Hydropower station income risk measurement method based on hydroenergy value

Abstract

The invention discloses a hydropower station income risk measurement method based on hydraulic energy value, which comprises the following steps: S1, constructing a hydraulic energy value dynamic evaluation model, calculating the hydraulic energy available amount under different space-time scenes by combining a distributed hydrological model, converting the hydraulic energy available amount into an economic value, and obtaining a dynamic hydraulic energy value; s2, establishing a multi-risk factor coupling network, and calculating a synergistic effect weight between risk factors; s3, constructing an income risk dynamic prediction model, updating and predicting a power generation income probability distribution curve in a future preset time period in real time, and identifying a key risk source; s4, constructing a risk-income tradeoff decision matrix through a prediction result and a key risk source output by the income risk dynamic prediction model, and generating income optimization schemes under different risk coping strategies; and S5, displaying the dynamic water energy value, the income risk prediction result and the income optimization scheme by using a visual interface. Accurate evaluation of the dynamic water energy value and real-time prediction of the power generation income risk are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy revenue risk measurement, and particularly relates to a method for measuring the revenue risk of a hydropower station based on the value of water energy. Background Art

[0002] Under the background of the accelerating transformation of the global energy structure towards cleaner energy, hydropower stations, as an important part of renewable energy, the stability of their revenues and the ability to prevent and control risks are crucial for the security of the energy system. The existing operation of hydropower stations faces complex dynamic environmental challenges: climate change has significantly increased the uncertainty of basin hydrological characteristics, the reform of the electricity market has made electricity price fluctuations normal, and the ecological protection policy has increasingly strict constraints on water energy development. The intertwining of multiple factors makes it difficult for traditional revenue assessment methods to meet the actual needs.

[0003] Traditional hydropower station revenue assessment technologies mainly rely on the statistical analysis of historical data, and achieve revenue prediction by establishing a static mapping relationship between runoff and power generation. For example, early methods only used the average annual flow to calculate the theoretical power generation, and estimated the revenue by combining a fixed on-grid electricity price, without considering the spatio-temporal variability characteristics of the hydrological process. The advantage of such technologies is that the calculation logic is simple and the data requirement threshold is low, but their defects are also very obvious: they cannot capture the impact of extreme climate events (such as droughts and floods) on the available water energy, ignore the direct impact of electricity market price fluctuations on revenues, and are even more difficult to quantify the changes in compliance costs brought about by policy factors such as ecological flow constraints. With the complexity of the hydropower station operation environment, the traditional static assessment mode has gradually revealed problems of insufficient timeliness and incomplete risk coverage, making it difficult for operators to cope with real-time changing market and natural risks.

[0004] Although existing technologies have introduced some dynamic elements on the basis of traditional methods, there are still significant limitations. For example, some studies have tried to combine hydrological models to predict runoff changes, or use time series analysis methods to capture electricity price fluctuation patterns, but most of them stay at the level of independent analysis of single risk factors. A typical solution is the power generation prediction based on a distributed hydrological model, which can depict the spatial distribution characteristics of runoff, but does not combine the physical properties of water energy resources with the economic properties of the electricity market, and cannot achieve the leap from "water volume assessment" to "value assessment"; another example is the electricity price prediction model based on machine learning, which can improve the prediction accuracy of short-term price fluctuations, but lacks the coupling analysis of multi-dimensional factors such as hydrological risks and equipment risks, and is difficult to construct a complete revenue risk assessment framework. Existing technologies generally lack the in-depth utilization of real-time monitoring data, and the risk warning and decision support functions are lagging, unable to meet the actual needs of hydropower station dynamic regulation. Summary of the Invention

[0005] Based on the above technical problems, the present application discloses a method for measuring the revenue risk of a hydropower station based on the value of water energy, including:

[0006] S1: Construct a dynamic evaluation model for the value of water energy, collect real-time meteorological data, satellite remote sensing runoff data, and hydropower station equipment operation data within the basin, calculate the available water energy under different spatio-temporal scenarios in combination with a distributed hydrological model, and convert the available water energy into economic value based on the real-time electricity price in the power market, medium- and long-term contract price, and ecological flow constraint conditions to obtain the dynamic value of water energy;

[0007] S2: Establish a multi-risk factor coupling network, identify risk sources, construct risk transmission paths, quantify the marginal impact of each risk factor on the value of water energy and power generation revenue, and calculate the synergy effect weight between risk factors;

[0008] S3: Use the reinforcement learning algorithm to take the dynamic value of water energy and the multi-risk factor coupling network data as inputs, construct a dynamic prediction model for revenue and risk, update in real time the probability distribution curve of power generation revenue predicted for a preset future time period, and identify key risk sources;

[0009] S4: Construct a risk-return trade-off decision matrix based on the prediction results and key risk sources output by the dynamic prediction model for revenue and risk, and generate revenue optimization plans under different risk response strategies in combination with the peak shaving and frequency modulation capabilities of the hydropower station and the reservoir water storage status;

[0010] S5: Use a visualization interface to display the dynamic value of water energy, the prediction results of revenue and risk, and the revenue optimization plans, support users to conduct multi-scenario simulation interactive analysis, and output visual risk curve graphs and revenue comparison charts.

[0011] Preferably, in S1, calculating the available water energy under different spatio-temporal scenarios in combination with a distributed hydrological model specifically includes: substituting the precipitation , evaporation in the real-time meteorological data, the initial runoff of the basin in the satellite remote sensing runoff data , and the turbine efficiency in the hydropower station equipment operation data into the spatio-temporal coupling equation of the distributed hydrological model. The formula is: , where is the regional precipitation-runoff conversion coefficient, is the spatio-temporal correction parameter of the terrain slope; according to the head of the hydropower station, through the available water energy calculation formula , calculate the available water energy under each spatio-temporal scenario . Among them, is the density of water, is the acceleration due to gravity, represents the spatial grid number, represents the time node.

[0012] Preferably, in S1, based on the real-time electricity price in the electricity market, the medium- and long-term contract price, and the ecological flow constraint conditions, the available water energy is converted into economic value through the dynamic evaluation model of water energy value, specifically:

[0013] Obtain the real-time electricity price in the electricity market , the medium- and long-term contract electricity price , and determine the threshold of the available water energy for power generation according to the ecological flow constraint conditions ; construct a price weight distribution function, the formula is: , where is the real-time electricity price priority adjustment coefficient, through the mixed pricing formula , calculate the dynamic water energy value at each time node , where is the available water energy at the time node, and obtain the dynamic water energy value.

[0014] Preferably, the risk sources determined in the multi-risk factor coupling network in S2 include hydrological risk, market risk, equipment risk, and policy risk; among them, hydrological risk includes seasonal runoff fluctuation risk, abnormal water volume risk caused by extreme climate, and hydrological change risk caused by human activities within the basin; market risk covers real-time electricity price fluctuation risk in the electricity market, medium- and long-term contract default risk, and consumption competition risk brought by new energy grid connection; equipment risk includes water turbine generator set failure risk, aging risk of power transmission and transformation equipment, and intelligent monitoring system failure risk; policy risk involves the risk of increased compliance costs caused by environmental protection policies and the risk of changes in the income structure brought about by power system reform.

[0015] Preferably, in S2, by constructing a risk transfer path, quantify the marginal impact of each risk factor on water energy value and power generation income, and calculate the synergy weight between risk factors, specifically: establish a risk factor set , where represents the th type of risk, the risk transfer coefficient matrix is , where represents the transfer intensity of risk factor to , use the marginal impact quantification formula to calculate the marginal impact of risk factor on water energy value , the formula is: , where is the partial derivative of water energy value with respect to risk factor , calculate the synergy weight between risk factor and through the synergy weight formula, the formula is: , where As risk factors When combined with the impact on the value of hydropower energy are respectively the impact amounts on the value of hydropower energy when acting alone and As risk factors When combined with the impact on the value of hydropower energy are respectively the impact amounts on the value of hydropower energy when acting alone and is the maximum impact value in all combinations of risk factors, and a quantitative analysis of the impact and synergistic effect of risk factors is carried out

[0016] Preferably, the revenue-risk dynamic prediction model in S3 includes a deep learning architecture of an input layer, an attention mechanism layer, a bidirectional long short-term memory network layer Bi-LSTM, and an output layer; the obtained dynamic hydropower energy value sequence, risk factor transfer intensity matrix, and synergistic effect weight matrix are used as the input layer data; the attention mechanism layer adaptively assigns weights to different risk factors and time series data, highlighting the key risk information that has a greater impact on revenue; the bidirectional long short-term memory network layer is used to capture the time-dependent relationship and bidirectional dynamic characteristics between risk factors and hydropower energy value; in the output layer, through the probability density function fitting module, the probability distribution curve of the power generation revenue within a preset future time period is output, where the probability density function uses a mixture Gaussian model, and the model parameters are optimized through the expectation maximization algorithm to achieve the dynamic prediction of power generation revenue risk

[0017] Preferably, the probability distribution curve of the power generation revenue within a preset future time period is predicted through the revenue-risk dynamic prediction model in S3 to identify the key risk sources, specifically:

[0018] Obtain the data collection frequency of , and each time new dynamic hydropower energy value data , risk transfer coefficient matrix and synergistic effect weight matrix are obtained, they are combined with the historical data sequence to form sliding time window data , which is input into the revenue-risk dynamic prediction model. The bidirectional long short-term memory network layer in the revenue-risk dynamic prediction model is used to extract features from the time window data, and the weights of each risk factor at the current moment are reallocated in combination with the attention mechanism layer. The probability density function of the power generation revenue within a preset future time period is calculated through the mixture Gaussian model in the output layer, where is the number of Gaussian distributions, and , are the mixing coefficient, mean, and variance of the -th Gaussian distribution at moment, respectively, so as to update the probability distribution curve of power generation revenue. By calculating the contribution degree of each risk factor to the variance of the probability distribution curve, the risk factors with contribution degree exceeding the set threshold are identified as key risk sources, and the formula is: , is the variance of power generation revenue , is the risk factor.

[0019] Preferably, in S4, a risk-return trade-off decision matrix is constructed through the prediction results output by the revenue risk dynamic prediction model and the key risk sources. Specifically: the probability distribution curve of power generation revenue in the prediction results is divided into quantiles to form high, medium, and low revenue scenario sets. For each revenue scenario, combined with the type and influence degree of the key risk sources, an evaluation index system including four dimensions of risk response strategy, implementation cost, revenue improvement potential, and risk mitigation effect is constructed. The analytic hierarchy process is used to determine the relative weights of each dimension, calculate the objective weights of each evaluation index, and form a combined weight vector; the peak regulation and frequency modulation capabilities of the hydropower station and the constraint conditions of the reservoir water storage state are transformed into the boundary conditions of the decision space, and the multi-objective programming algorithm is used to generate the Pareto optimal solution set in the decision space. Each solution corresponds to a risk-return trade-off scheme; clustering analysis is performed on the Pareto optimal solution set to form a limited number of representative decision scheme clusters. Each scheme cluster corresponds to the optimal decision strategy under different risk preferences, and a risk-return trade-off decision matrix is constructed.

[0020] Preferably, in S4, the method of transforming the peak regulation and frequency modulation capabilities of the hydropower station and the constraint conditions of the reservoir water storage state into the boundary conditions of the decision space, using the multi-objective programming algorithm to generate the Pareto optimal solution set, and then forming the decision scheme cluster through clustering analysis is as follows: define the decision variable set , where represents the implementation intensity of different risk response strategies; the peak regulation and frequency modulation capability constraint of the hydropower station is expressed as , and the reservoir water storage state constraint is expressed as , where , are the upper and lower limits of the peak regulation and frequency modulation power, , are the upper and lower limits of the reservoir water storage capacity, , Let \(\alpha\) be the influence coefficient of each strategy on the peak - shaving power and the water storage state, construct a decision - making space, and perform multi - objective optimization within the decision - making space through the non - dominated sorting genetic algorithm. Taking maximizing power generation revenue and minimizing the risk level as the objective functions, iterate and update to obtain the Pareto optimal solution set; for each solution in the Pareto optimal solution set , calculate the Euclidean distance from other solutions, and the formula is: , where is the number of objective functions, is the value of the th objective function. Set the density threshold and neighborhood radius, and cluster the solutions with a distance less than the neighborhood radius and a density greater than the density threshold into the same cluster, forming a finite number of representative decision - making scheme clusters, and each cluster corresponds to decision - making schemes with similar risk - return characteristics.

[0021] Preferably, in S5, the user can input custom scenario variables through the parameter adjustment panel, including but not limited to the amplitude of electricity price fluctuations and the probability of extreme hydrological events, and call the revenue - risk dynamic prediction model and the risk - return trade - off decision matrix in real - time, recalculate and generate visual charts corresponding to the scenarios, and associate the visual components for linkage analysis.

[0022] Compared with the prior art, the technical solution of the present application has the following technical effects:

[0023] The present invention realizes the dynamic conversion of water energy resources from "physical quantity" to "economic value" by integrating real - time meteorological data, satellite - remote - sensing runoff and distributed hydrological models, depicts the runoff changes in different grids and time periods through the spatio - temporal coupling equation, and combines the hybrid pricing mechanism of real - time electricity price and medium - and long - term contract price to accurately calculate the water energy value in each spatio - temporal scenario.

[0024] The present invention constructs a multi - risk - factor coupling network, incorporates four types of risks and their sub - risks, namely hydrological, market, equipment, and policy risks, into a unified framework, and reveals the conduction path and superposition effect between risks through the risk transfer coefficient matrix and the synergy weight algorithm. Multidimensional analysis makes the risk assessment shift from "fragmented" to "systematic", avoiding the failure of prevention and control strategies caused by ignoring the risk linkage in traditional methods.

[0025] The present invention adopts the deep - learning architecture of "attention mechanism + bidirectional long - short - term memory network", combines the sliding - time - window data to update the revenue - risk prediction model in real - time, automatically captures the real - time runoff data and electricity price fluctuation information, quickly updates the revenue probability distribution curve through the mixture Gaussian model, pre - identifies the compound risk scenario of "flood risk causing equipment failure + sudden drop in electricity price", and calculates the contribution degree of each risk factor to the revenue variance, accurately locating the key risk sources, and the update frequency of the prediction results can reach the minute level.

[0026] The present invention transforms complex water energy values, risk distributions, and decision-making schemes into intuitive charts. Users can customize and input parameters such as the amplitude of electricity price fluctuations and the probability of extreme hydrological events, and generate real-time comparative analysis results for multiple scenarios. Through the linkage analysis function, clicking on a risk area can jump to display the optimal power generation plan for the corresponding period.

[0027] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, so as to be implemented in accordance with the content of the specification, and in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the following describes in detail with reference to the preferred embodiments of this application and the accompanying drawings.

[0028] Based on the following detailed description of the specific embodiments of this application in conjunction with the accompanying drawings, those skilled in the art will be more clear about the above and other purposes, advantages, and features of this application. Description of the Drawings

[0029] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to actual scale.

[0030] Figure 1 It is a flow chart of a method for measuring the income risk of a hydropower station based on water energy value of the present invention;

[0031] Figure 2 It is a comparative curve graph of the daily water energy value and the real-time electricity price in the embodiment;

[0032] Figure 3 It is a comparative graph of the income distribution in the embodiment;

[0033] Figure 4 It is a radar graph of the recognition accuracy rate of key risk sources in the embodiment. Detailed Embodiments

[0034] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, rather than all of them. In the following description, providing specific details such as specific configurations and components is only to assist in a comprehensive understanding of the embodiments of this application. Therefore, those skilled in the art should clearly understand that various changes and modifications can be made to the embodiments described here without departing from the scope and spirit of this application. In addition, for the sake of clarity and conciseness, descriptions of known functions and structures are omitted in the embodiments.

[0035] It should be understood that the phrase "an embodiment" or "the embodiment" mentioned throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, the phrase "an embodiment" or "the embodiment" that appears throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics can be combined in one or more embodiments in any suitable manner.

[0036] In addition, this application may repeat reference numerals and / or letters in different examples. This repetition is for the purpose of simplicity and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0037] The term "and / or" in this document is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, B exists alone, and both A and B exist simultaneously. The term " / and" in this document describes another association relationship of associated objects, indicating that two relationships can exist. For example, A / and B can represent: A exists alone, and both A and B exist. In addition, the character " / " in this document generally indicates that the associated objects before and after are in an "or" relationship.

[0038] The term "at least one" in this document is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, at least one of A and B can represent: A exists alone, both A and B exist simultaneously, and B exists alone.

[0039] It should also be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise", or any other variant thereof are intended to cover non-exclusive inclusion.

[0040] Embodiment 1

[0041] This embodiment mainly describes a method for measuring the revenue risk of a hydropower station based on the value of water energy, as Figure 1 shown, specifically including:

[0042] S1: Construct a dynamic evaluation model of water energy value, collect real-time meteorological data, satellite remote sensing runoff data, and hydropower station equipment operation data within the basin, calculate the available water energy under different spatio-temporal scenarios in combination with a distributed hydrological model, and convert the available water energy into economic value based on the real-time electricity price in the power market, medium- and long-term contract price, and ecological flow constraint conditions to obtain the dynamic water energy value;

[0043] S2: Establish a multi-risk factor coupling network, determine the risk sources, construct the risk transmission path, quantify the marginal impact of each risk factor on the water energy value and power generation revenue, and calculate the synergy effect weight between risk factors;

[0044] S3: By using the reinforcement learning algorithm, take the dynamic water energy value and multi-risk factor coupling network data as inputs, construct a revenue risk dynamic prediction model, update the probability distribution curve of power generation revenue in the future preset time period in real time, and identify the key risk sources;

[0045] S4: Through the prediction results and key risk sources output by the revenue risk dynamic prediction model, construct a risk-revenue trade-off decision matrix, and generate revenue optimization plans under different risk response strategies in combination with the peak shaving and frequency modulation capabilities of the hydropower station and the reservoir water storage status;

[0046] S5: Use a visualization interface to display the dynamic water energy value, revenue risk prediction results, and revenue optimization plans, support users to conduct multi-scenario simulation interaction analysis, and output visual risk curves and revenue comparison charts.

[0047] Furthermore, in the above S1, calculating the available water energy under different spatio-temporal scenarios in combination with a distributed hydrological model specifically means: substituting the precipitation , evaporation in the real-time meteorological data, the initial runoff of the basin in the satellite remote sensing runoff data, and the turbine efficiency in the hydropower station equipment operation data into the spatio-temporal coupling equation of the distributed hydrological model. The formula is: , where is the regional precipitation-runoff conversion coefficient, is the spatio-temporal correction parameter of the terrain slope; according to the head of the hydropower station, through the available water energy calculation formula , calculate the available water energy under each spatio-temporal scenario . Among them, is the density of water, is the acceleration of gravity, represents the spatial grid number, and represents the time node.

[0048] Furthermore, in S1, based on the real-time electricity price in the electricity market, the medium- and long-term contract price, and the ecological flow constraint conditions, the available water energy is converted into economic value through a dynamic evaluation model of water energy value, specifically as follows:

[0049] Obtain the real-time electricity price in the electricity market , the medium- and long-term contract electricity price , and determine the threshold of available water energy for power generation according to the ecological flow constraint conditions ; construct a price weight allocation function, the formula is: , where is the real-time electricity price priority adjustment coefficient, through the mixed pricing formula , calculate the dynamic water energy value at each time node , where is the available water energy at the time node, and obtain the dynamic water energy value.

[0050] Furthermore, the risk sources determined in the multi-risk factor coupling network in S2 include hydrological risk, market risk, equipment risk, and policy risk; among them, hydrological risk includes seasonal runoff fluctuation risk, abnormal water volume risk caused by extreme climate, and hydrological change risk caused by human activities within the basin; market risk covers real-time electricity price fluctuation risk in the electricity market, medium- and long-term contract default risk, and consumption competition risk brought by new energy grid connection; equipment risk includes water turbine generator set failure risk, aging risk of power transmission and transformation equipment, and intelligent monitoring system failure risk; policy risk involves the risk of increased compliance costs caused by environmental protection policies and the risk of changes in the income structure brought about by power system reform.

[0051] Furthermore, in S2, by constructing a risk transmission path, the marginal impact of each risk factor on water energy value and power generation income is quantified, and the synergy effect weight between risk factors is calculated, specifically as follows: establish a risk factor set , where represents the th type of risk, the risk transmission coefficient matrix is , where represents the transmission intensity of risk factor on , use the marginal impact quantification formula to calculate the marginal impact of risk factor on water energy value , the formula is: , where is the partial derivative of water energy value with respect to risk factor , calculate the risk factor through the synergy effect weight formula The synergy effect weight between is given by the formula: , where is a risk factor The impact on the hydropower value when act together, are respectively The impact on the hydropower value when acts alone, is a risk factor The impact on the hydropower value when act together, are respectively The impact on the hydropower value when acts alone, is the maximum impact among all combinations of risk factors, and a quantitative analysis of the risk factor impact and synergy effect is carried out.

[0052] Furthermore, the revenue risk dynamic prediction model in S3 includes a deep learning architecture of an input layer, an attention mechanism layer, a bidirectional long short-term memory network layer Bi-LSTM, and an output layer; the obtained dynamic hydropower value sequence, risk factor transfer intensity matrix, and synergy effect weight matrix are used as the input layer data; the attention mechanism layer adaptively assigns weights to different risk factors and time series data, highlighting the key risk information with a greater impact on revenue; the bidirectional long short-term memory network layer is used to capture the time-dependent relationship and bidirectional dynamic characteristics between risk factors and hydropower value; in the output layer, through the probability density function fitting module, the probability distribution curve of the power generation revenue within a preset future time period is output, where the probability density function adopts a mixture Gaussian model, and the model parameters are optimized through the expectation maximization algorithm to achieve the dynamic prediction of the power generation revenue risk.

[0053] Furthermore, the probability distribution curve of the power generation revenue within a preset future time period is predicted through the revenue risk dynamic prediction model in S3 to identify the key risk sources, specifically:

[0054] Obtain a data collection frequency of , and each time new dynamic hydropower value data , risk transfer coefficient matrix , and synergy effect weight matrix are obtained, they are combined with the historical data sequence to form sliding time window data , which is input into the revenue risk dynamic prediction model. The bidirectional long short-term memory network layer in the revenue risk dynamic prediction model is used to extract features from the time window data, combined with the attention mechanism layer to reassign the weights of each risk factor at the current moment, and the mixture Gaussian model in the output layer is used to calculate the power generation revenue within a preset future time period Probability density function , where is the number of Gaussian distributions, , , are respectively the mixing coefficient, mean and variance of the -th Gaussian distribution at time . Thus, the probability distribution curve of power generation revenue is updated. By calculating the contribution degree of each risk factor to the variance of the probability distribution curve, the risk factors with contribution degree exceeding the set threshold are identified as key risk sources. The formula is: , is the variance of power generation revenue , is the risk factor.

[0055] Furthermore, in S4, a risk-return trade-off decision matrix is constructed based on the prediction results output by the revenue risk dynamic prediction model and the key risk sources. Specifically: the probability distribution curve of power generation revenue in the prediction results is divided into quantiles to form high, medium, and low revenue scenario sets. For each revenue scenario, combined with the type and impact degree of the key risk sources, an evaluation index system including four dimensions of risk response strategy, implementation cost, revenue improvement potential, and risk mitigation effect is constructed. The analytic hierarchy process is used to determine the relative weights of each dimension, calculate the objective weights of each evaluation index, and form a combined weight vector; the peak regulation and frequency modulation capabilities of the hydropower station and the reservoir water storage state constraint conditions are transformed into the boundary conditions of the decision space, and the multi-objective programming algorithm is used to generate the Pareto optimal solution set in the decision space. Each solution corresponds to a risk-return trade-off scheme; cluster analysis is performed on the Pareto optimal solution set to form a finite number of representative decision scheme clusters. Each scheme cluster corresponds to the optimal decision strategy under different risk preferences, and a risk-return trade-off decision matrix is constructed.

[0056] Furthermore, in S4, the specific method of transforming the peak regulation and frequency modulation capabilities of the hydropower station and the reservoir water storage state constraint conditions into the boundary conditions of the decision space, and then generating the Pareto optimal solution set by multi-objective programming algorithm and forming the decision scheme cluster by cluster analysis is as follows: Define the decision variable set , where represents the implementation intensity of different risk response strategies; the peak regulation and frequency modulation capability constraint of the hydropower station is expressed as , and the reservoir water storage state constraint is expressed as , where , are the upper and lower limits of the peak regulation and frequency modulation power, , are the upper and lower limits of the reservoir water storage capacity, , Let \( \alpha_{i} \) be the influence coefficients of each strategy on the peak - shaving power and the water storage state, construct the decision space, and perform multi - objective optimization within the decision space through the non - dominated sorting genetic algorithm. Taking maximizing the power generation revenue and minimizing the risk level as the objective functions, iterate and update to obtain the Pareto optimal solution set; for each solution in the Pareto optimal solution set , calculate the Euclidean distance from other solutions, and the formula is: , where is the number of objective functions, is the -th objective function value. Set the density threshold and the neighborhood radius, and cluster the solutions with a distance less than the neighborhood radius and a density greater than the density threshold into the same cluster, forming a finite number of representative decision - making plan clusters. Each cluster corresponds to decision - making plans with similar risk - return characteristics.

[0057] Furthermore, in step S5, the user can input custom scenario variables through the parameter adjustment panel, including but not limited to the amplitude of electricity price fluctuations and the probability of extreme hydrological events, and call the revenue - risk dynamic prediction model and the risk - return trade - off decision matrix in real - time, recalculate and generate the visual charts corresponding to the scenarios, and associate the visual components for linkage analysis.

[0058] This embodiment details the realization of the spatio - temporal dynamic calculation of the available water energy through the integration of real - time meteorological data, satellite remote - sensing runoff data and distributed hydrological models, and combines the multi - dimensional price mechanism of the power market and ecological constraint conditions to convert physical quantities into economic values, solving the problem of "lack of value evaluation" in traditional methods. A multi - risk - factor coupling network is established to quantify the marginal impacts and synergistic effects of risk sources such as hydrology, market, equipment, and policies. A revenue - risk dynamic prediction model is constructed through the reinforcement learning algorithm and the mixture Gaussian model, and the prediction results are updated in real - time using real - time data, significantly improving the timeliness and accuracy of risk prediction.

[0059] Based on Embodiment 1, this embodiment details the specific implementation effects of this application, specifically:

[0060] Taking a cascade hydropower station group in a certain basin in the southwest of China, abbreviated as "A Power Station Group", the region contains 3 cascade power stations with a total installed capacity of 1200 MW, undertaking the tasks of basin flood control, ecological regulation and system peak - shaving. Select the flood season from May to August 2024 as the research period, and combine real - time meteorological data, market trading information and equipment operation status to verify the effectiveness of the revenue - risk measurement method based on the value of water energy.

[0061] The drainage area where the A power station group is located is about 18,000 square kilometers, with an average annual precipitation of 1400 mm. The runoff is mainly replenished by precipitation, and the water volume during the flood season (May - September) accounts for about 70%. All three power stations are developed in a dam - type manner, with a total reservoir capacity of about 2.8 billion cubic meters. Among them, the upstream power station has an annual regulation capacity, and the middle and downstream power stations are seasonally regulated. The main parameters are shown in the following table:

[0062] Power Station Name Installed Capacity (MW) Regulation Performance Upstream Power Station 400 Annual Regulation Midstream Power Station 500 Seasonal Regulation Downstream Power Station 300 Seasonal Regulation

[0063] Obtain hydrological data. Hourly precipitation, evaporation, temperature, etc. are obtained through 12 meteorological stations and 3 Doppler radars within the basin. The average precipitation from May to August 2024 is 3.8 mm / h, and the maximum hourly rainfall intensity reaches 20 mm / h (appearing on July 12th); Use Sentinel - 1 radar satellite to invert the initial runoff of the basin. The average initial runoff during the flood season is 350 m³ / s, and the peak reaches 1200 m³ / s during extreme rainstorms (such as on July 12th); Collect equipment operation data. The average efficiency of the water turbine is 88%, and the water level fluctuation range of the reservoir during the flood season is 85% - 100% of the normal storage level.

[0064] Obtain market data. Real - time electricity price: Participate in the provincial electricity spot market. The real - time electricity price fluctuation range from May to August 2024 is 0.25 - 0.62 yuan / kWh. The average price during peak hours (18:00 - 22:00) is 0.55 yuan / kWh, and the average price during valley hours (00:00 - 06:00) is 0.30 yuan / kWh. Medium - and long - term contract: Sign an annual price - difference contract. The contract electricity volume accounts for 60% of the predicted annual power generation, and the contract electricity price is 0.38 yuan / kWh. The default rate is set at 5% (simulating market risks).

[0065] Set risk factors. For hydrological risks, set seasonal runoff fluctuations (probability 30%), extreme rainstorms (probability 10%), and runoff reduction caused by upstream land reclamation for farming (probability 15%); For market risks, set a real - time electricity price volatility of 18%, contract default risk (trigger condition: oversupply in the market due to large - scale new energy generation), and consumption competition (triggered when the new - energy penetration rate exceeds 35%); For equipment risks, set water turbine failures (average annual occurrence rate of 3 times), main transformer tripping (probability 2%), and monitoring system anomalies (probability 1%); For policy risks, set an increase in ecological flow by 10% due to environmental protection inspections (probability 20%), and adjustment of time - of - use electricity price policy (re - division of peak and valley hours, probability 15%).

[0066] Build 4 types of typical scenarios based on historical data:

[0067] Benchmark scenario (50%): Normal hydrological conditions, real - time electricity price fluctuates ±10%, no equipment failures or policy changes.

[0068] Hydrological risk scenario (25%): Extreme heavy rain combined with runoff fluctuations, and the ecological flow constraint tightens.

[0069] Market risk scenario (15%): The real-time electricity price drops sharply by 20%, and contract customers default.

[0070] Compound risk scenario (10%): Heavy rain + electricity price drop + unit failure + ecological flow increase.

[0071] During the process of dynamic evaluation of the value of hydropower, calculate the available amount of hydropower, and analyze the water balance under different spatio-temporal scenarios through a distributed hydrological model:

[0072] Normal period (such as mid-May): The average precipitation is 3 mm / h, the evaporation is 1.2 mm / h, and the initial runoff is 280 m³ / s. Through model calculation, the available amount of hydropower is about 2.2 million kW·h / hour, meeting the ecological flow requirements (the downstream power station needs to ensure a minimum of 20 m³ / s, corresponding to a hydropower threshold of 1.8 million kW·h / hour).

[0073] Extreme heavy rain period (14:00 - 16:00 on July 12): The hourly rainfall is 20 mm / h, and the initial runoff surges to 1200 m³ / s. However, due to the ecological flow constraint (it is necessary to maintain more than 30 m³ / s), the actual available hydropower for power generation is 5.5 million kW·h / hour (25% less than the unconstrained scenario).

[0074] Conduct economic value conversion: Adopt a mixed pricing mechanism, and calculate the revenue weight of each period according to the real-time electricity price priority coefficient γ = 0.6:

[0075] Peak period (18:00 - 22:00): The real-time electricity price is 0.58 yuan / kWh, and the contract electricity price is 0.38 yuan / kWh. The weight ω = 0.6×0.58 / (0.58 + 0.38) = 0.36, that is, 36% of the hydropower value is determined by the real-time market, and 64% is guaranteed by the contract.

[0076] Normal period (06:00 - 18:00): The real-time electricity price is 0.42 yuan / kWh, and the weight ω = 0.6×0.42 / (0.42 + 0.38) = 0.315, and the revenue structure tends to be balanced.

[0077] Valley period (00:00 - 06:00): The real-time electricity price is 0.28 yuan / kWh, and the weight ω = 0.6×0.28 / (0.28 + 0.38) = 0.255. The proportion of contract revenue exceeds 70%.

[0078] The hydropower value curve of a typical day (July 15), such as Figure 2As shown, the value of water energy throughout the day fluctuates in the range of 620,000 - 1,150,000 yuan per hour. The peak appears at 19:00 (real-time electricity price of 0.62 yuan / kWh and available water energy of 3.2 million kW·h), and the trough appears at 03:00 (electricity price of 0.25 yuan / kWh and water volume of 2.1 million kW·h). In the extreme rainstorm scenario, despite the sharp increase in water volume, the ecological constraints result in only a 15% increase in value (from the benchmark value of 900,000 yuan per hour to 1,035,000 yuan per hour).

[0079] For the coupled analysis of multiple risk factors, for the identification of risk sources and the transmission path, a coupled network containing 4 categories and 12 risk factors is constructed:

[0080] Hydrological risk chain: Extreme rainstorm → Surge in runoff → Exceeding the reservoir water level limit → Increase in water abandonment → Decrease in water energy utilization rate.

[0081] Market risk chain: Large-scale new energy generation → Decrease in real-time electricity price → Reduction in spot income; Contract default → High-cost electricity purchase required for electricity shortage → Increase in cost.

[0082] Equipment risk chain: Turbine failure → Shutdown for maintenance → Reduction in output → Missing high-price periods; Abnormal monitoring system → Delayed scheduling → Waste of water volume.

[0083] Policy risk chain: Increase in ecological flow → Reduction in available power generation water volume; Adjustment of peak and valley periods → Reconstruction of income during high-value periods.

[0084] The risk transfer coefficient matrix T shows that the transfer intensity of hydrological risk to market risk (such as rainstorm causing unit shutdown and affecting spot market declaration), and the feedback intensity of equipment risk to hydrological risk (such as monitoring failure causing delayed flood scheduling).

[0085] Quantify the synergy effect. Taking hydrological risk and market risk as examples, the impact on the value of water energy when acting alone is ten thousand yuan, ten thousand yuan, and when acting together ten thousand yuan. The synergy effect weight (synergy effect of all combinations) = 0.33, indicating that the risk amplification effect is significant when the two are superimposed.

[0086] Identify the key risk sources. Analyze the contribution degree of each factor to the variance of income through the dynamic prediction model of income risk:

[0087] Fluctuation of real-time electricity price ( = 0.38), extreme rainstorm ( = 0.32) are the primary risk sources, with a combined contribution of more than 70% to the income fluctuation;

[0088] Equipment failure ( = 0.15) and ecological policy adjustment ( = 0.10) are secondary risk sources and become prominent under complex scenarios.

[0089] Through the revenue-risk dynamic prediction model, adopting the "input layer - attention mechanism layer - Bi-LSTM layer - output layer" architecture, the input data includes: dynamic hydropower value sequence (hourly data for the past 7 days), risk transfer coefficient matrix T (updated in real time), and synergy weight matrix Ω (corrected based on the latest risk events). Taking the data on July 10, 2024 as an example, the sliding time window contains the for the first 168 hours (7 days). After inputting into the model, the revenue probability distribution curve for the next 72 hours is output.

[0090] As Figure 3 shown, in the prediction result analysis, for the benchmark scenario prediction, the revenue probability distribution is normally distributed, with a mean of 9.2 million yuan per day, a standard deviation of 0.85 million yuan, and a 95% confidence interval of 7.5 - 10.9 million yuan; key risk sources: real-time electricity price fluctuations (affecting 35% of the standard deviation), runoff fluctuations (28%); for the hydrological risk scenario prediction, extreme rainstorms cause the revenue distribution to be right-skewed, the mean increases to 10.5 million yuan per day (due to increased water volume), but the standard deviation expands to 1.2 million yuan (due to increased risk of water abandonment and rising scheduling costs), and the probability of tail risk (revenue < 8 million yuan) increases from 5% to 12%; for the compound risk scenario prediction, under the superposition of rainstorm + electricity price decline + unit failure, the revenue mean drops sharply to 7.8 million yuan per day, the standard deviation reaches 1.8 million yuan, and the high-risk probability of revenue < 6 million yuan reaches 25%, and an emergency dispatching plan needs to be activated.

[0091] As Figure 4 shown, through backtesting with historical data, the prediction error of the model for the revenue mean is ±6.5%, the prediction error of the standard deviation is ±8.2%, and the identification accuracy rate of key risk sources is 91.7%, which is significantly better than the traditional ARIMA model (error ±12%).

[0092] Generate risk-revenue trade-off decisions and plans. Divide the revenue distribution into three scenarios: high (> 10 million yuan per day), medium (8 - 10 million yuan per day), and low (< 8 million yuan per day). Combine key risk sources to construct a four-dimensional evaluation system as shown in the following table:

[0093] Risk Response Strategy Implementation Cost (10,000 yuan / day) Revenue Enhancement Potential (10,000 yuan / day) Risk Mitigation Effect (Standard Deviation Reduction) Spot Ratio Reduced by 10% 20 -30 (Conservative Scenario) 15% Flood Control Storage Capacity Increased by 5% 15 -18 (Water Volume Reduction) 22% (Hydrological Risk Reduction) Equipment Inspection Frequency Increased 25 +12 (Reduction of Shutdown Loss) 10% (Equipment Risk Reduction) Purchase Electricity Price Insurance 30 +25 (Market Risk Hedging) 20%

[0094] Considering the peak shaving capacity (the output needs to be at least 800 MW during peak load hours) and the reservoir water storage status (1.5 billion cubic meters of flood control storage capacity needs to be reserved at the end of the flood season), generate the Pareto solution set through multi-objective programming:

[0095] Scenario A (Conservative): The spot ratio is 30%. Priority is given to executing contracts. The average daily return is 8.5 million yuan, with a standard deviation of 0.7 million yuan. It is suitable for risk-averse decision-makers.

[0096] Scenario B (Balanced): The spot ratio is 50%. Water volume allocation is dynamically adjusted. The average daily return is 9.5 million yuan, with a standard deviation of 1 million yuan. It is suitable for medium risk preferences.

[0097] Scenario C (Aggressive): The spot ratio is 70%. Emphasis is placed on power generation during high-price periods. The average daily return is 10.8 million yuan, with a standard deviation of 1.5 million yuan. It is suitable for risk-preferring entities.

[0098] By inputting extreme scenario parameters through the visualization interface, the system automatically generates risk curve graphs, return comparison tables, and sensitivity analyses;

[0099] Therefore, for the flood season in 2024, the following optimized dispatching was carried out for Power Station Group A using this method:

[0100] Risk control: During extreme rainstorms, the spot ratio is reduced to 20% in advance to avoid losses in spot returns caused by water abandonment. The actual return only decreases by 9% compared to the baseline prediction value (the traditional method predicts a decrease of 18%);

[0101] Return improvement: During periods when the real-time electricity price is higher than 0.5 yuan / kWh, the output is dynamically increased by 15%, and the spot return increases by 12% year-on-year;

[0102] Decision-making efficiency: Through the visualization interface, multi-department collaborative analysis is achieved. The dispatching decision-making time is reduced from 4 times a day on average to 2 times, and the emergency response speed is increased by 50%.

[0103] This embodiment details specific implementation technologies, achieving that the dynamic evaluation based on the value of water energy can accurately depict the spatio-temporal differences in hydropower station returns. The hybrid pricing mechanism effectively balances the opportunities in the spot market and contract risks. The risk factor coupling network can reveal the conduction paths among hydrology - market - equipment - policies. The synergy effect is quantified to provide a scientific basis for composite risk assessment. Through the deep learning model combined with the attention mechanism, the dynamic characteristics of risks can be captured in real time, and the prediction accuracy meets the actual dispatching requirements. In addition, the risk-return trade-off decision matrix provides customized solutions for entities with different risk preferences, enhancing the flexibility of the power station in dealing with complex scenarios.

[0104] The above are only the preferred embodiments of the present invention, and it does not thereby limit the protection scope of the present invention. For those skilled in the art, the present invention can have various changes and modifications; all changes, modifications, substitutions, integrations, and parameter changes made to these embodiments by means of conventional substitutions or capable of achieving the same functions without departing from the principle and spirit of the present invention fall within the protection scope of the present invention.

Claims

1. A method for measuring the revenue risk of a hydropower station based on the value of water energy, characterized in that It includes the following steps: S1: Construct a dynamic evaluation model for the value of water energy, collect real-time meteorological data, satellite remote sensing runoff data, and hydropower station equipment operation data within the basin, calculate the available water energy under different spatio-temporal scenarios in combination with a distributed hydrological model, and convert the available water energy into economic value based on the real-time electricity price in the power market, medium- and long-term contract price, and ecological flow constraint conditions to obtain the dynamic value of water energy; S2: Establish a multi-risk factor coupling network, determine risk sources, construct risk transmission paths, quantify the marginal impact of each risk factor on the value of water energy and power generation revenue, and calculate the synergy effect weight between risk factors; S3: Use the reinforcement learning algorithm to take the dynamic value of water energy and multi-risk factor coupling network data as inputs, construct a dynamic prediction model for revenue and risk, and update in real time to predict the probability distribution curve of power generation revenue within a preset future time period and identify key risk sources; S4: Construct a risk-reward trade-off decision matrix based on the prediction results and key risk sources output by the dynamic prediction model for revenue and risk, and generate revenue optimization plans under different risk response strategies in combination with the peak regulation and frequency modulation capabilities of the hydropower station and the reservoir water storage status; S5: Use a visualization interface to display the dynamic value of water energy, revenue and risk prediction results, and revenue optimization plans, support users to conduct multi-scenario simulation interaction analysis, and output visual risk curve graphs and revenue comparison charts.

2. The method for measuring the revenue risk of a hydropower station based on the value of water energy according to claim 1, wherein, In S1, the available water energy under different spatio-temporal scenarios is calculated by combining a distributed hydrological model. Specifically: the precipitation in the real-time meteorological data , evaporation , the initial runoff of the basin in the satellite remote sensing runoff data , and the water turbine efficiency in the hydropower station equipment operation data are substituted into the spatio-temporal coupling equation of the distributed hydrological model. The formula is: , where is the regional precipitation-runoff conversion coefficient, is the spatio-temporal correction parameter of the terrain slope; according to the head of the hydropower station , through the available water energy calculation formula , the available water energy under each spatio-temporal scenario is calculated. Among them, is the density of water, is the acceleration of gravity, represents the spatial grid number, represents the time node.

3. A method for measuring the revenue risk of a hydropower station based on the value of water energy according to claim 2, wherein In S1, based on the real-time electricity price in the power market, medium- and long-term contract price, and ecological flow constraint conditions, the available water energy is converted into economic value through the dynamic evaluation model of water energy value, specifically as follows: Get real-time electricity prices in the power market , medium- and long-term contract electricity prices , determine the threshold of water energy availability for power generation based on ecological flow constraints ; Construct the price weight distribution function, the formula is: ,in is the real-time electricity price priority adjustment coefficient, through the mixed pricing formula , calculate each time node Dynamic water energy value ,in The available water energy at a time node is used to obtain the dynamic water energy value.

4. A method for measuring the revenue risk of a hydropower station based on the value of water energy according to claim 1, characterized in that The risk sources determined in the multi-risk factor coupling network in S2 include hydrological risks, market risks, equipment risks, and policy risks; among them, hydrological risks include seasonal runoff fluctuation risks, water volume anomaly risks caused by extreme climates, and hydrological change risks caused by human activities within the basin; market risks cover real-time electricity price fluctuation risks in the power market, medium- and long-term contract default risks, and consumption competition risks brought about by new energy grid connection; equipment risks include water turbine generator set failure risks, aging risks of transmission and transformation equipment, and intelligent monitoring system failure risks; policy risks involve risks of increased compliance costs caused by environmental protection policies and risks of changes in revenue structure brought about by power system reform.

5. A method for measuring the revenue risk of a hydropower station based on the value of water energy, as claimed in claim 4, wherein In S2, the marginal impacts of each risk factor on the water energy value and power generation revenue are quantified by constructing a risk transmission path, and the synergy effect weights between risk factors are calculated. Specifically: A risk factor set is established , where represents the type of risk, and the risk transmission coefficient matrix is , where represents the transmission intensity of risk factor on . The marginal impact of risk factor on the water energy value is calculated using the marginal impact quantification formula. The formula is: , where is the partial derivative of the water energy value with respect to risk factor . The synergy effect weight between risk factor and is calculated using the synergy effect weight formula. The formula is: , where is the impact on the water energy value when risk factors and act together, are respectively the impact amounts on the water energy value when acting alone, is the impact on the water energy value when risk factors and act together, are respectively the impact amounts on the water energy value when acting alone, is the maximum value among the impacts of all risk factor combinations, and a quantitative analysis of the risk factor impacts and synergy effects is carried out.

6. The method for measuring the revenue risk of a hydropower station based on the value of water energy according to claim 1, wherein The dynamic prediction model for revenue and risk in S3 includes a deep learning architecture with an input layer, an attention mechanism layer, a bidirectional long short-term memory network layer (Bi-LSTM), and an output layer; the obtained dynamic water energy value sequence, risk factor transmission intensity matrix, and synergy effect weight matrix are used as input layer data; the attention mechanism layer adaptively assigns weights to different risk factors and time series data to highlight key risk information with a greater impact on revenue; the bidirectional long short-term memory network layer is used to capture the time-dependent relationship and bidirectional dynamic characteristics between risk factors and the value of water energy; in the output layer, through a probability density function fitting module, the probability distribution curve of power generation revenue within a preset future time period is output, where the probability density function uses a mixture Gaussian model, and the model parameters are optimized through the expectation maximization algorithm to realize the dynamic prediction of power generation revenue risk.

7. A method for measuring the revenue risk of a hydropower station based on the value of water energy, as claimed in claim 1 or 6, characterized in that In step S3, the probability distribution curve of power generation revenue within a preset future time period is predicted through the revenue-risk dynamic prediction model to identify key risk sources, specifically as follows: Obtain the data acquisition frequency as , and each time new dynamic hydropower value data , risk transfer coefficient matrix and synergy effect weight matrix are obtained, combine them with the historical data sequence to form sliding time window data , input it into the revenue-risk dynamic prediction model, use the bidirectional long short-term memory network layer in the revenue-risk dynamic prediction model to extract features from the time window data, combine the attention mechanism layer to reallocate the weights of each risk factor at the current moment, and calculate the probability density function of the power generation revenue within the preset future time period through the mixture Gaussian model in the output layer, where is the number of Gaussian distributions, , , , are respectively the mixing coefficient, mean and variance of the -th Gaussian distribution at the moment, so as to update the power generation revenue probability distribution curve. By calculating the contribution degree of each risk factor to the variance of the probability distribution curve, identify the risk factors whose contribution degree exceeds the set threshold as key risk sources, and the formula is: , is the variance of the power generation revenue , is the risk factor.

8. A method for measuring the revenue risk of a hydropower station based on the value of water energy according to claim 1, characterized in that, In step S4, a risk-reward trade-off decision matrix is constructed based on the prediction results output by the revenue-risk dynamic prediction model and the key risk sources. Specifically: the probability distribution curve of power generation revenue in the prediction results is divided into quantiles to form high, medium, and low revenue scenario sets. For each revenue scenario, an evaluation index system including four dimensions of risk response strategy, implementation cost, revenue improvement potential, and risk mitigation effect is constructed in combination with the type and impact degree of the key risk sources. The analytic hierarchy process is used to determine the relative weights of each dimension, calculate the objective weights of each evaluation index, and form a combined weight vector; the peak shaving and frequency modulation capabilities of the hydropower station and the reservoir water storage state constraint conditions are transformed into the boundary conditions of the decision space, and a multi-objective programming algorithm is used to generate a Pareto optimal solution set within the decision space. Each solution corresponds to a risk-reward trade-off scheme; cluster analysis is performed on the Pareto optimal solution set to form a finite number of representative decision scheme clusters. Each scheme cluster corresponds to the optimal decision strategy under different risk preferences, and a risk-reward trade-off decision matrix is constructed.

9. The method for measuring the revenue risk of a hydropower station based on the value of water energy according to claim 8, wherein In S4, the specific method of transforming the peak regulation and frequency modulation capabilities of the hydropower station and the reservoir water storage state constraint conditions into decision space boundary conditions, and using the multi-objective programming algorithm to generate the Pareto optimal solution set, and then forming the decision scheme cluster through cluster analysis is as follows: Define the decision variable set , where represents the implementation intensity of different risk response strategies; represent the peak regulation and frequency modulation capability constraint of the hydropower station as , and represent the reservoir water storage state constraint as , where and are the upper and lower limits of the peak regulation and frequency modulation power, and are the upper and lower limits of the reservoir water storage capacity, and are the influence coefficients of each strategy on the peak regulation power and the water storage state. Construct the decision space, and perform multi-objective optimization in the decision space through the non-dominated sorting genetic algorithm. Take maximizing the power generation benefit and minimizing the risk level as the objective functions, and update iteratively to obtain the Pareto optimal solution set; for each solution in the Pareto optimal solution set, calculate the Euclidean distance from other solutions. The formula is: , where is the number of objective functions, is the th objective function value. Set the density threshold and the neighborhood radius, and cluster the solutions with a distance less than the neighborhood radius and a density greater than the density threshold into the same cluster to form a finite number of representative decision scheme clusters. Each cluster corresponds to a decision scheme with similar risk-benefit characteristics.

10. A method for measuring the revenue risk of a hydropower station based on the value of water energy, as claimed in claim 1, wherein In step S5, the user can input custom scenario variables through the parameter adjustment panel, including but not limited to the electricity price fluctuation range and the probability of extreme hydrological events, and call the revenue-risk dynamic prediction model and the risk-reward trade-off decision matrix in real time to recalculate and generate visual charts corresponding to the scenarios. The visual components are associated for linkage analysis.

Images