Power instability monitoring and early warning method based on deep learning

Abstract

The invention discloses an electric power instability monitoring and early warning method based on deep learning, and the method comprises the steps: recognizing an electric power countercurrent event and a potential countercurrent instability event according to the electric power flow data of an electric power system; constructing a power instability mode identification model, and identifying an instability mode and an instability event risk level of a potential inverse instability event; based on the countercurrent influence factor of the node, identifying a power grid key node with countercurrent impact load overrun; according to the load deviation value of the power grid key node with the countercurrent impact load exceeding the limit, the load capacity needing to be transferred is determined, and a load regulation and control scheme is formulated; on the basis of a power instability mode recognition model, predicting a time point when an instability precursor event is converted into a reverse instability event; evaluating the stability of the power grid system after the load regulation and control scheme is implemented, and optimizing regulation and control parameters based on regulation and control feedback data. According to the method, the monitoring, early warning and dynamic regulation and control capabilities of the power system on the countercurrent and instability events are remarkably improved, and the safe and stable operation of the power grid is effectively guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of power monitoring, and in particular to a power instability monitoring and early warning method based on deep learning. Background Art

[0002] In modern power systems, the stability of power flow is crucial. Power flow refers to the flow process of power from the power generation source to the load end, and the stability of current flow direction, frequency and voltage are key indicators to ensure the safe operation of the power grid. However, in actual operation, abnormal reverse flow may occur in the power system sometimes, that is, the direction of current flow is reversed, resulting in a large reverse flow in a short period of time, accompanied by fluctuations in frequency, phase and voltage. Under certain conditions, such reverse flow events may further develop into reverse flow instability events, that is, the reverse flow phenomenon is not alleviated, resulting in continuous instability of the power system, and parameters such as frequency and phase deviate from normal levels, seriously affecting the safety of system operation. Reverse flow instability events are particularly threatening the security of key nodes of the power grid. If not controlled, they may cause equipment damage, overload of key nodes, and even cause large-scale power outages. Such events are different from common power instability events. The former is evolved from the reverse flow phenomenon, while the latter is mostly caused by sudden factors such as load surge or system failure. In a complex power grid environment, reverse flow events and instability events are easily confused, making power system monitoring challenging. Existing power system monitoring mostly relies on setting thresholds and static analysis methods, and judges the system status through fixed thresholds such as current fluctuation amplitude and frequency deviation. However, reverse flow events and instability events are affected by many factors, and traditional threshold methods are difficult to accurately distinguish between the two. Under complex power grid conditions, fixed thresholds often cause reverse flow events to be mistaken for instability precursors, resulting in false alarms and missed alarms, affecting the response speed of the power grid and the effectiveness of emergency response. In addition, existing methods also have limitations in risk identification and load regulation of power reverse flow events. The lack of dynamic load regulation means for key nodes makes it difficult to adjust the load in a timely manner during reverse flow events, and the key nodes are prone to overload, increasing the risk of system instability. Instability events usually go through the stages of instability precursors, reverse flow instability and complete instability, and traditional monitoring is difficult to identify potential instability trends in the instability precursor stage, which makes the power system passively respond when the event worsens, lacking the ability to warn in advance. Especially under extreme conditions, the reverse flow fluctuation frequency will have a nonlinear resonance effect with the load change frequency, causing the load fluctuation amplitude of the node to increase sharply, and the reverse flow phenomenon may quickly evolve into an instability event. Traditional monitoring methods are difficult to respond in time. Therefore, there is an urgent need for a power instability monitoring and early warning method based on intelligent technology to accurately identify power reverse flow events and instability events, provide effective early warnings, and thus improve the stability and emergency response capabilities of the power system. Summary of the invention

[0003] To solve the problems existing in the above-mentioned prior art, the present invention provides a method for monitoring and early warning of power instability based on deep learning, which mainly includes:

[0004] Based on the power flow data of the power system, identify the period when the abnormal fluctuation amplitude exceeds the limit, determine the power reverse flow event, and identify the potential reverse flow instability event based on the frequency deviation amplitude, deviation recovery rate and instantaneous change rate of the power reverse flow event;

[0005] Based on the key parameters of historical power instability events, a power instability pattern recognition model is constructed to identify the instability patterns of potential reverse current instability events and the risk level of reverse current instability events where the instability patterns are power instability;

[0006] Based on the real-time load fluctuation data of the key nodes of the power grid during the reverse flow instability event and the reverse flow influencing factors of the nodes, the key nodes of the power grid with reverse flow impact load exceeding the limit are identified;

[0007] Obtain real-time load data and historical load fluctuation patterns of key nodes of the power grid where reverse flow impact load exceeds the limit, calculate the load deviation value of each node, determine the amount of load that needs to be transferred to each node, and formulate a load control plan;

[0008] Based on the historical key parameters of potential reverse current instability events where the instability mode is a precursor to instability, the key parameters of the instability precursor events in the future preset time period are predicted, and combined with the power instability pattern recognition model, the time point when the instability precursor event turns into a reverse current instability event is predicted, and a damping coefficient dynamic adjustment plan and a resonance early warning plan are implemented;

[0009] Obtain the load fluctuation response of key nodes in the power grid, evaluate the stability of the power grid system after implementing the load control scheme, damping coefficient dynamic adjustment scheme and resonance early warning scheme, and optimize the control parameters based on the control feedback data.

[0010] Further, the method of identifying the time period when the abnormal fluctuation amplitude exceeds the limit according to the power flow data of the power system, determining the power reverse flow event, and identifying the potential reverse flow instability event based on the frequency deviation amplitude, deviation recovery rate and instantaneous change rate of the power reverse flow event includes:

[0011] According to the power data interface of the power system, the power flow data is obtained, including current direction, voltage fluctuation and frequency change; the data preprocessing algorithm is used to clean the power flow data, remove noise and abnormal points, and store the power flow data in the data cache in timestamp order; the short-time Fourier transform algorithm is used to convert the current and voltage data into frequency domain and time domain signals, and the power characteristic parameters are extracted, including the change amplitude of the current direction, the change value of the voltage fluctuation amplitude and the frequency fluctuation rate; according to the power characteristic parameters, the isolation forest algorithm is used to identify the time period when the abnormal fluctuation amplitude exceeds the limit, and the power reverse flow event is determined; according to the power flow data of the power reverse flow event, the frequency deviation amplitude and deviation recovery rate of the power reverse flow event are statistically calculated, and the instantaneous change rate of the frequency deviation is calculated using the sliding average method; according to the frequency deviation amplitude, deviation recovery rate and instantaneous change rate of the power reverse flow event, the decision tree algorithm is used for model training, and a potential reverse flow instability event identification model is constructed to identify potential reverse flow instability events.

[0012] Furthermore, the power instability pattern recognition model is constructed based on the key parameters of the historical power instability events to identify the instability pattern of potential reverse flow instability events and the risk level of reverse flow instability events whose instability pattern is power instability, including:

[0013] Through the power instability feature database, the key parameters of historical power instability events are obtained, including the amplitude, duration and frequency characteristics of current fluctuations, and the stages of power instability events and the risk levels of power instability events are marked. The random forest algorithm is used for model training to build a power instability pattern recognition model. The stages of power instability events include instability precursors and power instability. The risk levels of power instability events include normal, warning and dangerous. The instability modes include normal reverse flow, instability precursors and power instability. According to the key parameters of potential reverse flow instability events, the power instability pattern recognition model is used to identify the instability mode of potential reverse flow instability events, and identify the risk level of reverse flow instability events with the instability mode as power instability. Potential reverse flow instability events with the instability mode as instability precursors are marked as instability precursor events, and potential reverse flow instability events with the instability mode as power instability are marked as reverse flow instability events. The reverse flow instability events with risk level labels are transmitted to the power instability event monitoring database, and a multi-level early warning classification mechanism is used to determine the response level of the reverse flow instability events.

[0014] Further, the real-time load fluctuation data of the key nodes of the power grid according to the reverse flow instability event, combined with the reverse flow impact factor of the node, identifies the key nodes of the power grid where the reverse flow impact load exceeds the limit, including:

[0015] Obtain real-time load fluctuation data of key nodes of the power grid during reverse flow instability events. Key nodes of the power grid include but are not limited to load concentration area connection points, trunk line nodes, power generation hub nodes, regional hub nodes and backup power supply nodes. Load fluctuation data include the load change rate, fluctuation amplitude, frequency and duration of the nodes; Based on the load fluctuation data of key nodes of the power grid, combined with the reverse flow influencing factors of the nodes, including the current reverse ratio and the phase angle of load change, use the time-varying load reverse resonance factor evaluation formula Calculate the time-varying load reverse resonance factor Q of the key nodes of the power grid under the impact of reverse flow, where P1 is the benchmark load of the key nodes of the power grid, R is the current reverse ratio when the reverse flow occurs, indicating the reverse flow intensity of the current, θ is the phase angle of the load change, f is the reverse flow fluctuation frequency, g is the load change frequency, ζ is the damping coefficient, indicating the attenuation capacity of the power system to resonance, which is obtained by fitting historical data; determine the load fluctuation amplitude of the key nodes of the power grid under the impact of reverse flow according to the time-varying load reverse resonance factor and the benchmark load of the key nodes of the power grid; identify the key nodes of the power grid with excessive reverse flow impact load according to the preset node load fluctuation tolerance threshold and the calculated load fluctuation amplitude of the key nodes of the power grid under the impact of reverse flow; monitor the reverse flow fluctuation frequency, load change frequency and the rising rate of the variable load reverse resonance factor in real time, and formulate a dynamic adjustment plan for the damping coefficient and a resonance early warning plan.

[0016] Among them, real-time monitoring of the reverse flow fluctuation frequency, load change frequency and the rising rate of the variable load reverse resonance factor is carried out to formulate a dynamic adjustment plan for the damping coefficient and a resonance early warning plan, including:

[0017] Real-time monitoring of the reverse flow fluctuation frequency f and load change frequency g. If the frequency ratio is detected If it is greater than the preset ratio threshold, a dynamic adjustment plan for the damping coefficient is formulated and implemented, and the damping coefficient ζ is dynamically adjusted to the preset critical damping coefficient ζ0; the rising rate of the time-varying load reverse resonance factor is calculated and recorded in real time. If the rising rate exceeds the preset rate threshold, a resonance early warning plan is formulated and implemented, including controlling the load flow and transferring part of the load of the current node to the adjacent node or backup power supply node whose load is lower than the preset load threshold by limiting the load at the key nodes of the power grid or cutting off the designated nodes.

[0018] Furthermore, the real-time load data and historical load fluctuation patterns of the key nodes of the power grid where the reverse flow impact load exceeds the limit are obtained, the load deviation value of each node is calculated, the load amount that needs to be transferred or adjusted at each node is determined, and a load control plan is formulated, including:

[0019] Acquire real-time load data of key nodes of the power grid where the reverse impact load exceeds the limit, including load fluctuation amplitude, change rate and fluctuation frequency; extract historical load fluctuation patterns of key nodes of the power grid where the reverse impact load exceeds the limit through the power instability feature database, including load peak, average load level and fluctuation period; compare the real-time load data with the historical data, calculate the load deviation value of each node, and obtain the real-time-historical load deviation characteristics of the key nodes of the power grid; use the adaptive control algorithm to dynamically adjust the control parameters according to the real-time-historical load deviation characteristics of the key nodes of the power grid, determine the amount of load that needs to be transferred at each node, and obtain the adaptive control parameter set; formulate a load control plan based on the adaptive control parameter set to transfer the load of key nodes of the power grid where the reverse impact load exceeds the limit, and give priority to allocating the excess load to adjacent nodes or backup power supply nodes whose load is lower than the preset load threshold.

[0020] Furthermore, the historical key parameters of the potential reverse current instability event based on the instability mode as the instability precursor are predicted, the key parameters of the instability precursor event in the future preset time period are predicted, and the time point when the instability precursor event turns into the reverse current instability event is predicted in combination with the power instability mode recognition model, and the damping coefficient dynamic adjustment scheme and the resonance early warning scheme are implemented, including:

[0021] Through the power instability characteristic database, the historical key parameters of the instability precursor events are obtained and arranged in time series to construct the time series data of the historical key parameters of the instability precursor events; based on the time series data of the historical key parameters of the instability precursor events, the long short-term memory network is used to train the model to predict the key parameters of the instability precursor events in the future preset time period; based on the prediction results of the key parameters of the instability precursor events in the future preset time period, combined with the power instability pattern recognition model, the time point when the instability precursor event turns into the reverse flow instability event and the risk level of the reverse flow instability event are predicted; according to the predicted time point when the instability precursor event turns into the reverse flow instability event, a reverse flow instability event warning is sent, and a damping coefficient dynamic adjustment plan and a resonance warning plan are implemented.

[0022] Furthermore, the load fluctuation response of key nodes of the power grid is obtained, the stability of the power grid system after the load control scheme, the damping coefficient dynamic adjustment scheme and the resonance early warning scheme are evaluated, and the control parameters are optimized based on the control feedback data, including:

[0023] Continuously monitor the real-time load data of the power system after the implementation of the load control scheme, the damping coefficient dynamic adjustment scheme and the resonance warning scheme, obtain the load fluctuation response and dynamic change data of the damping coefficient of the key nodes of the power grid, and evaluate the stability of the power grid system after the implementation of each scheme; record the feedback data in the load control, damping coefficient adjustment and resonance warning response, including load change, the ratio of the reverse flow fluctuation frequency to the load change frequency and the resonance warning effect, and judge the power instability mitigation effect of each scheme; based on the power instability mitigation effect, optimize the load control scheme, the damping coefficient dynamic adjustment scheme and the resonance warning scheme, adjust the load distribution amount, control direction and critical damping coefficient; re-verify the optimized load control scheme, damping coefficient dynamic adjustment scheme and resonance warning scheme, and record the load adjustment amount, critical damping coefficient, warning execution time and load distribution direction of each key node of the power grid. If the power instability mitigation effect of each scheme meets the expectations, the optimized load control scheme, damping coefficient dynamic adjustment scheme and resonance warning scheme will be stored in the power system control database.

[0024] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0025] The present invention provides a method for monitoring and early warning of power instability based on deep learning. By real-time monitoring of power flow data, the present invention analyzes frequency deviation, recovery rate and instantaneous change rate, can accurately identify abnormal reverse flow events, and effectively distinguish between instability precursors and reverse flow instability, significantly reducing false alarms and missed reports. Based on historical data analysis, the present invention can identify different types of instability event patterns and evaluate their risk levels, helping the power grid to take more targeted early warning and response measures for different risk levels. By dynamically regulating the load of key nodes and quickly responding to the impact of reverse flow instability on nodes, the risk of overload of key nodes is avoided and the stability of the power grid is enhanced. The prediction and early warning function of the present invention enables the precursor event of instability to be intervened in time before it evolves into reverse flow instability, effectively preventing the further deterioration of instability events. The present invention significantly improves the monitoring, early warning and dynamic regulation capabilities of the power system for reverse flow and instability events, and effectively ensures the safe and stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a method for monitoring and early warning of power instability based on deep learning of the present invention;

[0027] Figure 2 A schematic diagram of a power instability monitoring and early warning method based on deep learning of the present invention;

[0028] Figure 3 This is another schematic diagram of a power instability monitoring and early warning method based on deep learning of the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0030] like Figure 1-3 In this embodiment, a power instability monitoring and early warning method based on deep learning may specifically include:

[0031] Step S101, based on the power flow data of the power system, identify the time period when the abnormal fluctuation amplitude exceeds the limit, determine the power reverse flow event, and identify the potential reverse flow instability event based on the frequency deviation amplitude, deviation recovery rate and instantaneous change rate of the power reverse flow event.

[0032] According to the power data interface of the power system, power flow data is obtained, including current flow direction, voltage fluctuation and frequency change. The data preprocessing algorithm is used to clean the power flow data, remove noise and abnormal points, and store the power flow data in the data cache in timestamp order. The short-time Fourier transform algorithm is used to convert the current and voltage data into frequency domain and time domain signals, and the power characteristic parameters are extracted, including the change amplitude of the current flow direction, the change value of the voltage fluctuation amplitude and the frequency fluctuation rate. According to the power characteristic parameters, the isolation forest algorithm is used to identify the time period when the abnormal fluctuation amplitude exceeds the limit, and the power reverse flow event is determined. According to the power flow data of the power reverse flow event, the frequency deviation amplitude and deviation recovery rate of the power reverse flow event are counted, and the instantaneous change rate of the frequency deviation is calculated using the sliding average method. According to the frequency deviation amplitude, deviation recovery rate and instantaneous change rate of the power reverse flow event, the decision tree algorithm is used for model training, and a potential reverse flow instability event identification model is constructed to identify potential reverse flow instability events.

[0033] For example, in an electric power system, the power flow data acquired in real time through the power data interface include that the current flow direction changes from 100A to 125A in a short period of time, resulting in a flow direction change amplitude of 25A, the voltage rises from 220V to 230V during this period, resulting in a voltage fluctuation of 10V, and the frequency fluctuates slightly from 50Hz to 49.9Hz, with a frequency deviation of 0.1Hz. To ensure the accuracy of the data, the data is first cleaned to remove noise and abnormal points, and the cleaned data is stored in the data cache in timestamp order. The short-time Fourier transform is used to convert the current and voltage data from the time domain to the frequency domain, and the power characteristic parameters are extracted, including the current flow direction change amplitude of 25A, the voltage fluctuation amplitude of 10V, and the frequency fluctuation rate of 0.02Hz / s. The isolation forest algorithm is used to detect abnormal fluctuations. If the threshold of the power system is set to a current flow change amplitude of no more than 20A, a voltage fluctuation of no more than 8V, and a frequency fluctuation rate of no more than 0.015Hz / s, the detection results in this time period show that the current flow change amplitude of 25A and the frequency fluctuation rate of 0.02Hz / s both exceed the threshold, so this period is determined to be a power reverse flow event. After identifying the reverse flow event, the frequency deviation amplitude of the event is further statistically 0.1Hz, and the deviation recovery rate is 0.05Hz per minute. By using the sliding average method, with a period of 5s, the instantaneous change rate is calculated to be 0.02Hz / s. Using the frequency deviation amplitude, deviation recovery rate and instantaneous change rate of the power reverse flow event, the decision tree algorithm is used for training and model construction to identify the power reverse flow event as a potential reverse flow instability event.

[0034] Step S102, based on key parameters of historical power instability events, construct a power instability pattern recognition model to identify the instability pattern of potential reverse current instability events and the risk level of reverse current instability events whose instability pattern is power instability.

[0035] Through the power instability feature database, the key parameters of historical power instability events are obtained, including the amplitude, duration and frequency characteristics of current fluctuations, and the power instability event stages and power instability event risk levels are marked. The random forest algorithm is used for model training to construct a power instability pattern recognition model. The power instability event stages include instability precursors and power instability. The power instability event risk levels include normal, warning, and dangerous. The instability modes include normal reverse flow, instability precursors, and power instability. According to the key parameters of potential reverse flow instability events, the power instability pattern recognition model is used to identify the instability mode of potential reverse flow instability events, and identify the risk level of reverse flow instability events with instability modes as power instability. Potential reverse flow instability events with instability modes as instability precursors are marked as instability precursor events, and potential reverse flow instability events with instability modes as power instability are marked as reverse flow instability events. Reverse flow instability events with risk level labels are transmitted to the power instability event monitoring database, and a multi-level early warning classification mechanism is used to determine the response level of reverse flow instability events.

[0036] Exemplarily, in the power instability feature database, the key parameters of multiple historical power instability events are obtained, among which the current fluctuation amplitude is 35A, the duration is 20s, and the frequency characteristics show that the frequency drops briefly from 50Hz to 49.3Hz during the event. The event is marked as the power instability stage, and the risk level is warning. Event 2 is that the current fluctuation amplitude is 42A, the duration is 25s, and the frequency drops from 50Hz to 49.0Hz. This event is identified as the power instability stage, and because its frequency fluctuation is large and lasts longer, it is rated as a dangerous risk level. Event 3 is that the current fluctuation amplitude is 30A, the duration is 18s, and the frequency fluctuates between 50Hz and 49.5Hz. Although the frequency fluctuation is controlled, the fluctuation amplitude and duration reach the standard of the instability stage, so it is marked as the power instability stage, and the risk level is ordinary. Based on a large number of similar events, the random forest algorithm is trained to construct a power instability pattern recognition model to identify the instability mode of potential reverse current instability events. If the key parameters of a potential reverse current instability event are a current fluctuation amplitude of 30A, a duration of 15s, and a frequency drop to 49.4Hz, the power instability pattern recognition model identifies it as an instability precursor mode, and the potential reverse current instability event is an instability precursor time, so the risk level will not be marked. If the key parameters of a reverse current instability event are a current fluctuation amplitude of 40A, a duration of 25s, and a frequency drop to 49.2Hz, the power instability pattern recognition model determines that it has entered the power instability stage, and then marks the event as a dangerous risk level. Potential reverse current instability events with an instability mode as an instability precursor are marked as instability precursor events, and potential reverse current instability events with an instability mode as power instability are marked as reverse current instability events. For events that are in the power instability stage and marked with risk levels, their classification labels with risk levels are stored in the power instability event monitoring database. According to the dangerous risk level of the event, the three-level early warning mechanism is triggered to remind power management personnel to take immediate measures to deal with the event to ensure the stability of the power system and prevent the situation from further deteriorating.

[0037] Step S103, identifying the key nodes of the power grid where the reverse flow impact load exceeds the limit according to the real-time load fluctuation data of the key nodes of the power grid in the reverse flow instability event and the reverse flow impact factor of the node.

[0038] Obtain real-time load fluctuation data of key nodes of the power grid during reverse flow instability events. Key nodes of the power grid include but are not limited to load concentration area connection points, trunk line nodes, power generation hub nodes, regional hub nodes and backup power supply nodes. Load fluctuation data include the load change rate, fluctuation amplitude, frequency and duration of the nodes. Based on the load fluctuation data of key nodes of the power grid, combined with the reverse flow influencing factors of the nodes, including the current reverse ratio and the phase angle of load change, use the time-varying load reverse resonance factor evaluation formula Calculate the time-varying load reverse resonance factor Q of the key nodes of the power grid under the impact of reverse flow, where P1 is the benchmark load of the key nodes of the power grid, R is the current reverse ratio when the reverse flow occurs, indicating the reverse flow intensity of the current, θ is the phase angle of the load change, f is the reverse flow fluctuation frequency, g is the load change frequency, and ζ is the damping coefficient, indicating the attenuation capacity of the power system to resonance, which is obtained by fitting historical data. According to the time-varying load reverse resonance factor and the benchmark load of the key nodes of the power grid, determine the load fluctuation amplitude of the key nodes of the power grid under the impact of reverse flow. According to the preset node load fluctuation tolerance threshold and the calculated load fluctuation amplitude of the key nodes of the power grid under the impact of reverse flow, identify the key nodes of the power grid with excessive reverse flow impact load. Real-time monitoring of the reverse flow fluctuation frequency, load change frequency and the rising rate of the variable load reverse resonance factor, formulate a dynamic adjustment plan for the damping coefficient and a resonance early warning plan.

[0039] For example, in an electric power system, the real-time load fluctuation data of a key node of the power grid in a reverse flow instability event is obtained. The key node is located in a load concentration area, and the recorded load fluctuation data includes a load change rate of 20kW / s, a fluctuation amplitude of 80kW, a frequency of 49Hz, and a duration of 40s. Among them, the key nodes of the power grid include connection points in load concentration areas, trunk line nodes, power generation hub nodes, regional hub nodes, and backup power supply nodes, etc., and the benchmark load P1 of the key node is obtained to be 300kW, and the phase angle θ of the load change is 45°. In some reverse flow instability events, the current reverse ratio R and the reverse flow fluctuation frequency f will produce a nonlinear resonance effect with the load change frequency g, causing the load fluctuation amplitude of the node to increase sharply, further increasing the risk of the key node. According to the reverse flow impact factor of the key node of the power grid, the reverse flow impact load fluctuation amplitude formula is used. The time-varying load reverse resonance factor Q of the key nodes of the power grid under the impact of reverse flow is calculated, where the current reverse ratio R is 1.1, the fluctuation frequency f is 49Hz, the phase angle θ of the load change is 45°, that is, sin(θ)=0.707, the load change frequency g is 50Hz, the damping coefficient ζ is 0.05 obtained by fitting historical data, and the calculated Q is ≈1.95. According to the time-varying load reverse resonance factor Q and the node's benchmark load P1, the amplified load fluctuation amplitude of the node under the impact of reverse flow is determined to be 585kW. If the preset load fluctuation tolerance threshold of the power grid is 500kW, the fluctuation amplitude of 585kW has exceeded the tolerance range, and the risk of overload of reverse flow impact at the key nodes of the power grid is identified. This result triggers the early warning mechanism of the power system, prompting relevant departments to take timely control measures to reduce load pressure and ensure the stability of the power system. To further control risks, the system developed a dynamic adjustment plan for the damping coefficient and a resonance early warning plan, and began to monitor the rising rate of the reverse flow fluctuation frequency f, load change frequency g and resonance factor Q in real time to alleviate load fluctuations and prevent the resonance effect from spreading to other nodes in the power grid.

[0040] Among them, the countercurrent fluctuation frequency, load change frequency and the rising rate of the variable load reverse resonance factor are monitored in real time, and a dynamic adjustment plan for the damping coefficient and a resonance early warning plan are formulated.

[0041] Real-time monitoring of the reverse flow fluctuation frequency f and load change frequency g. If the frequency ratio is detected If the ratio is greater than the preset ratio threshold, a dynamic damping coefficient adjustment plan is formulated and implemented to dynamically adjust the damping coefficient ζ to the preset critical damping coefficient ζ0. The rising rate of the time-varying load reverse resonance factor is calculated and recorded in real time. If the rising rate exceeds the preset rate threshold, a resonance early warning plan is formulated and implemented, including limiting the load at key nodes of the power grid or cutting off designated nodes to control the load flow and transfer part of the load of the current node to adjacent nodes or backup power supply nodes whose load is lower than the preset load threshold.

[0042] For example, in the power system, a reverse flow instability event is detected in real time at a key node of the power grid, and the reverse flow fluctuation frequency and load change frequency of the node are continuously recorded during the process. If the reverse flow fluctuation frequency f is 49.2Hz and the load change frequency g is 50Hz. The preset frequency ratio threshold is 0.98, and the frequency ratio at this time is is 0.984, which has exceeded the preset ratio threshold. After detecting that the ratio exceeds the threshold, the dynamic adjustment scheme of the damping coefficient is immediately started, and the damping coefficient is gradually increased from the original value to the preset critical damping coefficient of 0.15 to suppress the resonance effect of the system. This adjustment can effectively slow down the amplification effect of reverse flow instability on the load fluctuation amplitude and help the power system to remain within a controllable range. At the same time, the rising rate of the time-varying load reverse resonance factor is calculated and recorded in real time. If the current rising rate is 0.05 / s, and the preset rate threshold of the system is 0.04 / s. This shows that the growth rate of the time-varying load reverse resonance factor is too fast, which may lead to the risk of load overload. Therefore, a resonance early warning scheme is immediately formulated and implemented. The resonance early warning scheme includes intervention through load limitation and load transfer measures. First, the load of the key node is limited and the load flow is controlled below 400kW to avoid further fluctuation amplification. Then, the system transfers part of the load of the current node, such as 50kW, to the adjacent backup power supply node or other nodes with loads below the preset threshold to ensure that other nodes in the power grid are not affected by the conduction of the resonance effect.

[0043] Step S104, obtaining real-time load data and historical load fluctuation patterns of key nodes of the power grid where the reverse flow impact load exceeds the limit, calculating the load deviation value of each node, determining the load amount that needs to be transferred to each node, and formulating a load control plan.

[0044] Obtain the real-time load data of the key nodes of the power grid where the reverse impact load exceeds the limit, including the load fluctuation amplitude, change rate and fluctuation frequency. Through the power instability feature database, extract the historical load fluctuation pattern of the key nodes of the power grid where the reverse impact load exceeds the limit, including the load peak, average load level and fluctuation period. Compare the real-time load data with the historical data, calculate the load deviation value of each node, and obtain the real-time-historical load deviation characteristics of the key nodes of the power grid. Use the adaptive control algorithm to dynamically adjust the control parameters according to the real-time-historical load deviation characteristics of the key nodes of the power grid, determine the amount of load that needs to be transferred at each node, and obtain the adaptive control parameter set. According to the adaptive control parameter set, formulate a load control plan to transfer the load of the key nodes of the power grid where the reverse impact load exceeds the limit, and give priority to allocating the excess load to the neighboring nodes or backup power supply nodes whose load is lower than the preset load threshold.

[0045] For example, in the power grid system, a critical node of a power grid is overloaded due to a reverse flow shock. Real-time data shows that the load fluctuation amplitude of the node is 380kW, the change rate is 12kW / s, and the fluctuation frequency is 48Hz. Through the power instability feature database, the historical load fluctuation pattern of the node is extracted, which records the load peak of 350kW, the average load level of 320kW, and the fluctuation period of 60s. The real-time data is compared with the historical data, and the load deviation value of the node is calculated to be 30kW by subtracting the historical load peak of 350kW from the real-time load fluctuation amplitude of 380kW, and the real-time-historical load deviation characteristics of the node are obtained. Due to the large load deviation, the adaptive control algorithm is started, and the control parameters are dynamically adjusted according to the degree and change rate of the load deviation, and the load amount that needs to be transferred to the node is calculated to be 30kW. According to the adaptive control parameter set, a load control plan is formulated to preferentially distribute the 30kW overload to the neighboring nodes or backup power supply nodes whose load is lower than the preset threshold, such as transferring 15kW of load to the neighboring node M with lower load, and transferring the remaining 15kW to the backup power supply node N. This control plan effectively reduces the load pressure of the key node by reasonably distributing the overload, and enhances the stability and security of the power grid.

[0046] Step S105, based on the historical key parameters of the potential reverse current instability event whose instability mode is a precursor to instability, predict the key parameters of the instability precursor event in the future preset time period, and combine with the power instability pattern recognition model to predict the time point when the instability precursor event turns into a reverse current instability event, and implement the damping coefficient dynamic adjustment plan and the resonance early warning plan.

[0047] Through the power instability feature database, the historical key parameters of the instability precursor events are obtained and arranged in time series to construct the time series data of the historical key parameters of the instability precursor events. According to the time series data of the historical key parameters of the instability precursor events, the long short-term memory network is used for model training to predict the key parameters of the instability precursor events in the future preset time period. According to the prediction results of the key parameters of the instability precursor events in the future preset time period, combined with the power instability pattern recognition model, the time point when the instability precursor event turns into the reverse flow instability event and the risk level of the reverse flow instability event are predicted. According to the predicted time point when the instability precursor event turns into the reverse flow instability event, the reverse flow instability event warning is sent, and the damping coefficient dynamic adjustment plan and the resonance warning plan are implemented.

[0048] For example, in the power instability feature database, the historical data of an instability precursor event is obtained. The parameters of the past three instability precursor events are that the current fluctuation amplitude is 15A, 20A and 25A, the event duration is 10s, 15s and 20s respectively, and the frequency characteristics show that the frequency drops from 50Hz to 49.7Hz, 49.5Hz and 49.3Hz respectively. These data are arranged in chronological order to construct the time series data of the instability precursor event of the node. The long short-term memory network model is used to train these time series data and predict the key parameters of the instability precursor event that may occur in the next 10 minutes. According to the prediction results, the current fluctuation amplitude is expected to reach 30A, the duration is expected to be extended to 25s, and the frequency may drop to 49.2Hz. Combined with the analysis of the power instability pattern recognition model, the prediction results of the long short-term memory network model show that the instability precursor event of the node will be transformed into a reverse flow instability event after 8 minutes, and the risk level of the event is dangerous. According to this prediction, a reverse flow instability event warning is immediately sent to indicate that a reverse flow instability event may occur at the node in the next 8 minutes. In order to reduce the load and prevent the instability from worsening, the dynamic adjustment scheme of the damping coefficient and the resonance early warning scheme are started in advance, and the real-time monitoring of the reverse flow fluctuation frequency, load change frequency and the rising rate of the resonance factor is started to alleviate the load fluctuation and prevent the resonance effect from spreading to other nodes of the power grid.

[0049] Step S106, obtaining the load fluctuation response of the key nodes of the power grid, evaluating the stability of the power grid system after implementing the load control scheme, the damping coefficient dynamic adjustment scheme and the resonance early warning scheme, and optimizing the control parameters based on the control feedback data.

[0050] Continuously monitor the real-time load data of the power system after the implementation of the load control scheme, damping coefficient dynamic adjustment scheme and resonance warning scheme, obtain the load fluctuation response and dynamic change data of the damping coefficient of the key nodes of the power grid, and evaluate the stability of the power grid system after the implementation of each scheme. Record the control feedback data in the load control, damping coefficient adjustment and resonance warning response, including load change, the ratio of reverse flow fluctuation frequency to load change frequency and the resonance warning effect, and judge the power instability mitigation effect of each scheme. Based on the power instability mitigation effect, optimize the load control scheme, damping coefficient dynamic adjustment scheme and resonance warning scheme, and adjust the load distribution amount, control direction and critical damping coefficient. Re-verify the optimized load control scheme, damping coefficient dynamic adjustment scheme and resonance warning scheme, and record the load adjustment amount, critical damping coefficient, warning execution time and load distribution direction of each key node of the power grid. If the power instability mitigation effect of each scheme meets the expectations, the optimized load control scheme, damping coefficient dynamic adjustment scheme and resonance warning scheme will be stored in the power system control database.

[0051] For example, during the operation of the power system, a load control scheme, a dynamic adjustment scheme for the damping coefficient, and a resonance warning scheme were implemented for a key node of a power grid in a load-concentrated area to mitigate the risk of load fluctuations caused by reverse flow instability at the node. Real-time monitoring data showed that the initial load fluctuation amplitude of the node was 75kW, the load change rate was 20kW / s, the reverse flow fluctuation frequency was 49Hz, and the load change frequency was 50Hz. The frequency ratio was 0.98, reaching the preset ratio threshold. Therefore, the dynamic adjustment scheme for the damping coefficient was immediately implemented, and the damping coefficient of the node was directly set to the preset critical damping coefficient of 0.1 to suppress the resonance effect. After the implementation of the scheme, the load fluctuation response data was continuously monitored and recorded. It was observed that the load fluctuation amplitude dropped to 55kW, indicating that the load control scheme achieved a certain mitigation effect. At the same time, the resonance warning scheme effectively controlled the further spread of load fluctuations and ensured the stability of the system. In the control feedback data, the load adjustment of the node is recorded as 25kW, and part of the load is transferred to the backup power supply node with lower load. The damping coefficient adjustment feedback shows that the critical damping coefficient has been successfully set to 0.1, ensuring that the system has good attenuation capability. The feedback of the resonance warning scheme records that the warning execution time is 12 minutes. The power system effectively achieves fluctuation mitigation by limiting the load flow of key nodes and dispersing the load. Based on the above feedback data, the load control scheme, damping coefficient dynamic adjustment scheme and resonance warning scheme are optimized. The optimized scheme adjusts the load distribution to 20kW, replans the control direction to balance the load distribution, and the critical damping coefficient is verified to be set to 0.09 to enhance the stability of the system in subsequent similar events. Re-verify the optimized schemes. If each scheme achieves the expected power instability mitigation effect, the optimized load control scheme, damping coefficient dynamic adjustment scheme and resonance warning scheme and related data will be stored in the power system control database as a reference for subsequent event response. The relevant data include the load adjustment of key nodes, the set critical damping coefficient, the warning execution time and the load distribution direction.

[0052] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the concept of the present application. For example, the above features are replaced with the technical features with similar functions disclosed in the present application (but not limited to) to form a technical solution.

Claims

1. A power instability monitoring and early warning method based on deep learning, characterized in that: The method comprises: Based on the power flow data of the power system, identify the period when the abnormal fluctuation amplitude exceeds the limit, determine the power reverse flow event, and identify the potential reverse flow instability event based on the frequency deviation amplitude, deviation recovery rate and instantaneous change rate of the power reverse flow event; Based on the key parameters of historical power instability events, a power instability pattern recognition model is constructed to identify the instability patterns of potential reverse current instability events and the risk level of reverse current instability events where the instability patterns are power instability; Based on the real-time load fluctuation data of the key nodes of the power grid during the reverse flow instability event and the reverse flow influencing factors of the nodes, the key nodes of the power grid with reverse flow impact load exceeding the limit are identified; Obtain real-time load data and historical load fluctuation patterns of key nodes of the power grid where reverse flow impact load exceeds the limit, calculate the load deviation value of each node, determine the amount of load that needs to be transferred to each node, and formulate a load control plan; Based on the historical key parameters of potential reverse current instability events where the instability mode is a precursor to instability, the key parameters of the instability precursor events in the future preset time period are predicted, and combined with the power instability pattern recognition model, the time point when the instability precursor event turns into a reverse current instability event is predicted, and a damping coefficient dynamic adjustment plan and a resonance early warning plan are implemented; Obtain the load fluctuation response of key nodes in the power grid, evaluate the stability of the power grid system after implementing the load control scheme, damping coefficient dynamic adjustment scheme and resonance early warning scheme, and optimize the control parameters based on the control feedback data.

2. The method according to claim 1, wherein: The method of identifying the period of time when the abnormal fluctuation amplitude exceeds the limit according to the power flow data of the power system, determining the power reverse flow event, and identifying the potential reverse flow instability event based on the frequency deviation amplitude, deviation recovery rate and instantaneous change rate of the power reverse flow event includes: According to the power data interface of the power system, the power flow data is obtained, including current direction, voltage fluctuation and frequency change; the data preprocessing algorithm is used to clean the power flow data, remove noise and abnormal points, and store the power flow data in the data cache in timestamp order; the short-time Fourier transform algorithm is used to convert the current and voltage data into frequency domain and time domain signals, and the power characteristic parameters are extracted, including the change amplitude of the current direction, the change value of the voltage fluctuation amplitude and the frequency fluctuation rate; according to the power characteristic parameters, the isolation forest algorithm is used to identify the time period when the abnormal fluctuation amplitude exceeds the limit, and the power reverse flow event is determined; according to the power flow data of the power reverse flow event, the frequency deviation amplitude and deviation recovery rate of the power reverse flow event are statistically calculated, and the instantaneous change rate of the frequency deviation is calculated using the sliding average method; according to the frequency deviation amplitude, deviation recovery rate and instantaneous change rate of the power reverse flow event, the decision tree algorithm is used for model training, and a potential reverse flow instability event identification model is constructed to identify potential reverse flow instability events.

3. The method according to claim 1, wherein: The power instability pattern recognition model is constructed based on the key parameters of the historical power instability events to identify the instability pattern of potential reverse flow instability events and the risk level of reverse flow instability events whose instability pattern is power instability, including: Through the power instability feature database, the key parameters of historical power instability events are obtained, including the amplitude, duration and frequency characteristics of current fluctuations, and the power instability event stages and power instability event risk levels are marked. The random forest algorithm is used for model training to build a power instability pattern recognition model. The power instability event stages include instability precursors and power instability. The power instability event risk levels include normal, warning, and dangerous. The instability modes include normal reverse flow, instability precursors, and power instability. According to the key parameters of potential reverse flow instability events, the power instability pattern recognition model is used to identify the instability mode of potential reverse flow instability events, and identify the reverse flow instability event risk level whose instability mode is power instability. The potential reverse current instability event whose instability mode is a precursor of instability is marked as a precursor of instability event, and the potential reverse current instability event whose instability mode is power instability is marked as a reverse current instability event; The reverse flow instability events with risk level labels are transmitted to the power instability event monitoring database, and a multi-level early warning classification mechanism is used to determine the response level of the reverse flow instability events.

4. The method according to claim 1, wherein: The real-time load fluctuation data of the key nodes of the power grid according to the reverse flow instability event, combined with the reverse flow impact factor of the node, identifies the key nodes of the power grid where the reverse flow impact load exceeds the limit, including: Obtain real-time load fluctuation data of key nodes of the power grid during reverse flow instability events. Key nodes of the power grid include but are not limited to load concentration area connection points, trunk line nodes, power generation hub nodes, regional hub nodes and backup power supply nodes. Load fluctuation data include the load change rate, fluctuation amplitude, frequency and duration of the nodes; Based on the load fluctuation data of key nodes of the power grid, combined with the reverse flow influencing factors of the nodes, including the current reverse ratio and the phase angle of load change, use the time-varying load reverse resonance factor evaluation formula Calculate the time-varying load reverse resonance factor Q of the key nodes of the power grid under the impact of reverse flow, where P1 is the benchmark load of the key nodes of the power grid, R is the current reverse ratio when the reverse flow occurs, indicating the reverse flow intensity of the current, θ is the phase angle of the load change, f is the reverse flow fluctuation frequency, g is the load change frequency, and ζ is the damping coefficient, indicating the attenuation capacity of the power system to resonance; determine the load fluctuation amplitude of the key nodes of the power grid under the impact of reverse flow according to the time-varying load reverse resonance factor and the benchmark load of the key nodes of the power grid; identify the key nodes of the power grid with excessive reverse flow impact load according to the preset node load fluctuation tolerance threshold and the calculated load fluctuation amplitude of the key nodes of the power grid under the impact of reverse flow; monitor the rising rate of the reverse flow fluctuation frequency, load change frequency and variable load reverse resonance factor in real time, and formulate a dynamic adjustment plan for the damping coefficient and a resonance early warning plan.

5. The method according to claim 4, wherein: The real-time monitoring of the reverse flow fluctuation frequency, the load change frequency and the rising rate of the variable load reverse resonance factor, and the formulation of a damping coefficient dynamic adjustment plan and a resonance early warning plan include: Real-time monitoring of the reverse flow fluctuation frequency f and load change frequency g. If the frequency ratio is detected If it is greater than the preset ratio threshold, a dynamic adjustment plan for the damping coefficient is formulated and implemented, and the damping coefficient ζ is dynamically adjusted to the preset critical damping coefficient ζ0; the rising rate of the time-varying load reverse resonance factor is calculated and recorded in real time. If the rising rate exceeds the preset rate threshold, a resonance early warning plan is formulated and implemented, including limiting the load at key nodes of the power grid or cutting off designated nodes, controlling the load flow, and transferring part of the load of the current node to adjacent nodes or backup power supply nodes whose load is lower than the preset load threshold.

6. The method according to claim 1, wherein: The real-time load data and historical load fluctuation patterns of the key nodes of the power grid where the reverse flow impact load exceeds the limit are obtained, the load deviation value of each node is calculated, the load amount that needs to be transferred to each node is determined, and a load control plan is formulated, including: Acquire real-time load data of key nodes of the power grid where the reverse impact load exceeds the limit, including load fluctuation amplitude, change rate and fluctuation frequency; extract historical load fluctuation patterns of key nodes of the power grid where the reverse impact load exceeds the limit through the power instability feature database, including load peak, average load level and fluctuation period; compare the real-time load data with the historical data, calculate the load deviation value of each node, and obtain the real-time-historical load deviation characteristics of the key nodes of the power grid; use the adaptive control algorithm to dynamically adjust the control parameters according to the real-time-historical load deviation characteristics of the key nodes of the power grid, determine the amount of load that needs to be transferred at each node, and obtain the adaptive control parameter set; formulate a load control plan based on the adaptive control parameter set to transfer the load of key nodes of the power grid where the reverse impact load exceeds the limit, and give priority to allocating the excess load to adjacent nodes or backup power supply nodes whose load is lower than the preset load threshold.

7. The method according to claim 1, wherein: The method predicts the key parameters of the instability precursor event in the future preset time period based on the historical key parameters of the potential reverse current instability event with the instability mode as the instability precursor, and predicts the time point when the instability precursor event turns into the reverse current instability event in combination with the power instability mode recognition model, and implements the damping coefficient dynamic adjustment scheme and the resonance early warning scheme, including: Through the power instability characteristic database, the historical key parameters of the instability precursor events are obtained and arranged in time series to construct the time series data of the historical key parameters of the instability precursor events; Based on the time series data of historical key parameters of instability precursor events, long short-term memory networks are used for model training to predict the key parameters of instability precursor events within a preset time period in the future; based on the prediction results of the key parameters of instability precursor events within the preset time period in the future, combined with the power instability pattern recognition model, the time point when the instability precursor event turns into a reverse current instability event and the risk level of the reverse current instability event are predicted; based on the predicted time point when the instability precursor event turns into a reverse current instability event, a reverse current instability event warning is sent, and a damping coefficient dynamic adjustment plan and a resonance warning plan are implemented.

8. The method according to claim 1, wherein: The method of obtaining the load fluctuation response of key nodes of the power grid, evaluating the stability of the power grid system after implementing the load control scheme, the damping coefficient dynamic adjustment scheme and the resonance early warning scheme, and optimizing the control parameters based on the control feedback data includes: Continuously monitor the real-time load data of the power system after the implementation of the load control scheme, the damping coefficient dynamic adjustment scheme and the resonance early warning scheme, obtain the load fluctuation response and dynamic change data of the damping coefficient of the key nodes of the power grid, and evaluate the stability of the power grid system after the implementation of each scheme; Record the feedback data in load control, damping coefficient adjustment and resonance warning response, including load change, the ratio of reverse flow fluctuation frequency to load change frequency and resonance warning effect, and judge the power instability mitigation effect of each scheme; based on the power instability mitigation effect, optimize the load control scheme, damping coefficient dynamic adjustment scheme and resonance warning scheme, and adjust the load distribution, control direction and critical damping coefficient; Re-verify the optimized load control scheme, damping coefficient dynamic adjustment scheme and resonance warning scheme, and record the load adjustment amount, critical damping coefficient, warning execution time and load distribution direction of each key node of the power grid. If the power instability mitigation effect of each scheme meets the expectations, the optimized load control scheme, damping coefficient dynamic adjustment scheme and resonance warning scheme will be stored in the power system control database.

Images