner.

[0093] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0094] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0095] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. The three-dimensional simulation system of substation is characterized by: It includes update frequency monitoring module, transmission delay analysis module, real-time evaluation module, real-time division module, optimization module and dynamic adjustment module; Update frequency monitoring module: through the real-time monitoring system of the substation, the dynamic state change frequency of the substation equipment in several time periods is monitored. The several time periods are divided according to the sampling intervals of the equipment state changes, and the average frequency of the equipment state changes is calculated, and the degree of deviation from the update frequency of the 3D simulation system is analyzed to evaluate whether the update mechanism needs to be adjusted; Transmission delay analysis module: When the adjustment and update mechanism is needed, the data transmission path from the field to the simulation system is monitored, the data transmission time is measured and the synchronization error is recorded. The data transmission delay in different time periods is evaluated by time series analysis; Real-time evaluation module: evaluates the real-time update of the 3D simulation model based on the deviation between the average frequency of device status changes and the update frequency of the 3D simulation system and the data transmission delay in different time periods; Real-time classification module: according to the evaluation results, the update real-time of the 3D simulation model is classified into different levels, namely, high real-time update level, medium real-time update level and low real-time update level; Optimization module: For high real-time update levels, adjust the update cycle of the simulation system according to the frequency of device status changes; for low real-time update levels, increase the model update frequency and optimize the response time of data acquisition devices and transmission systems; Dynamic adjustment module: For the medium real-time update level, the real-time update of the 3D simulation model within a fixed time period is deeply analyzed, and the update frequency of the model is dynamically adjusted according to the analysis results, and timely warning processing is carried out.

2. The three-dimensional simulation system for substation according to claim 1, characterized in that: In the update frequency monitoring module, the frequency synchronization deviation index is generated according to the comparison result between the average frequency of the device state change and the update frequency of the three-dimensional simulation system. The method for obtaining the frequency synchronization deviation index is as follows: From the substation real-time monitoring system, obtain the state change frequency of the equipment in n time periods i, and calculate the average frequency of equipment state changes , records the update frequency of the 3D simulation system in the corresponding time period i ; Assign a weight to each time period i , calculate the absolute deviation for each time period , that is, the difference between the device state change frequency and the simulation system update frequency, and the frequency synchronization deviation index is calculated using the weighted average formula, which is expressed as: ; In the formula, is the frequency synchronization deviation index, and n is the total number of time periods.

3. The three-dimensional simulation system for substation according to claim 2, characterized in that: In the transmission delay analysis module, the data transmission delay in each time period is compared and analyzed by the autoregressive integral moving average model to generate a data transmission delay anomaly index. The method for obtaining the data transmission delay anomaly index is as follows: Collect the substation data transmission delay values ​​within the T time period to form a time series data set ; Stabilize the collected data and determine the parameters p, d, and q of the autoregressive integrated moving average model ARIMA; p indicates how many lagged data are used to predict the current value, d indicates the number of differences required to make the time series stable, and q indicates the impact of current and past error terms on the current value; Use the selected p, d, and q parameters to fit the time series of data transmission delay using the ARIMA model, and the expression is: ; The delay value at the current time point, α is a constant term, is the autoregression coefficient, is the sliding average coefficient, is the white noise term; Use the ARIMA model to predict the data transmission delay in the future period and obtain the predicted value ; Then, calculate the forecast error for each time period , the expression is: ; is the actual delay value, is the predicted value of the ARIMA model; the data transmission delay anomaly index reflects the abnormal degree of the prediction error. The data transmission delay anomaly index is calculated as follows: ; is the data transmission delay anomaly index, The error sequence The standard deviation of .

4. The three-dimensional simulation system for substation according to claim 3, characterized in that: In the real-time evaluation module, the real-time update of the 3D simulation model is evaluated based on the deviation between the average frequency of device status changes and the update frequency of the 3D simulation system and the data transmission delay in different time periods. Specifically: The frequency synchronization deviation index and the data transmission delay anomaly index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model predicts the updated real-time value label of the three-dimensional simulation model with each group of comprehensive feature vectors as the prediction target, and minimizes the sum of prediction errors of the updated real-time value labels of all three-dimensional simulation models as the training target. The machine learning model is trained until the sum of prediction errors converges and the model training is stopped. The updated real-time value of the three-dimensional simulation model is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

5. The three-dimensional simulation system for substation according to claim 4, characterized in that: In the real-time classification module, the update real-time of the three-dimensional simulation model is divided into different levels according to the evaluation results, which are divided into high real-time update level, medium real-time update level and low real-time update level, specifically: The updated real-time value of the three-dimensional simulation model obtained is compared with a gradient standard threshold, wherein the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the updated real-time value of the three-dimensional simulation model is compared with the first standard threshold and the second standard threshold respectively; If the update real-time value of the three-dimensional simulation model is greater than the second standard threshold, it means that the update real-time of the three-dimensional simulation model is high, and a high real-time signal is generated, and the update real-time of the three-dimensional simulation model is classified into a high real-time update level; If the update real-time value of the three-dimensional simulation model is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, it means that the update real-time of the three-dimensional simulation model is general, and a medium real-time signal is generated at this time, and the update real-time of the three-dimensional simulation model is classified as a medium real-time update level; If the update real-time value of the 3D simulation model is less than the first standard threshold, it indicates that the update real-time of the 3D simulation model is low. In this case, a low real-time signal is generated and the update real-time of the 3D simulation model is classified into a low real-time update level.

6. The three-dimensional simulation system for substation according to claim 1, characterized in that: In the dynamic adjustment module, for the medium real-time update level, the real-time update of the 3D simulation model within a fixed time period is deeply analyzed, and the update frequency of the model is dynamically adjusted according to the analysis results, and timely warning processing is carried out, specifically: For the medium real-time update level, that is, the update real-time value of the three-dimensional simulation model generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the update real-time values ​​of the three-dimensional simulation model generated within a subsequent fixed time period that are greater than or equal to the first standard threshold and less than or equal to the second standard threshold are collected, and a corresponding data set is established, the mean and standard deviation of the data set are calculated, and after analyzing them, the update frequency of the model is dynamically adjusted according to the analysis results, and timely early warning processing is performed.

7. The three-dimensional simulation system for substation according to claim 6, characterized in that: If the mean of the update real-time values ​​in the data set is greater than or equal to the reference threshold of the update real-time value mean, and the standard deviation of the update real-time value is less than the reference threshold of the update real-time value standard deviation, a third-level warning signal is generated and the update frequency remains unchanged; If the mean of the updated real-time values ​​is greater than or equal to the reference threshold of the mean of the updated real-time values, and the standard deviation of the updated real-time values ​​is greater than or equal to the reference threshold of the standard deviation of the updated real-time values, a secondary warning signal is generated at this time, and the update frequency of the simulation model needs to be increased and the update cycle needs to be reduced; If the mean of the updated real-time value is less than the reference threshold of the mean of the updated real-time value, and the standard deviation of the updated real-time value is greater than or equal to the reference threshold of the standard deviation of the updated real-time value, a first-level warning signal is generated, the update frequency is increased, and the response time of the data acquisition device and the data transmission system is optimized first; If the updated real-time value mean is less than the reference threshold of the updated real-time value mean, and the updated real-time value standard deviation is less than the reference threshold of the updated real-time value standard deviation, no warning signal is generated and no additional adjustment is required.

Images