Hydropower dispatching training simulation examination evaluation method and system

Abstract

The invention discloses a hydropower dispatching training simulation test evaluation method and system, and relates to the technical field of hydropower dispatching, and the method comprises the following steps: obtaining various parameter information generated in a simulation platform operation process, including power grid load distribution information and hydropower resource utilization efficiency information; through obtaining power grid load distribution information and hydroelectric resource utilization efficiency information generated by a simulation platform and combining intelligent model analysis, an abnormal operation index is generated and real-time monitoring and evaluation are carried out. An index is generated for abnormal analysis of tidal current distribution and tidal energy balance, and potential anomalies are found in time. And when the abnormal index exceeds the standard, the system is divided into a high-risk operation state and gives out an early warning, so that the simulation accuracy and stability are ensured, and the decision-making quality of a dispatcher is improved. Continuous monitoring, evaluation and early warning effectively avoid misoperation, improve emergency processing capacity, reduce power grid accident risks and guarantee stable operation of a power grid.

Description

Technical Field

[0001] The invention relates to the technical field of hydropower dispatching, and in particular to a hydropower dispatching training simulation examination and evaluation method and system. Background Art

[0002] The simulation test and evaluation method for hydropower dispatching training refers to the systematic examination and evaluation of the dispatchers of hydropower stations by simulating real power dispatching scenarios to improve their coping ability and professional level in actual operations. This test usually uses an advanced simulation platform to simulate various complex situations such as different power grid operation states, load demand changes, fault emergency handling, etc. In the simulation environment, the dispatcher needs to make various operational decisions, such as load distribution, power generation dispatching, water level regulation, emergency accident handling, etc. Through these processes, the dispatcher's reaction speed, decision correctness, operational standardization and other skills are examined. This method can effectively reflect the comprehensive ability of dispatchers in actual work, help managers find problems and formulate corresponding improvement measures.

[0003] In addition, the assessment method usually includes multiple indicators, such as technical operation accuracy, standardization of execution procedures, timeliness of fault handling, teamwork ability, etc. The scoring criteria can be quantitatively evaluated based on the pre-set simulation scenarios and operation procedures combined with the actual performance of the dispatcher. The training simulation test is not only a test of personal ability, but also can evaluate the overall coordination efficiency of the hydropower dispatching team through the overall team collaboration. Through this systematic assessment method, the professional quality of hydropower dispatching personnel can be effectively improved to ensure the safe and stable operation of the power system.

[0004] The prior art has the following deficiencies:

[0005] If the simulation platform has anomalies when simulating various environments, resulting in the simulated power grid status, load demand or fault scenario being inconsistent with the actual situation, the decisions made by the dispatcher in the wrong scenario may be mistakenly considered correct, thus forming incorrect operating habits. For example, if the simulation system underestimates the change in load demand, the dispatcher may habitually underestimate the power generation or ignore the precise allocation of the load in actual operation. This situation may cause unstable power grid operation, and in severe cases even cause large-scale power outages. In addition, in emergency situations, dispatchers may not be able to quickly and effectively handle emergencies due to lack of accurate decision-making training, further aggravating the consequences of the accident and causing serious economic losses and social impacts.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide a method and system for evaluating the simulation test of hydropower dispatching training, which obtains the power grid load distribution information and hydropower resource utilization efficiency information generated by the simulation platform, combines intelligent model analysis, generates an abnormal operation index and performs real-time monitoring and evaluation. An index is generated for abnormal analysis of tidal flow distribution and tidal energy balance to detect potential anomalies in a timely manner. When the abnormal index exceeds the standard, the system is divided into a high-risk operating state and an early warning is issued to ensure accurate and stable simulation and improve the quality of dispatcher decision-making. Continuous monitoring, evaluation and early warning can effectively avoid erroneous operations, improve emergency handling capabilities, reduce the risk of power grid accidents, and ensure stable operation of the power grid to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a hydropower dispatching training simulation test evaluation method, comprising the following steps:

[0009] Obtain various parameter information generated during the operation of the simulation platform, including grid load distribution information and hydropower resource utilization efficiency information;

[0010] Perform abnormal analysis on the acquired power grid load distribution information and hydropower resource utilization efficiency information, and input the power grid load distribution information and hydropower resource utilization efficiency information after abnormal analysis into the pre-learned machine model, generate an abnormal operation index through the machine model, and perform intelligent evaluation on the operation process of the simulation platform through the generated abnormal operation index;

[0011] Based on the generated abnormal operation index, the simulation platform operation process is divided into a high-risk abnormal operation state or a low-risk abnormal operation state, and the abnormal operation process of the simulation platform is intelligently perceived;

[0012] For the classified high-risk abnormal operation status, the operation information of the simulation platform is continuously obtained during operation, and several abnormal operation indexes generated subsequently are comprehensively analyzed with the pre-set abnormal operation index reference threshold to generate an evaluation index;

[0013] The generated evaluation index is compared with the pre-set evaluation index reference threshold to generate a risk signal, and an early warning prompt is issued for the risk signal.

[0014] Preferably, the grid load distribution information includes flow distribution, which is a key indicator reflecting the degree of balanced distribution of current on different transmission lines in the power system. The hydropower resource utilization efficiency information includes tidal energy balance, which is an indicator for measuring the balance of water resource scheduling and power generation in the process of hydropower stations utilizing tidal energy to generate electricity.

[0015] Preferably, after performing abnormal analysis on the tidal distribution and tidal energy balance, a tidal distribution index and a tidal energy balance index are generated respectively, and the tidal distribution index and the tidal energy balance index generated after the abnormal analysis are input into a pre-learned machine model, and an abnormal operation index is generated through the machine model, and the operation process of the simulation platform is intelligently evaluated through the generated abnormal operation index.

[0016] Preferably, the logic of analyzing the abnormal flow distribution and generating the flow distribution index is as follows:

[0017] In the detection window, the current sensor and load monitor equipment are used to obtain the current, voltage and line impedance information of each transmission line in real time. The collected information includes the current value I i (t), represents the current value of transmission line i at time t, impedance Z i , represents the impedance of transmission line i, the total voltage V(t), represents the total voltage of the power grid at time t, and the rated load capacity S i , represents the rated load capacity of transmission line i;

[0018] Calculate the instantaneous active power of the transmission line, the calculation expression is as follows: P i (t)=V(t)·I i (t)·cos(θ i ), where P i (t) represents the active power, that is, the instantaneous active power of transmission line i, θ i is the phase angle between voltage and current;

[0019] Calculate the load utilization of each line. The calculation expression is as follows:

[0020]

[0021] , where U i (t) is the load utilization rate, which indicates the load utilization of line i at time t. Then, by comparing the line load utilization rates, the balance of current distribution is evaluated and the load balance coefficient is introduced. The calculation expression is as follows:

[0022]

[0023] , where η(t) represents the load balancing coefficient, N is the total number of transmission lines, and Z i is the impedance value of line i;

[0024] Based on the load utilization U i (t), load balancing coefficient η(t) and impedance value Z of line i i , generate the power flow distribution index, the calculation expression is as follows:

[0025] ,

[0026] Where PFD represents the power flow distribution index.

[0027] Preferably, the logic of analyzing the tidal energy balance anomaly and generating the tidal energy balance index is as follows:

[0028] In the detection window, to obtain the tidal energy balance, we must first calculate the tidal energy input obtained by the hydropower station. The calculation expression is as follows: In the formula, E input represents the tidal energy input, 0 represents the start time of the tidal cycle, T represents the end time of the tidal cycle, ρ represents the density of water, g represents the acceleration of gravity, A(t) represents the cross-sectional area of ​​the reservoir at time t, which changes with the tide, and h(t) represents the change in water level height at time t, reflecting the fluctuation of water level during the tidal cycle;

[0029] According to the tidal energy input, the effective energy of actual power generation is calculated. The effective energy is determined by the efficiency of the turbine, the operating status of the power generation equipment, and the matching degree between the power generation and the tidal cycle. The calculation expression is as follows:

[0030] ,

[0031] In the formula, E output Represents the effective energy of actual power generation, η turbine represents the efficiency of the turbine, P(t) represents the turbine output power at time t, Q(t) represents the water flow of the turbine at time t, q max Indicates the maximum design flow rate of the turbine;

[0032] Calculate the energy utilization efficiency. The energy utilization efficiency reflects the efficiency of converting tidal energy into effective power generation. The calculation expression is as follows:

[0033] ,

[0034] In the formula, E efficiency It indicates the efficiency of energy utilization;

[0035] Calculate the impact of reservoir water level fluctuation on power generation. The calculation expression is as follows: W impact Indicates the fluctuation amplitude of reservoir water level, h tar get (t) represents the preset target water level, and h(t) represents the actual water level;

[0036] Finally, the tidal energy balance index is generated, and the calculation expression is as follows: TEB = E efficiency ·(1-α·W impact), where TEB represents the tidal energy balance index, W impact It represents the impact of reservoir water level fluctuation on power generation, and α is the influence coefficient, which measures the sensitivity of water level fluctuation to energy balance.

[0037] Preferably, the tidal current distribution index PFD and the tidal energy balance index TEB are input into a pre-learned machine model, and the abnormal operation index AO is generated by the machine model according to the formula:

[0038] ,

[0039] Wherein, k1 and k2 are the preset proportional coefficients of the tidal distribution index PFD and the tidal energy balance index TEB, and both k1 and k2 are greater than 0.

[0040] Preferably, the generated abnormal operation index is compared and analyzed with a preset abnormal operation index reference threshold, and the comparison result is as follows:

[0041] If the generated abnormal operation index is greater than or equal to the preset abnormal operation index reference threshold, the simulation platform operation process is classified as a high-risk operation state;

[0042] If the generated abnormal operation index is less than a preset abnormal operation index reference threshold, the simulation platform operation process is classified as a low-risk operation state.

[0043] Preferably, when a high-risk abnormal operation state is generated during the operation of the simulation platform, a number of abnormal operation indexes generated subsequently are comprehensively analyzed with a preset abnormal operation index reference threshold to generate an evaluation index SS, based on the formula: In the formula, AO a represents a risk assessment index greater than or equal to a reference threshold value of an abnormal operation index, a represents the number of an abnormal operation index greater than or equal to the reference threshold value of an abnormal operation index, a=1, 2, 3, ..., q, where q is a positive integer.

[0044] Preferably, the generated evaluation index is compared and analyzed with a preset evaluation index reference threshold, and the analysis results are as follows:

[0045] If the generated evaluation index is greater than or equal to the pre-set evaluation index reference threshold, a high-risk signal is generated and a warning message is issued for the high-risk signal;

[0046] If the generated evaluation index is less than the pre-set evaluation index reference threshold, a low-risk signal is generated, and no warning information is issued for the low-risk signal.

[0047] A hydropower dispatching training simulation test and evaluation system, including a data acquisition module, an abnormal analysis and model input module, an intelligent evaluation module, a continuous monitoring and evaluation module, and a risk warning module;

[0048] The data acquisition module acquires various parameter information generated during the operation of the simulation platform, including grid load distribution information and hydropower resource utilization efficiency information;

[0049] The abnormal analysis and model input module performs abnormal analysis on the acquired grid load distribution information and hydropower resource utilization efficiency information, and inputs the grid load distribution information and hydropower resource utilization efficiency information after abnormal analysis into the pre-learned machine model, generates an abnormal operation index through the machine model, and performs intelligent evaluation on the operation process of the simulation platform through the generated abnormal operation index;

[0050] The intelligent evaluation module divides the operation process of the simulation platform into a high-risk abnormal operation state or a low-risk abnormal operation state based on the generated abnormal operation index, and performs intelligent perception of the abnormal operation process of the simulation platform;

[0051] The continuous monitoring and evaluation module continuously obtains the operation information of the simulation platform during operation according to the classified high-risk abnormal operation status, and comprehensively analyzes several abnormal operation indexes generated subsequently with the pre-set abnormal operation index reference threshold to generate an evaluation index;

[0052] The risk warning module compares the generated evaluation index with the pre-set evaluation index reference threshold, generates a risk signal, and issues a warning prompt for the risk signal.

[0053] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0054] The present invention obtains the grid load distribution information and hydropower resource utilization efficiency information generated during the operation of the simulation platform, analyzes these data in combination with the intelligent machine model, and can generate an abnormal operation index, thereby monitoring and evaluating the operation status of the simulation platform in real time. By performing abnormal analysis on the tidal distribution and tidal energy balance, generating the tidal distribution index and the tidal energy balance index, the system can promptly detect potential abnormalities in the simulation platform. Once the abnormal operation index reaches or exceeds the set reference threshold, the system will classify the simulation platform as a high-risk operation state and issue an early warning prompt. This intelligent perception and early warning mechanism ensures that the operation of the simulation platform is more accurate and stable, avoids erroneous decision-making training due to abnormalities, and fundamentally improves the decision-making quality of dispatchers and the reliability of simulation training.

[0055] The present invention can update and analyze the abnormal operation index in real time, generate an evaluation index and issue an early warning by continuously monitoring the operating status of the simulation platform, especially the high-risk abnormal operation status. Through this continuous risk assessment, the dispatcher can grasp the abnormal situation of the system in a timely manner, avoid wrong operating habits and wrong decisions caused by the abnormality of the simulation platform, thereby improving the dispatcher's judgment and emergency handling capabilities. Especially in emergency situations, the dispatcher can rely on the simulation results that have been strictly evaluated to make a quick and accurate response, reduce the risks of power grid instability or large-scale power outages in actual operations, and ensure the safe and stable operation of the power grid. This data-based risk warning and intelligent assessment greatly reduces the error rate of dispatching decisions and improves the overall efficiency and response speed of the dispatching team. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] 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.

[0057] Figure 1 The present invention is a method flow chart of a hydropower dispatching training simulation test evaluation method.

[0058] Figure 2 The present invention is a module schematic diagram of a hydropower dispatching training simulation test and evaluation system. DETAILED DESCRIPTION

[0059] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0060] The present invention provides Figure 1 A hydropower dispatching training simulation test evaluation method shown includes the following steps:

[0061] Obtain various parameter information generated during the operation of the simulation platform, including grid load distribution information and hydropower resource utilization efficiency information;

[0062] The grid load distribution information includes the power flow distribution, which is a key indicator reflecting the degree of balance of current distribution on different transmission lines in the power system. The hydropower resource utilization efficiency information includes the tidal energy balance, which is an indicator for measuring the balance between water resource scheduling and power generation in the process of hydropower stations using tidal energy to generate electricity.

[0063] Perform abnormal analysis on the acquired power grid load distribution information and hydropower resource utilization efficiency information, and input the power grid load distribution information and hydropower resource utilization efficiency information after abnormal analysis into the pre-learned machine model, generate an abnormal operation index through the machine model, and perform intelligent evaluation on the operation process of the simulation platform through the generated abnormal operation index;

[0064] After abnormal analysis of tidal distribution and tidal energy balance, tidal distribution index and tidal energy balance index are generated respectively. The tidal distribution index and tidal energy balance index generated after abnormal analysis are input into the pre-learned machine model, and the abnormal operation index is generated through the machine model. The operation process of the simulation platform is intelligently evaluated through the generated abnormal operation index.

[0065] Changes in the power flow distribution index during the operation of the simulation platform may indeed cause the simulation environment to be unable to accurately reflect the actual operating status, load changes, and emergency fault handling of the power grid. This is because the power flow distribution index directly reflects the distribution of current in different transmission lines in the power grid, and its changes mean that the flow of electricity in the system is unbalanced. If the simulation platform cannot capture this unbalanced change in a timely and accurate manner, it will affect the accurate simulation of the power grid load. For example, if some transmission lines are overloaded or underloaded in actual operation, and the simulation platform fails to accurately reflect this change, the decisions made by the dispatcher in the simulation scenario will be out of touch with the actual situation, which may lead to incorrect emergency handling operations. In addition, changes in power flow distribution may be directly related to the development path of power grid failures, especially when dealing with sudden load changes or equipment failures, the redistribution of power flow is very critical. The changes in the power flow distribution index in the simulation platform fail to synchronize or accurately reflect the actual situation, and the dispatcher may not be able to correctly predict or respond to faults, thereby affecting the response speed and decision-making quality in actual operations. Therefore, if the changes in the power flow distribution index cannot be accurately simulated, it will indeed affect the authenticity and effectiveness of the simulation environment, thereby interfering with the training effect and ability evaluation of the dispatcher.

[0066] The logic of generating the power flow distribution index for power flow distribution anomaly analysis is as follows:

[0067] In the detection window, the current sensor and load monitor equipment are used to obtain the current, voltage and line impedance information of each transmission line in real time. The collected information includes the current value I i (t), represents the current value of transmission line i at time t, impedance Z i , represents the impedance of transmission line i, the total voltage V(t), represents the total voltage of the power grid at time t, and the rated load capacity S i , represents the rated load capacity of transmission line i;

[0068] It should be noted that:

[0069] To obtain real-time information such as current, voltage, and line impedance of each transmission line, various types of current sensors and load monitors are usually used. The following are some common devices and their functions that can help monitor and obtain key information of the power system:

[0070] 1. Current sensor

[0071] Current sensors are mainly used to monitor current changes on transmission lines. They can convert the current value in the line into a usable electrical signal for real-time analysis by the dispatching system. These sensors can measure both AC and DC and have the characteristics of high accuracy and fast response. The following are the commonly used types of current sensors:

[0072] Hall effect current sensor;

[0073] Hall effect current sensors can measure current by detecting magnetic fields and are suitable for real-time monitoring of transmission lines. They can measure high voltage and high current transmission lines without contact and are often used to sense line current in power systems and are suitable for continuous, online current monitoring.

[0074] Shunt current sensor;

[0075] Shunt current sensors measure the current passing through a precision resistor (shunt) in parallel with the transmission line. The sensor calculates the current based on the voltage drop caused by the current passing through the resistor. This type of sensor is very effective for high-precision current measurement and is suitable for real-time data collection.

[0076] Converter;

[0077] A current transformer is a current sensing device widely used in high current lines. It can convert high current into a lower measurable current signal through electromagnetic induction. CT can be installed on high-voltage transmission lines in the power grid to monitor the AC current value in the transmission line online.

[0078] 2. Voltage sensor

[0079] Voltage sensors are used to measure the voltage on transmission lines and obtain real-time voltage fluctuations of the power grid. The following are commonly used types of voltage sensors:

[0080] Voltage transformer;

[0081] Voltage transformer is a device used in high-voltage power transmission systems. It can transform the voltage of high-voltage power grid to low voltage for monitoring and measurement. VT is widely used in high-voltage lines of power grids. It can obtain grid voltage information in real time and help dispatchers understand the operation status of the power grid.

[0082] Capacitive voltage sensor;

[0083] Capacitive voltage sensors sense voltage changes on the line through the principle of capacitors. They are usually used in high-voltage power systems, have high accuracy and stability, and can detect voltage fluctuations in real time.

[0084] 3. Load Monitor

[0085] The load monitor is responsible for monitoring the load conditions of each transmission line, especially the comprehensive performance of current and voltage. Through this information, key parameters such as the line's active power, reactive power, and power factor can be derived.

[0086] Intelligent electronic devices;

[0087] IED is an advanced monitoring device widely used in power system automation. It can comprehensively monitor the current, voltage and load on the transmission line, and can calculate important parameters such as active power and reactive power. It is suitable for real-time monitoring of the overall operation of the transmission line. IED usually also has protection and control functions.

[0088] Load monitoring terminal;

[0089] The load monitoring terminal can collect real-time load data of the transmission line, including current, voltage, power factor, frequency and other information. LMT is suitable for distributed deployment and can be widely used in different transmission line nodes for real-time monitoring.

[0090] Power quality monitoring devices;

[0091] This device can monitor the voltage, current and power quality in the power system in real time. It can provide information such as instantaneous current, voltage fluctuations, harmonics and power factor. Power quality monitoring equipment is very suitable for tracking load changes in complex power grid environments and analyzing abnormal fluctuations.

[0092] 4. Impedance measurement equipment

[0093] Impedance measurement is used to determine the combined impedance of resistance and reactance in a circuit, usually indirectly by measuring the relative phase angle of voltage and current. The following are commonly used equipment:

[0094] Impedance relay;

[0095] Impedance relays can be used to measure the impedance value of transmission lines online. They can determine the line impedance by measuring the relationship between current and voltage. They are mainly used for the protection and monitoring of power systems, and can also obtain line impedance information in real time.

[0096] Phase measurement unit;

[0097] PMU is a phasor device that can measure voltage and current synchronously with high precision, and is often used in key nodes in large power grids. PMU can indirectly derive line impedance by analyzing the phase relationship between current and voltage, and provide extremely accurate phasor measurement data to help perform system stability analysis and impedance evaluation.

[0098] Calculate the instantaneous active power of the transmission line, the calculation expression is as follows: P i (t)=V(t)·I i (t)·cos(θ i ), where P i (t) represents the active power, that is, the instantaneous active power of transmission line i, θ i is the phase angle between voltage and current;

[0099] It should be noted that:

[0100] Active power is the power actually used to do work in the power system, usually expressed in watts (W). Active power is the part that converts electrical energy into other forms of energy such as mechanical energy, heat energy, and light energy. It is the part of electricity actually consumed by users. For example, the rotation of motors and the lighting of light bulbs all rely on active power. The flow of active power is closely related to the stability and efficiency of the power grid and is the most critical part of the power system.

[0101] The phase angle between voltage and current refers to the relative offset angle of the voltage waveform and the current waveform in time, usually expressed in degrees or radians. In a pure resistance circuit, the voltage and current are synchronized and the phase angle is zero; in a circuit with inductance or capacitance, the current and voltage waveforms will be out of sync, that is, there is a phase angle. The angle at which the current lags or leads the voltage depends on the inductance or capacitance of the circuit. If the current lags behind the voltage, the phase angle is positive (usually occurs in inductive loads, such as motors); if the current leads the voltage, the phase angle is negative (usually occurs in capacitive loads). The phase angle directly affects the distribution of active power and reactive power, so it needs to be closely monitored during power grid operation.

[0102] Phase angle is the time offset of voltage and current on the waveform, which determines the relative relationship between the two. Changes in phase angle directly affect the ratio of active power to reactive power, so phase angle management is crucial in the dispatch and control of power systems.

[0103] Calculate the load utilization of each line. The calculation expression is as follows:

[0104]

[0105] , where U i(t) is the load utilization rate, which indicates the load utilization of line i at time t, that is, the ratio of the current carrying power of the line to its rated load capacity. Then, by comparing the line load utilization rate, the balance of current distribution is evaluated, and the load balancing coefficient is introduced. The calculation expression is as follows:

[0106]

[0107] , where η(t) represents the load balancing coefficient, N is the total number of transmission lines, and Z i is the impedance value of line i;

[0108] Based on the load utilization U i (t), load balancing coefficient η(t) and impedance value Z of line i i , generate the power flow distribution index, the calculation expression is as follows:

[0109]

[0110] , where PFD represents the power flow distribution index;

[0111] It can be seen from the calculation expression of the power flow distribution index that, under the detection window, the larger the power flow distribution index performance value generated after the power flow distribution anomaly analysis, the greater the degree of deviation of the power grid load distribution from the normal situation, indicating that the simulation platform has a higher probability of abnormality when simulating the power grid operation state. On the contrary, if the power flow distribution index performance value is smaller, it means that the load distribution is closer to the normal situation, and the probability of abnormality of the simulation platform in the simulation environment is lower. Therefore, the power flow distribution index is an important indicator to measure the simulation accuracy of the simulation platform.

[0112] Changes in the tidal energy balance index during the operation of the simulation platform may lead to misjudgments of the reservoir water level and power generation capacity, which in turn affects the college's regulation of hydropower production. This is because the tidal energy balance index directly reflects the utilization of hydropower resources by the hydropower station during the tidal cycle. When the index is abnormal or changes, the simulation platform may not be able to accurately simulate the water level fluctuations and power generation capacity during the tidal cycle, and the dispatcher will make decisions based on inaccurate data. For example, a high index may cause the dispatcher to mistakenly believe that there is sufficient water resources at the peak of the tide, resulting in excessive power generation and waste of water energy; while at the low tide, the reservoir may not be able to meet the power generation demand due to insufficient water level, resulting in insufficient power supply. In addition, when responding to changes in the tidal cycle, the dispatcher may not be able to adjust the power generation plan in time, resulting in unstable power production and an imbalance between power supply and demand. Such wrong decisions not only affect the rational use of water resources, but also pose a threat to the stability of the power system and the safety of power supply. Therefore, the accuracy of the tidal energy balance index plays a vital role in the dispatch of hydropower stations, which is directly related to the efficiency and safety of reservoir water level management and power production.

[0113] The logic of generating the tidal energy balance index by analyzing the tidal energy balance anomaly is as follows:

[0114] In the detection window, to obtain the tidal energy balance, we must first calculate the tidal energy input obtained by the hydropower station. The calculation expression is as follows: In the formula, E input represents the tidal energy input, 0 represents the start time of the tidal cycle, T represents the end time of the tidal cycle, ρ represents the density of water, g represents the acceleration of gravity, A(t) represents the cross-sectional area of ​​the reservoir at time t, which changes with the tide, and h(t) represents the change in water level height at time t, reflecting the fluctuation of water level during the tidal cycle;

[0115] It should be noted that tidal energy input refers to the potential energy obtained by the reservoir through the rise and fall of tides during the tidal cycle, which is mainly used for hydroelectric power generation. Tides are the periodic rise and fall of seawater caused by the gravitational effects of the moon and the sun. As the tide rises and falls, the water level of the reservoir changes. This water level difference can store and release huge energy. When the tide rises, the water level of the reservoir rises and the potential energy of the water body increases; when the tide recedes, the water in the reservoir flows out through the turbine, and the potential energy is converted into kinetic energy, and then converted into electrical energy through the generator. The size of tidal energy input depends on many factors, including the density of the water body, the amplitude of the tide (tidal range), the cross-sectional area of ​​the reservoir, and the change in water level height. The calculation of tidal energy input is usually completed through an integral formula within the tidal cycle, taking into account the dynamic changes of water level and reservoir area throughout the cycle. This energy input is crucial to the scheduling and power generation plan of hydropower stations. It determines how much energy a hydropower station can use to generate electricity during a specific tidal cycle. If the tidal energy input is large, the hydropower station can store more water resources during peak hours to generate electricity at low tide and ensure the balance of power supply and demand. Therefore, tidal energy input is the core indicator of hydropower resource utilization efficiency, which directly affects the power generation capacity and energy management of the hydropower station.

[0116] According to the tidal energy input, the effective energy of actual power generation is calculated. The effective energy is determined by the efficiency of the turbine, the operating status of the power generation equipment, and the matching degree between the power generation and the tidal cycle. The calculation expression is as follows:

[0117]

[0118] , where E output Represents the effective energy of actual power generation, η turbine represents the efficiency of the turbine, P(t) represents the turbine output power at time t, Q(t) represents the water flow of the turbine at time t, Q max Indicates the maximum design flow rate of the turbine;

[0119] Calculate the energy utilization efficiency. The energy utilization efficiency reflects the efficiency of converting tidal energy into effective power generation. The calculation expression is as follows:

[0120]

[0121] , where E efficiency It indicates the efficiency of energy utilization;

[0122] Calculate the impact of reservoir water level fluctuation on power generation. The calculation expression is as follows: W impact Indicates the fluctuation amplitude of reservoir water level, h tar get (t) represents the preset target water level, and h(t) represents the actual water level;

[0123] Finally, the tidal energy balance index is generated, and the calculation expression is as follows: TEB = E efficiency ·(1-α·W impact ), where TEB represents the tidal energy balance index, W impact represents the impact of reservoir water level fluctuation on power generation, α is the impact coefficient, which measures the sensitivity of water level fluctuation to energy balance;

[0124] It should be noted that the determination of the influence coefficient α is usually based on a comprehensive consideration of multiple factors, including historical data analysis, field observation results, and simulation experiments. The influence coefficient is used to measure the sensitivity of water level fluctuations to energy balance. Its main purpose is to reflect the degree of influence of reservoir water level fluctuations on power generation efficiency. When determining α, the energy utilization efficiency of the reservoir under different water level regulation strategies is usually analyzed to observe the impact of water level deviation from the target value on power generation and energy balance. This coefficient is often obtained through regression analysis or sensitivity analysis of long-term operating data to ensure that it can truly reflect the impact of water level fluctuations on the energy management of hydropower stations.

[0125] It can be seen from the calculation expression of the tidal energy balance index that, under the detection window, the larger the tidal energy balance index performance value generated after the tidal energy balance anomaly analysis, the more significant the deviation in the utilization efficiency of hydropower resources, indicating that the simulation platform has a higher probability of abnormalities when simulating various environments. This means that the simulation platform may not accurately reflect the actual power grid status and load demand, thus affecting the decision of the dispatcher. On the contrary, if the performance value of the index is smaller, it means that the simulation platform is more stable when simulating various environments, the probability of abnormalities is lower, and the simulation results are more reliable.

[0126] The tidal distribution index PFD and the tidal energy balance index TEB are input into the pre-learned machine model, and the abnormal operation index AO is generated through the machine model according to the formula:

[0127]

[0128] , where k1 and k2 are the preset proportional coefficients of the tidal distribution index PFD and the tidal energy balance index TEB, and both k1 and k2 are greater than 0;

[0129] It can be seen from the calculation expression of the abnormal operation index that, under the detection window, the larger the performance value of the tidal distribution index generated after the abnormal analysis of the tidal distribution, the larger the performance value of the tidal energy balance index generated after the abnormal analysis of the tidal energy balance, and the larger the performance value of the abnormal operation index, the greater the probability of abnormality in the simulation process of the simulation platform, and vice versa, it means that the simulation process of the simulation platform is in an accurate state;

[0130] Based on the generated abnormal operation index, the simulation platform operation process is divided into a high-risk abnormal operation state or a low-risk abnormal operation state, and the abnormal operation process of the simulation platform is intelligently perceived;

[0131] The generated abnormal operation index is compared and analyzed with the preset abnormal operation index reference threshold. The comparison results are as follows:

[0132] If the generated abnormal operation index is greater than or equal to the preset abnormal operation index reference threshold, the simulation platform operation process is classified as a high-risk operation state;

[0133] If the generated abnormal operation index is less than the preset abnormal operation index reference threshold, the simulation platform operation process is classified as a low-risk operation state;

[0134] For the classified high-risk abnormal operation status, the operation information of the simulation platform is continuously obtained during operation, and several abnormal operation indexes generated subsequently are comprehensively analyzed with the pre-set abnormal operation index reference threshold to generate an evaluation index;

[0135] When a high-risk abnormal operation state is generated during the operation of the simulation platform and a warning signal is issued, a comprehensive analysis is performed on several abnormal operation indexes generated subsequently and the preset abnormal operation index reference threshold to generate an evaluation index SS, based on the formula: In the formula, AO a represents a risk assessment index greater than or equal to the abnormal operation index reference threshold, a represents the number of the abnormal operation index greater than or equal to the abnormal operation index reference threshold, a=1, 2, 3, ..., q, q is a positive integer;

[0136] The generated evaluation index is compared with the pre-set evaluation index reference threshold to generate a risk signal, and an early warning prompt is issued for the risk signal.

[0137] The generated evaluation index is compared with the pre-set evaluation index reference threshold, and the analysis results are as follows:

[0138] If the generated evaluation index is greater than or equal to the preset evaluation index reference threshold, a high-risk signal is generated, and a warning message is issued for the high-risk signal, prompting relevant staff to promptly check and maintain the operation status of the simulation platform to prevent the simulation scene from being distorted due to abnormal operation of the simulation platform;

[0139] If the generated evaluation index is less than the preset evaluation index reference threshold, a low-risk signal is generated, and no warning information is issued for the low-risk signal. When this happens, it indicates that an accidental minor anomaly has occurred during the operation of the simulation platform, which will not have a significant impact on the operation of the simulation platform;

[0140] The present invention generates a tidal distribution index and a tidal energy balance index by performing a detailed abnormal analysis on the tidal distribution and tidal energy balance, and then inputs the index into the machine model for intelligent evaluation. This process ensures the accuracy of the operating status of the simulation platform and avoids the problem of simulation environment distortion caused by abnormalities of the simulation platform. Through abnormal analysis and index evaluation, the dispatcher's coping ability in simulation training can be fed back more realistically and accurately, ensuring that he has the ability to cope with complex situations when facing the actual operation of the power grid. In this way, the dispatcher's operating skills can be objectively and accurately evaluated, avoiding misjudgment, thereby improving the quality of training, enhancing the fit between the training results and actual work needs, and ensuring that the dispatcher has the necessary decision-making ability and emergency response level in actual operation.

[0141] The present invention intelligently analyzes the operating status of the simulation platform, and divides the high-risk and low-risk states in real time according to the generated abnormal operation index and evaluation index, which effectively improves the simulation platform's intelligent perception and early warning capabilities for abnormal operating states. When the simulation platform enters a high-risk state, the system will continue to monitor and generate further risk assessments, and determine whether it is necessary to issue an early warning signal after comprehensive analysis. This intelligent risk perception and early warning mechanism based on data and models can significantly reduce possible operational errors in power grid dispatching and reduce the potential risk of power grid accidents caused by abnormal simulation platforms. Through accurate risk analysis, dispatching managers can be aware of potential operating problems in advance to ensure the safety and stability of power system operation.

[0142] The present invention provides Figure 2 A hydropower dispatching training simulation test and evaluation system shown includes a data acquisition module, an abnormal analysis and model input module, an intelligent evaluation module, a continuous monitoring and evaluation module, and a risk warning module;

[0143] The data acquisition module acquires various parameter information generated during the operation of the simulation platform, including grid load distribution information and hydropower resource utilization efficiency information;

[0144] The abnormal analysis and model input module performs abnormal analysis on the acquired grid load distribution information and hydropower resource utilization efficiency information, and inputs the grid load distribution information and hydropower resource utilization efficiency information after abnormal analysis into the pre-learned machine model, generates an abnormal operation index through the machine model, and performs intelligent evaluation on the operation process of the simulation platform through the generated abnormal operation index;

[0145] The intelligent evaluation module divides the operation process of the simulation platform into a high-risk abnormal operation state or a low-risk abnormal operation state based on the generated abnormal operation index, and performs intelligent perception of the abnormal operation process of the simulation platform;

[0146] The continuous monitoring and evaluation module continuously obtains the operation information of the simulation platform during operation according to the classified high-risk abnormal operation status, and comprehensively analyzes several abnormal operation indexes generated subsequently with the pre-set abnormal operation index reference threshold to generate an evaluation index;

[0147] The risk warning module compares the generated evaluation index with the pre-set evaluation index reference threshold, generates a risk signal, and issues a warning prompt for the risk signal.

[0148] A hydropower dispatching training simulation examination and evaluation system provided in an embodiment of the present invention is used to implement the above-mentioned hydropower dispatching training simulation examination and evaluation method. The specific methods and processes of a hydropower dispatching training simulation examination and evaluation system are detailed in the embodiment of the above-mentioned hydropower dispatching training simulation examination and evaluation method, which will not be repeated here.

[0149] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A hydropower dispatching training simulation test evaluation method, characterized in that: The following steps are involved: Obtain various parameter information generated during the operation of the simulation platform, including grid load distribution information and hydropower resource utilization efficiency information; Perform abnormal analysis on the acquired power grid load distribution information and hydropower resource utilization efficiency information, and input the power grid load distribution information and hydropower resource utilization efficiency information after abnormal analysis into the pre-learned machine model, generate an abnormal operation index through the machine model, and perform intelligent evaluation on the operation process of the simulation platform through the generated abnormal operation index; Based on the generated abnormal operation index, the simulation platform operation process is divided into a high-risk abnormal operation state or a low-risk abnormal operation state, and the abnormal operation process of the simulation platform is intelligently perceived; For the classified high-risk abnormal operation status, the operation information of the simulation platform is continuously obtained during operation, and several abnormal operation indexes generated subsequently are comprehensively analyzed with the pre-set abnormal operation index reference threshold to generate an evaluation index; The generated evaluation index is compared with the pre-set evaluation index reference threshold to generate a risk signal, and an early warning prompt is issued for the risk signal.

2. A hydropower dispatching training simulation test evaluation method according to claim 1, characterized in that: The grid load distribution information includes the flow distribution, which is a key indicator reflecting the degree of balanced distribution of current on different transmission lines in the power system. The hydropower resource utilization efficiency information includes the tidal energy balance, which is an indicator for measuring the balance between water resource scheduling and power generation when a hydropower station uses tidal energy to generate electricity.

3. A hydropower dispatching training simulation test evaluation method according to claim 2, characterized in that: After abnormal analysis of tidal distribution and tidal energy balance, the tidal distribution index and tidal energy balance index are generated respectively. The tidal distribution index and tidal energy balance index generated after abnormal analysis are input into the pre-learned machine model, and the abnormal operation index is generated by the machine model. The operation process of the simulation platform is intelligently evaluated by the generated abnormal operation index.

4. A hydropower dispatching training simulation test evaluation method according to claim 3, characterized in that: The logic of generating the power flow distribution index for power flow distribution anomaly analysis is as follows: In the detection window, the current sensor and load monitor equipment are used to obtain the current, voltage and line impedance information of each transmission line in real time. The collected information includes the current value I i (t), represents the current value of transmission line i at time t, impedance Z i , represents the impedance of transmission line i, the total voltage V(t), represents the total voltage of the power grid at time t, and the rated load capacity S i , represents the rated load capacity of transmission line i; Calculate the instantaneous active power of the transmission line, the calculation expression is as follows: P i (t)=V(t)·I i (t)·cos(θ i ), where P i (t) represents the active power, that is, the instantaneous active power of transmission line i, θ i is the phase angle between voltage and current; Calculate the load utilization of each line. The calculation expression is as follows: , Where U i (t) is the load utilization rate, which indicates the load utilization of line i at time t. Then, by comparing the line load utilization rates, the balance of current distribution is evaluated and the load balance coefficient is introduced. The calculation expression is as follows: , Where η(t) represents the load balancing coefficient, N is the total number of transmission lines, and Z i is the impedance value of line i; Based on the load utilization U i (t), load balancing coefficient η(t) and impedance value Z of line i i , generate the power flow distribution index, the calculation expression is as follows: , Where PFD represents the power flow distribution index.

5. A hydropower dispatching training simulation test evaluation method according to claim 3, characterized in that: The logic of generating the tidal energy balance index by analyzing the tidal energy balance anomaly is as follows: In the detection window, to obtain the tidal energy balance, we must first calculate the tidal energy input obtained by the hydropower station. The calculation expression is as follows: In the formula, E input represents the tidal energy input, 0 represents the start time of the tidal cycle, T represents the end time of the tidal cycle, ρ represents the density of water, g represents the acceleration of gravity, A(t) represents the cross-sectional area of ​​the reservoir at time t, which changes with the tide, and h(t) represents the change in water level height at time t, reflecting the fluctuation of water level during the tidal cycle; According to the tidal energy input, the effective energy of actual power generation is calculated. The effective energy is determined by the efficiency of the turbine, the operating status of the power generation equipment, and the matching degree between the power generation and the tidal cycle. The calculation expression is as follows: , In the formula, E output Represents the effective energy of actual power generation, η turbine represents the efficiency of the turbine, P(t) represents the turbine output power at time t, Q(t) represents the water flow of the turbine at time t, Q max Indicates the maximum design flow rate of the turbine; Calculate the energy utilization efficiency. The energy utilization efficiency reflects the efficiency of converting tidal energy into effective power generation. The calculation expression is as follows: , In the formula, E efficiency It indicates the efficiency of energy utilization; Calculate the impact of reservoir water level fluctuation on power generation. The calculation expression is as follows: W impact Indicates the fluctuation amplitude of reservoir water level, h target (t) represents the preset target water level, and h(t) represents the actual water level; Finally, the tidal energy balance index is generated, and the calculation expression is as follows: TEB = E efficiency ·(1-α·W impact ), where TEB represents the tidal energy balance index, W impact It represents the impact of reservoir water level fluctuation on power generation, and α is the influence coefficient, which measures the sensitivity of water level fluctuation to energy balance.

6. A hydropower dispatching training simulation test evaluation method according to claim 3, characterized in that: The tidal distribution index PFD and the tidal energy balance index TEB are input into the pre-learned machine model, and the abnormal operation index AO is generated through the machine model according to the formula: , Wherein, k1 and k2 are the preset proportional coefficients of the tidal distribution index PFD and the tidal energy balance index TEB, and both k1 and k2 are greater than 0.

7. A hydropower dispatching training simulation test evaluation method according to claim 6, characterized in that: The generated abnormal operation index is compared and analyzed with the preset abnormal operation index reference threshold. The comparison results are as follows: If the generated abnormal operation index is greater than or equal to the preset abnormal operation index reference threshold, the simulation platform operation process is classified as a high-risk operation state; If the generated abnormal operation index is less than a preset abnormal operation index reference threshold, the simulation platform operation process is classified as a low-risk operation state.

8. A hydropower dispatching training simulation test and evaluation method according to claim 7, characterized in that: When a high-risk abnormal operation state is generated during the operation of the simulation platform, a comprehensive analysis is performed on several abnormal operation indexes generated subsequently and the preset abnormal operation index reference threshold to generate an evaluation index SS, based on the formula: In the formula, AO a represents a risk assessment index greater than or equal to a reference threshold value of an abnormal operation index, a represents the number of an abnormal operation index greater than or equal to the reference threshold value of an abnormal operation index, a=1, 2, 3, ..., q, where q is a positive integer.

9. A hydropower dispatching training simulation test and evaluation method according to claim 7, characterized in that: The generated evaluation index is compared with the pre-set evaluation index reference threshold, and the analysis results are as follows: If the generated evaluation index is greater than or equal to the pre-set evaluation index reference threshold, a high-risk signal is generated and a warning message is issued for the high-risk signal; If the generated evaluation index is less than the pre-set evaluation index reference threshold, a low-risk signal is generated, and no warning information is issued for the low-risk signal.

10. A hydropower dispatching training simulation test evaluation system, used to implement any one of the hydropower dispatching training simulation test evaluation methods of claims 1-9, characterized in that: It includes data acquisition module, abnormal analysis and model input module, intelligent assessment module, continuous monitoring and assessment module and risk warning module; The data acquisition module acquires various parameter information generated during the operation of the simulation platform, including grid load distribution information and hydropower resource utilization efficiency information; The abnormal analysis and model input module performs abnormal analysis on the acquired grid load distribution information and hydropower resource utilization efficiency information, and inputs the grid load distribution information and hydropower resource utilization efficiency information after abnormal analysis into the pre-learned machine model, generates an abnormal operation index through the machine model, and performs intelligent evaluation on the operation process of the simulation platform through the generated abnormal operation index; The intelligent evaluation module divides the operation process of the simulation platform into a high-risk abnormal operation state or a low-risk abnormal operation state based on the generated abnormal operation index, and performs intelligent perception of the abnormal operation process of the simulation platform; The continuous monitoring and evaluation module continuously obtains the operation information of the simulation platform during operation according to the classified high-risk abnormal operation status, and comprehensively analyzes several abnormal operation indexes generated subsequently with the pre-set abnormal operation index reference threshold to generate an evaluation index; The risk warning module compares the generated evaluation index with the pre-set evaluation index reference threshold, generates a risk signal, and issues a warning prompt for the risk signal.

Images