Hydropower station power generation optimization control method and system

Abstract

The invention provides a hydropower station power generation optimization control method and system, and relates to the technical field of power station optimization scheduling, and the method comprises the steps: collecting the operation data of each generator set, the energy storage data of an energy storage system, and the power grid data; constructing a unit state model, and inputting the operation data of each generator set into the unit state model to obtain the residual frequency modulation capability of each generator set; calculating a current power grid frequency modulation demand based on the power grid data; and constructing a multi-target optimization model, solving the multi-target optimization model by adopting an optimization algorithm, and outputting and executing a target frequency modulation strategy. The method comprehensively considers the power grid frequency modulation demand and the residual frequency modulation capability of each unit through a multi-objective optimization mode, achieves the reasonable distribution of frequency modulation tasks among multiple units, reduces the excessive calling of a single unit, improves the safety, reliability and long-term stability of the overall operation of a hydropower station, and improves the power generation efficiency. The method is especially suitable for a complex frequency modulation working condition under a high-proportion new energy access condition.

Description

Technical Field

[0001] This application relates to the field of power plant optimization scheduling technology, and in particular to a method and system for optimizing power generation control in hydropower stations. Background Technology

[0002] As the penetration rate of renewable energy sources such as wind power and photovoltaics in the power grid continues to increase, their power generation exhibits significant fluctuations and intermittency, posing a severe challenge to the stability of the power grid frequency. Hydropower generating units, due to their large-scale power support and regulatory flexibility, have become an important resource for primary frequency regulation of the power grid. However, hydropower units are limited by hydraulic and mechanical inertia when dealing with high-frequency disturbances, resulting in a delayed response. Furthermore, frequent adjustments to guide vanes or start-up and shutdown operations accelerate mechanical wear, increase maintenance costs, and shorten equipment lifespan, impacting the overall economic benefits of hydropower stations.

[0003] Existing methods for optimizing hydropower generation control mainly include traditional dispatch strategies, hydro-storage joint frequency regulation strategies, and vibration zone constraint methods. Traditional dispatch strategies typically target power generation or a constant incremental rate, with fixed allocation of unit frequency regulation capacity. They lack dynamic awareness of real-time unit fatigue and hydraulic transient risks, making it difficult to balance unit lifespan with grid frequency regulation requirements. Hydro-storage joint frequency regulation methods compensate for hydropower unit response lag by introducing energy storage systems, but power allocation often uses fixed ratios or logical switching, lacking forward-looking dispatch and dynamic optimization. This leads to frequent activation of hydropower units during small disturbances, increasing wear, while large disturbances may prevent full utilization of unit regulation capacity. While some methods consider unit vibration zones and start-up / shutdown constraints, reducing unit risk by avoiding vibration zones or limiting the number of crossings, these are mostly static constraints. They do not quantify regulation capacity as attenuable resources for global dynamic optimization and lack real-time adaptability to changes in unit state.

[0004] Therefore, under the conditions of high penetration of new energy sources and increased grid frequency fluctuations, existing technologies still suffer from problems such as excessively rapid unit wear, decreased efficiency, and insufficient frequency regulation response. Summary of the Invention

[0005] To overcome the above shortcomings, this application provides a method and system for optimizing the power generation control of a hydropower station.

[0006] Firstly, this application provides a method for optimizing the power generation control of a hydropower station, employing the following technical solution: A method for optimizing power generation control in a hydropower station, the method comprising: Data collection: Collect operating data of each generator set, energy storage data of the energy storage system, and grid data; operating data includes status data and hydraulic data; status data includes active power, cumulative start-stop count, guide vane opening data, and operating time; Calculate the remaining frequency regulation capacity: Construct a unit state model, input the operating data of each generator unit into the unit state model, and obtain the remaining frequency regulation capacity of each generator unit; Calculate frequency regulation demand: Based on power grid data, calculate the current power grid frequency regulation demand; Obtaining frequency regulation strategy: Construct a multi-objective optimization model. Based on the energy storage data of the energy storage system, the current grid frequency regulation demand, and the remaining frequency regulation capacity of each generator unit, use an optimization algorithm to solve the multi-objective optimization model and output the target frequency regulation strategy. Execute the frequency modulation strategy: Execute the obtained target frequency modulation strategy.

[0007] Optionally, after performing the step of acquiring data and before performing the step of calculating the remaining frequency modulation capacity, the method further includes: Constructing a unit operation fatigue index model: The formula for the unit operation fatigue index model is as follows: ; in, express Time of the first The unit's operating fatigue index. This represents the start-stop equivalent fatigue coefficient. Indicates the first The cumulative number of start-stop cycles for each generator unit This represents the equivalent fatigue coefficient for power variation. Indicates the first The first generator set Secondary active power variation amplitude This represents the equivalent fatigue coefficient for changes in guide vane opening. Indicates the first The first generator set Secondary guide vane opening amplitude This represents the fatigue coefficient equivalent to runtime. Indicates the first Operating time of the generator set.

[0008] Optionally, the generator set's status data further includes regulation frequencies, which include active power regulation frequencies and guide vane opening regulation frequencies. After performing the step of constructing the generator set's operating fatigue index model, and before performing the step of calculating the remaining frequency regulation capacity, the data further includes: Index Correction: The unit operation fatigue index model is optimized based on the adjustment frequency of the generator set, and the optimized unit operation fatigue index model is used as the new unit operation fatigue index model. The optimized formula for the unit's operating fatigue index is:

[0009] in, Indicates the first The frequency of active power regulation of the generator set. Indicates the first Frequency of guide vane opening adjustment for the generator set.

[0010] Optionally, after performing the step of acquiring data and before performing the step of calculating the remaining frequency modulation capacity, the method further includes: Constructing a hydraulic transient risk model: The calculation formula for the hydraulic transient risk model is as follows: ; in express Time of the first The hydraulic transient risk index of the generator unit Indicates the head risk weight. express Time of the first Head risk factors for generator units , express Time of the first The effective head of the generator set Indicates the first The rated head of the generator set, Indicates the weight of the change in guide vane opening. express Time of the first Risk factors for guide vane changes in generator sets. , express Time of the first Guide vane opening data of the generator set Indicates the preset time interval. Indicates the weight of power change. express Time of the first Risk factors for power variation of generator sets, , express Time of the first The active power of the generator set. Indicates the weight of pressure changes. express Time of the first Pressure variation risk factors for generator sets. , express Time of the first The amplitude of pressure fluctuations in the water intake system of the generator unit. Indicates the first The maximum pressure fluctuation of the preset water intake system of the generator set.

[0011] Optionally, after performing the data acquisition step and before performing the step of constructing the hydraulic transient risk model, the following steps are also included: Acquire generator set data: Obtain real-time operating data for each generator set; Identify the current operating condition: Construct an operating condition identification model, input the real-time operating data of each generator set into the operating condition identification model, and output the current operating condition label of each generator set; Obtaining the optimal weights: Construct a weight objective function, and solve the weight objective function using an optimization algorithm based on the current operating condition labels of each generator unit to obtain the target weights. The target weights include the head risk weight, guide vane opening change weight, power change weight, and pressure change weight.

[0012] Optionally, the formula for the unit state model is: ; in, Indicates the first The maximum frequency regulation capability of the generator set. express Time of the first The unit's operating fatigue index. express Time of the first The hydraulic transient risk index of the generator unit.

[0013] Optionally, in the step of calculating the remaining frequency modulation capability, the remaining frequency modulation capability includes the remaining up-frequency capability and the remaining down-frequency capability; The formula for calculating the remaining up-frequency capability is as follows: ; The formula for calculating the remaining down-modulation frequency capability is as follows: ; in, Indicates the first The rated maximum output power of the generator set Indicates the first The rated minimum output power of the generator set.

[0014] Optionally, the power grid data includes power grid frequency, rated power grid frequency, power grid load, and renewable energy generation. The steps for calculating frequency modulation (FM) requirements include: Calculate frequency deviation: Obtain the real-time power grid frequency, calculate the difference between the real-time power grid frequency and the rated power grid frequency, and record the obtained difference as the current power grid frequency deviation; Calculate the current frequency regulation demand: Construct a frequency regulation demand model, input the current power grid frequency deviation and power grid data into the frequency regulation demand model, and output the current power grid frequency regulation demand; The formula for calculating the frequency demand model is as follows: ; in, This represents the frequency deviation weighting coefficient. express The power grid frequency deviation at any given time, , express The power grid frequency at that moment, Indicates the rated frequency of the power grid. This represents the weighting coefficient for the rate of change of frequency. Indicates the power imbalance weighting coefficient. , express The grid load at any given time , express The amount of renewable energy generated at any given moment.

[0015] Optionally, the target frequency regulation strategy includes the target frequency regulation power of each generator set and the target charging and discharging power of the energy storage system; The steps to obtain the frequency modulation strategy include: Constructing a multi-objective optimization model : ; Set constraints: The constraints include generator output constraints and energy storage system charge / discharge constraints; the generator output constraint is that the target frequency regulation power of the generator set is within the range of the generator set's remaining frequency regulation capacity; the energy storage system charge / discharge constraint is that the target charge / discharge power of the energy storage system is within the preset range of the energy storage system's charge / discharge power. Variable solution: An optimization algorithm is used to solve the multi-objective optimization model to obtain the target frequency modulation strategy; in, This represents the objective function that minimizes the risks of unit operation fatigue and hydraulic transients. This represents the objective function for maximizing the frequency regulation capability of the power grid. This represents the objective function for maximizing the utilization rate of the energy storage system.

[0016] Secondly, this application provides a hydropower station power generation optimization control system, the system being applicable to the method described in any one of the first aspects above, the system comprising: A hydropower station power generation optimization control system, the system comprising: The data acquisition module is used to collect operating data of each generator set, energy storage data of the energy storage system, and grid data; the operating data includes status data and hydraulic data; the status data includes active power, cumulative start-stop count, guide vane opening data, and running time; The module for calculating remaining frequency regulation capacity is used to construct the unit state model. The operating data of each generator unit is input into the unit state model to obtain the remaining frequency regulation capacity of each generator unit. The frequency regulation demand calculation module is used to calculate the current frequency regulation demand of the power grid based on power grid data. The frequency regulation strategy acquisition module is used to construct a multi-objective optimization model. Based on the energy storage data of the energy storage system, the current grid frequency regulation demand, and the remaining frequency regulation capacity of each generator unit, the multi-objective optimization model is solved by an optimization algorithm, and the target frequency regulation strategy is output. The frequency modulation strategy execution module is used to execute the obtained target frequency modulation strategy.

[0017] In summary, this application includes at least one of the following beneficial technical effects: 1. This application comprehensively considers unit fatigue, hydraulic transient risks, grid frequency regulation requirements, and energy storage system utilization. Through multi-objective optimization algorithms and constraint coordination, a global dynamic scheduling strategy is formed. This strategy enables the frequency regulation strategy to optimize grid frequency regulation capability and energy storage system utilization efficiency while taking into account unit lifespan and hydraulic safety. It achieves safe, reliable, and efficient operation of the system under conditions of high new energy penetration and frequency fluctuations, improves the overall economy and frequency regulation capability of hydropower stations, and provides a quantitative and executable optimization scheme for dynamic scheduling.

[0018] 2. This application constructs a unit operation fatigue index model and a hydraulic transient risk model to quantify in real time the operational risks of the generator unit, such as the number of start-ups and shutdowns, power regulation amplitude, guide vane opening changes, and head fluctuations. It dynamically and quantitatively transforms the unit's regulation capacity into an optimizable resource, enabling comprehensive perception and management of the unit's lifespan status. By dynamically adjusting the frequency regulation strategy, it can effectively reduce the wear risk caused by frequent unit calls due to small disturbances, improve the long-term operational reliability of the unit, and extend the service life of the equipment.

[0019] 3. This application uses a multi-objective optimization model to jointly consider the charging and discharging capacity of the energy storage system and the remaining frequency regulation capacity of the hydropower unit, and outputs the target frequency regulation power of each unit and the energy storage system to achieve coordinated scheduling of water and energy storage. This strategy not only enhances the frequency response capability of the power grid and reduces the regulation pressure of a single unit, but also balances the impact of new energy power generation fluctuations on system scheduling, improves the overall regulation efficiency and flexibility, and ensures that the power grid frequency fluctuations can be responded to quickly and stably under high wind and solar penetration conditions. Attached Figure Description

[0020] Figure 1 This is a schematic flowchart of Embodiment 1 of this application; Figure 2 This is a schematic flowchart of obtaining weights in S13 of Embodiment 1 of this application; Figure 3This is a schematic flowchart of S4 obtaining the frequency modulation strategy in Embodiment 1 of this application. Detailed Implementation

[0021] The following combination Figures 1 to 3 This application will be described in further detail.

[0022] Example 1: This example discloses a method for optimizing the power generation control of a hydropower station, such as... Figure 1 As shown, the method includes: collecting operating data of each generator unit, energy storage data of the energy storage system, and grid data; constructing a unit state model, inputting the operating data of each generator unit into the unit state model to obtain the remaining frequency regulation capacity of each generator unit; calculating the current grid frequency regulation demand based on grid data; constructing a multi-objective optimization model, solving the multi-objective optimization model using an optimization algorithm, outputting the target frequency regulation strategy, and executing it. This embodiment includes the following steps: S1 Data Acquisition: This involves collecting operational data from each generator set, energy storage data from the energy storage system, and grid data. The operational data for each generator set includes status data and hydraulic data. Status data includes active power, cumulative start-stop counts, adjustment frequency, guide vane opening data, and operating time. Hydraulic data includes rated head and effective head. Energy storage data for the energy storage system includes stored energy, charging power, and discharging power. Grid data includes grid frequency, rated grid frequency, grid load, and renewable energy generation. The cumulative start-stop count refers to the total number of starts and stops since the generator set began operation. The adjustment frequency includes active power adjustment frequency and guide vane opening adjustment frequency. Renewable energy generation may include, but is not limited to, wind power generation and photovoltaic power generation. Real-time renewable energy generation can be obtained through the corresponding wind power system or photovoltaic system. In this embodiment, the collected data includes both current real-time data and historical data.

[0023] In this embodiment, after collecting the above data, it is necessary to preprocess the data. The data preprocessing steps include data cleaning and data normalization.

[0024] S11 Constructs a Fatigue Index Model for Unit Operation: The formula for the fatigue index model for unit operation is as follows: ; in, express Time of the first The unit's operating fatigue index. This represents the start-stop equivalent fatigue coefficient. Indicates the first The cumulative number of start-stop cycles for each generator unit This represents the equivalent fatigue coefficient for power variation. Indicates the first The first generator set Secondary active power variation amplitude This represents the equivalent fatigue coefficient for changes in guide vane opening. Indicates the first The first generator set Secondary guide vane opening amplitude This represents the fatigue coefficient equivalent to runtime. Indicates the first Operating time of the generator set.

[0025] In this embodiment, , , , , and The value can be set according to the actual usage needs of technical personnel.

[0026] S12 Index Correction: The unit operation fatigue index model is optimized based on the adjustment frequency of the generator set, and the optimized unit operation fatigue index model is used as the new unit operation fatigue index model.

[0027] The optimized formula for the unit's operating fatigue index is:

[0028] in, Indicates the first The frequency of active power regulation of the generator set. Indicates the first Frequency of guide vane opening adjustment for the generator set.

[0029] S13 Obtain Weights: This includes S131 Obtaining Unit Data, S132 Identifying Current Operating Conditions, and S133 Obtaining Optimal Weights, such as... Figure 2 As shown.

[0030] S131 Acquire Unit Data: Acquire real-time and historical operating data of each generator unit, as well as the corresponding operating condition tags for the historical operating data.

[0031] S132 Identify Current Operating Condition: Construct an operating condition identification model. Input historical operating data and corresponding operating condition labels as sample datasets into the operating condition identification model for training, obtaining a trained operating condition identification model. Use the trained operating condition identification model as a new operating condition identification model. Input real-time operating data of each generator unit into the new operating condition identification model, and output the current operating condition labels of each generator unit. In this embodiment, the basic model architecture of the operating condition identification model includes, but is not limited to, any one or a combination of the following: a tree-based classification model, including a random forest model, a gradient boosting decision tree model, or an extreme random tree model; a support vector machine-based classification model; a neural network-based classification model, including a multilayer perceptron model, a convolutional neural network model, or a recurrent neural network model; a deep learning-based temporal classification model, including a long short-term memory network (LSTM) model, a gated recurrent unit (GRU) model, or a temporal classification model based on an attention mechanism. The operating condition labels include steady-state operating condition, load regulation operating condition, frequency regulation operating condition, low load operating condition, rated load operating condition, high load operating condition, start-up operating condition, shutdown operating condition, grid connection operating condition, disconnection operating condition, excessive vibration operating condition, abnormal head operating condition, and emergency support operating condition.

[0032] S133 Obtaining Optimal Weights: Construct a weight objective function. Based on the current operating condition labels of each generator unit, obtain the initial value range of each target weight from the preset operating condition-weight rule base, set weight constraints, use the target weights as optimization variables, and minimize the weight objective function as the optimization objective. Combined with the weight constraints, use a genetic algorithm, particle swarm optimization algorithm, or differential evolution algorithm to iteratively solve the weight objective function. The weight combination with the smallest weight objective function value is taken as the target weight under the current operating condition. The target weights include head risk weight, guide vane opening change weight, power change weight, and pressure change weight.

[0033] The formula for the weighted objective function is: ,in, This indicates the total number of generator units in the hydroelectric power station, 1 , Take the integer part.

[0034] The weight constraints include: the sum of the values ​​of each objective weight is 1, and each objective weight is within the initial value range of the objective weight.

[0035] S14 Constructing a hydraulic transient risk model: The calculation formula for the hydraulic transient risk model is as follows: ; in, express Time of the first The hydraulic transient risk index of the generator unit Indicates the head risk weight. express Time of the first Head risk factors for generator units , express Time of the first The effective head of the generator set Indicates the first The rated head of the generator set, Indicates the weight of the change in guide vane opening. express Time of the first Risk factors for guide vane changes in generator sets. , express Time of the first Guide vane opening data of the generator set Indicates the preset time interval. Indicates the weight of power change. express Time of the first Risk factors for power variation of generator sets, , express Time of the first The active power of the generator set. Indicates the weight of pressure changes. express Time of the first Pressure variation risk factors for generator sets. , express Time of the first The amplitude of pressure fluctuations in the water intake system of the generator unit. Indicates the first The maximum pressure fluctuation of the preset water intake system of the generator set.

[0036] S2 Calculation of Remaining Frequency Regulation Capacity: Construct a unit state model, input the operating data of each generator unit into the unit state model, and obtain the remaining frequency regulation capacity of each generator unit.

[0037] The formula for the unit state model is: ; in, Indicates the first The maximum frequency regulation capability of a generator set is also known as its maximum regulating power. express Time of the first The unit's operating fatigue index. express Time of the first The hydraulic transient risk index of the generator set should be noted. It should be noted that the maximum regulating power of the generator set is the rated maximum regulating power.

[0038] S3 calculates frequency regulation requirements: Based on power grid data, calculates the current power grid frequency regulation requirements, including S31 calculating frequency deviation and S32 calculating frequency regulation requirements.

[0039] S31 calculates the frequency deviation: obtains the real-time grid frequency, calculates the difference between the real-time grid frequency and the grid rated frequency, and records the obtained difference as the current grid frequency deviation.

[0040] S32 calculates frequency regulation demand: Construct a frequency regulation demand model, input the current power grid frequency deviation and power grid data into the frequency regulation demand model, and output the current power grid frequency regulation demand.

[0041] The formula for calculating the frequency demand model is as follows: ; in, This represents the frequency deviation weighting coefficient. express The power grid frequency deviation at any given time, , express The power grid frequency at that moment, Indicates the rated frequency of the power grid. This represents the weighting coefficient for the rate of change of frequency. Indicates the power imbalance weighting coefficient. , express The grid load at any given time , express The amount of renewable energy generated at any given time. In this embodiment, , , and The value can be set according to the actual usage needs of technical personnel.

[0042] S4 Obtaining Frequency Regulation Strategy: Constructing a multi-objective optimization model based on energy storage data of the energy storage system, current grid frequency regulation demand, and remaining frequency regulation capacity of each generating unit, an optimization algorithm is used to solve the multi-objective optimization model, outputting the target frequency regulation strategy. The target frequency regulation strategy includes the target frequency regulation power of each generating unit and the target charging and discharging power of the energy storage system. This includes S41 constructing the multi-objective optimization model, S42 setting constraints, and S43 solving for variables, such as... Figure 3 As shown.

[0043] S41 Construct a multi-objective optimization model : .

[0044] in, This represents the objective function that minimizes the risks of unit operation fatigue and hydraulic transients. This represents the objective function for maximizing the frequency regulation capability of the power grid. This represents the objective function for maximizing the utilization rate of the energy storage system.

[0045] ; ; ; in, Indicates power weight, Indicates the first The target frequency regulation power of the generator set. express Time of the first The active power of the generator set. Indicates the fatigue weight of the unit. Indicates the hydraulic risk weight. Indicates the target power for charging and discharging the energy storage system. This indicates the current frequency regulation demand of the power grid. In this embodiment, , , and The value can be set according to the actual usage needs of technical personnel.

[0046] S42 sets constraints: The constraints include generator output constraints and energy storage system charge / discharge constraints; the generator output constraint is that the target frequency regulation power of the generator set is within the range of the generator set's remaining frequency regulation capacity; the energy storage system charge / discharge constraint is that the target charge / discharge power of the energy storage system is within the preset range of the energy storage system charge / discharge power.

[0047] S43 Variable Solving: A genetic algorithm or particle swarm optimization algorithm is used to solve the multi-objective optimization model to obtain the target frequency regulation strategy. In this embodiment, a particle swarm optimization algorithm is used to solve the multi-objective optimization model. The specific steps are as follows: each particle corresponds to a set of generator unit frequency regulation power and energy storage system charging and discharging power; the positions of each particle in the particle swarm are initialized as the initial solution; the cost function is calculated in each iteration. The particle position and velocity are updated until the maximum number of iterations is reached, and the optimal solution is output. The output optimal solution is used as the target frequency modulation strategy.

[0048] The particle position update formula and velocity update formula are as follows: ; ; in, Indicates the first The first particle The position of the next iteration. Indicates the first The first particle The speed of each iteration Indicates inertia weight, and Indicates the acceleration coefficient. and The value range is usually [1.0, 2.5], and in this embodiment, it can be 2.0. and Represents a random number. and The value range is [0, 1]. This represents the particle's own historical optimal solution. This represents the globally optimal solution.

[0049] S5 executes the frequency modulation strategy: executes the obtained target frequency modulation strategy.

[0050] Unlike existing technologies that rely solely on predicting remaining lifespan as a static constraint, this embodiment directly incorporates the unit's frequency regulation capability as an optimizable resource into multi-objective frequency regulation decisions. By combining an operating condition identification model and weighted adaptive optimization, it achieves global dynamic coordination of grid frequency response, power plant frequency regulation capability, energy storage system utilization, and unit lifespan risk. This overcomes the limitations of traditional static constraints or fixed-ratio scheduling, enabling simultaneous optimization of unit lifespan management and grid frequency regulation capability. It is particularly suitable for operating environments with high renewable energy penetration and intensified frequency fluctuations, significantly improving scheduling foresight, system security, and economy.

[0051] Example 2: The difference from Example 1 is that the remaining frequency modulation capability includes the remaining up-modulation capability and the remaining down-modulation capability, specifically: The formula for calculating the remaining up-frequency capability is as follows: ; The formula for calculating the remaining down-modulation frequency capability is as follows: ; in, Indicates the first The rated maximum output power of the generator set Indicates the first The rated minimum output power of the generator set.

[0052] After setting constraints in S42 and before solving for variables in S43, the following steps are also included: S33 Frequency Regulation Demand Allocation: Based on the remaining upward and downward frequency regulation capabilities of each generator set, calculate the total remaining upward and downward frequency regulation capabilities of the generator sets respectively, determine the frequency regulation direction required by the current power grid frequency regulation demand, and based on the frequency regulation direction and frequency regulation demand, allocate the initial target frequency regulation power of each generator set according to the proportion of the remaining upward frequency regulation capability of each generator set to the total remaining upward frequency regulation capability or the proportion of the remaining downward frequency regulation capability to the total remaining downward frequency regulation capability. Use the initial target frequency regulation power of each generator set as the initial solution of the multi-objective optimization model.

[0053] In solving the S43 variables, the initial target frequency regulation power of each generator set is used as the initial solution of the multi-objective optimization model, and the multi-objective optimization model is solved iteratively.

[0054] In this embodiment, by quantifying the remaining frequency regulation capabilities of each generating unit and allocating initial target power proportionally according to the current grid frequency regulation direction and demand, the frequency regulation task allocation is precisely matched with the actual adjustable capabilities of the generating units. This avoids scheduling deviations caused by fixed proportions or experience-based allocations, improving frequency regulation response speed and system power utilization efficiency. Simultaneously, the allocated initial target power is used as the initial solution for the multi-objective optimization model, ensuring that iterative solutions start from reasonable initial values, reducing local optimum traps, improving the convergence speed of the optimization algorithm and the likelihood of finding the global optimum, thus enhancing the scientific rigor and reliability of the frequency regulation strategy.

[0055] Example 3: This example discloses a hydropower station power generation optimization control system. The system is applicable to the method described in Example 1, and the system includes: The data acquisition module is used to collect operating data of each generator set, energy storage data of the energy storage system, and grid data; the operating data includes status data and hydraulic data; the status data includes active power, cumulative start-stop count, guide vane opening data, and running time; The module for calculating remaining frequency regulation capacity is used to construct the unit state model. The operating data of each generator unit is input into the unit state model to obtain the remaining frequency regulation capacity of each generator unit. The frequency regulation demand calculation module is used to calculate the current frequency regulation demand of the power grid based on power grid data. The frequency regulation strategy acquisition module is used to construct a multi-objective optimization model. Based on the energy storage data of the energy storage system, the current grid frequency regulation demand, and the remaining frequency regulation capacity of each generator unit, the multi-objective optimization model is solved by an optimization algorithm, and the target frequency regulation strategy is output. The frequency modulation strategy execution module is used to execute the obtained target frequency modulation strategy.

[0056] This application constructs a unit operation fatigue index and a hydraulic transient risk model, quantifying operational risks such as the number of start-ups and shutdowns, power regulation amplitude, guide vane opening changes, and head fluctuations into attenuable regulation capabilities. This enables dynamic quantification of the unit's state. Compared with existing optimization methods that rely solely on remaining life prediction as a constraint, this application uses the quantified regulation capabilities as optimization resources to participate in frequency regulation decisions. This allows small disturbances to avoid frequent start-ups and shutdowns, while large disturbances can fully utilize the unit's remaining regulation capabilities, achieving synchronous optimization of unit life management and frequency regulation response.

[0057] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method for optimizing power generation control in a hydropower station, characterized in that, The method includes: Data collection: Collect operating data of each generator set, energy storage data of the energy storage system, and grid data; operating data includes status data and hydraulic data; status data includes active power, cumulative start-stop count, guide vane opening data, and operating time; Calculate the remaining frequency regulation capacity: Construct a unit state model, input the operating data of each generator unit into the unit state model, and obtain the remaining frequency regulation capacity of each generator unit; Calculate frequency regulation demand: Based on power grid data, calculate the current power grid frequency regulation demand; Obtaining frequency regulation strategy: Construct a multi-objective optimization model. Based on the energy storage data of the energy storage system, the current grid frequency regulation demand, and the remaining frequency regulation capacity of each generator unit, use an optimization algorithm to solve the multi-objective optimization model and output the target frequency regulation strategy. Execute the frequency modulation strategy: Execute the obtained target frequency modulation strategy.

2. The hydropower station power generation optimization control method according to claim 1, characterized in that, After performing the data acquisition step and before performing the step of calculating the remaining frequency modulation capacity, the following steps are also included: Constructing a unit operation fatigue index model: The formula for the unit operation fatigue index model is as follows: ; in, express Time of the first The unit's operating fatigue index. This represents the start-stop equivalent fatigue coefficient. Indicates the first The cumulative number of start-stop cycles for each generator unit This represents the equivalent fatigue coefficient for power variation. Indicates the first The first generator set Secondary active power variation amplitude This represents the equivalent fatigue coefficient for changes in guide vane opening. Indicates the first The first generator set Secondary guide vane opening amplitude This represents the fatigue coefficient equivalent to runtime. Indicates the first Operating time of the generator set.

3. The hydropower station power generation optimization control method according to claim 2, characterized in that, The generator set's status data also includes regulation frequencies, which include active power regulation frequencies and guide vane opening regulation frequencies. After performing the step of constructing the generator set's operating fatigue index model and before performing the step of calculating the remaining frequency regulation capacity, the data also includes: Index Correction: The unit operation fatigue index model is optimized based on the adjustment frequency of the generator set, and the optimized unit operation fatigue index model is used as the new unit operation fatigue index model. The optimized formula for the unit's operating fatigue index is: ; in, Indicates the first The frequency of active power regulation of the generator set. Indicates the first Frequency of guide vane opening adjustment for the generator set.

4. The hydropower station power generation optimization control method according to claim 1, characterized in that, After performing the data acquisition step and before performing the step of calculating the remaining frequency modulation capacity, the following steps are also included: Constructing a hydraulic transient risk model: The calculation formula for the hydraulic transient risk model is as follows: ； in express Time of the first The hydraulic transient risk index of the generator unit Indicates the head risk weight. express Time of the first Head risk factors for generator units , express Time of the first The effective head of the generator set Indicates the first The rated head of the generator set, Indicates the weight of the change in guide vane opening. express Time of the first Risk factors for guide vane changes in generator sets. , express Time of the first Guide vane opening data of the generator set Indicates the preset time interval. Indicates the weight of power change. express Time of the first Risk factors for power variation of generator sets, , express Time of the first The active power of the generator set. Indicates the weight of pressure changes. express Time of the first Pressure variation risk factors for generator sets. , express Time of the first The amplitude of pressure fluctuations in the water intake system of the generator unit. Indicates the first The maximum pressure fluctuation of the preset water intake system of the generator set.

5. The hydropower station power generation optimization control method according to claim 4, characterized in that, After performing the data acquisition step and before performing the step of constructing the hydraulic transient risk model, the following steps are also included: Acquire generator set data: Obtain real-time operating data for each generator set; Identify the current operating condition: Construct an operating condition identification model, input the real-time operating data of each generator set into the operating condition identification model, and output the current operating condition label of each generator set; Obtaining the optimal weights: Construct a weight objective function, and solve the weight objective function using an optimization algorithm based on the current operating condition labels of each generator unit to obtain the target weights. The target weights include the head risk weight, guide vane opening change weight, power change weight, and pressure change weight.

6. The hydropower station power generation optimization control method according to claim 1, characterized in that, The formula for the unit state model is: ； in, Indicates the first The maximum frequency regulation capability of the generator set. express Time of the first The unit's operating fatigue index. express Time of the first The hydraulic transient risk index of the generator unit.

7. The hydropower station power generation optimization control method according to claim 6, characterized in that, In the step of calculating the remaining frequency modulation capability, the remaining frequency modulation capability includes the remaining up-frequency modulation capability and the remaining down-frequency modulation capability; The formula for calculating the remaining up-frequency capability is as follows: ; The formula for calculating the remaining down-modulation frequency capability is as follows: ; in, Indicates the first The rated maximum output power of the generator set Indicates the first The rated minimum output power of the generator set.

8. The hydropower station power generation optimization control method according to claim 1, characterized in that, The power grid data includes power grid frequency, rated power grid frequency, power grid load, and renewable energy generation. The steps for calculating frequency modulation (FM) requirements include: Calculate frequency deviation: Obtain the real-time power grid frequency, calculate the difference between the real-time power grid frequency and the rated power grid frequency, and record the obtained difference as the current power grid frequency deviation; Calculate the current frequency regulation demand: Construct a frequency regulation demand model, input the current power grid frequency deviation and power grid data into the frequency regulation demand model, and output the current power grid frequency regulation demand; The formula for calculating the frequency demand model is as follows: ； in, This represents the frequency deviation weighting coefficient. express The power grid frequency deviation at any given time, , express The power grid frequency at that moment, Indicates the rated frequency of the power grid. This represents the weighting coefficient for the rate of change of frequency. Indicates the power imbalance weighting coefficient. , express The grid load at any given time , express The amount of renewable energy generated at any given moment.

9. The hydropower station power generation optimization control method according to claim 1, characterized in that, The target frequency regulation strategy includes the target frequency regulation power of each generator set and the target charging and discharging power of the energy storage system; The steps to obtain the frequency modulation strategy include: Constructing a multi-objective optimization model : ; Set constraints: The constraints include generator output constraints and energy storage system charge / discharge constraints; the generator output constraint is that the target frequency regulation power of the generator set is within the range of the generator set's remaining frequency regulation capacity; the energy storage system charge / discharge constraint is that the target charge / discharge power of the energy storage system is within the preset range of the energy storage system's charge / discharge power. Variable solution: An optimization algorithm is used to solve the multi-objective optimization model to obtain the target frequency modulation strategy; in, This represents the objective function that minimizes the risks of unit operation fatigue and hydraulic transients. This represents the objective function for maximizing the frequency regulation capability of the power grid. This represents the objective function for maximizing the utilization rate of the energy storage system.

10. A hydropower station power generation optimization control system, characterized in that, The system is applicable to the method as described in any one of claims 1-9, the system comprising: The data acquisition module is used to collect operating data of each generator set, energy storage data of the energy storage system, and grid data; the operating data includes status data and hydraulic data; the status data includes active power, cumulative start-stop count, guide vane opening data, and running time; The module for calculating remaining frequency regulation capacity is used to construct the unit state model. The operating data of each generator unit is input into the unit state model to obtain the remaining frequency regulation capacity of each generator unit. The frequency regulation demand calculation module is used to calculate the current frequency regulation demand of the power grid based on power grid data. The frequency regulation strategy acquisition module is used to construct a multi-objective optimization model. Based on the energy storage data of the energy storage system, the current grid frequency regulation demand, and the remaining frequency regulation capacity of each generator unit, the multi-objective optimization model is solved by an optimization algorithm, and the target frequency regulation strategy is output. The frequency modulation strategy execution module is used to execute the obtained target frequency modulation strategy.

Images