Runoff prediction and water-electricity-hydrogen system combined scheduling method and device

Abstract

The invention relates to the technical field of hydroelectric generation, and discloses a runoff prediction and hydroelectric-hydrogen system combined scheduling method and device, and the method comprises the steps: obtaining the historical drought data of a target hydropower station, and carrying out the enhancement processing of the historical drought data, and obtaining a runoff enhancement data set; training a preset prediction model by using the runoff enhanced data set to obtain a trained prediction model; and obtaining runoff prediction data of the target hydropower station according to the preset sampling time by using the prediction model, the runoff prediction data including the predicted runoff volume of each preset sampling time, and performing energy scheduling on the hydropower-hydrogen system based on the annual income demand and the predicted runoff volume of the hydropower-hydrogen system. The historical runoff data is enhanced, the number of training samples of the prediction model is increased, the performance of the prediction model is improved, energy scheduling is carried out based on the annual income demand of the hydroelectric-hydrogen system, it is guaranteed that the annual income of the target hydropower station is maximum, and the toughness of the hydroelectric system under the extreme drought condition is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hydropower generation, and in particular to a method and device for joint scheduling of runoff prediction and hydropower-hydrogen system. Background Art

[0002] As global climate conditions change, drought has become one of the most destructive natural disasters that affect the reliability of hydropower supply. In recent years, changes in hydroclimatic and socioeconomic conditions have exacerbated the challenge of water shortage. Hydropower is the key to electricity supply and is highly dependent on hydrological conditions. Severe drought disasters directly affect the power generation flow of hydropower stations, and long-term insufficient power generation flow often leads to a reduction in renewable energy power generation. The widening supply and demand gap caused by insufficient power supply will trigger a series of chain reactions in social and economic fields. Therefore, effectively improving the resilience of the power grid to cope with the challenges of extreme drought has received widespread attention. Active defense before disasters, emergency recovery during disasters, and post-disaster recovery are key links in risk prevention and resilience improvement throughout the entire operation process.

[0003] First, runoff prediction under extreme drought conditions is a scientific and engineering challenge. The key to the problem lies in accurately establishing a small sample long-period runoff time series prediction model. Traditional physical models require the precise assignment of a large number of hydrological parameters, rich expert knowledge and high-quality data, which are difficult to promote. Most data-driven time models are difficult to adapt to the characteristics of small samples and high randomness. Secondly, extreme drought disasters often last for a long seasonal cycle. Even if accurate prediction and warning can be achieved, how to improve the power supply capacity of the system under the influence of drought disasters through resource allocation is also a major challenge. Summary of the invention

[0004] In view of this, the present invention provides a runoff prediction and a joint scheduling method and device for a hydropower-hydrogen system to solve the problem of improving the resilience of the hydropower system under extreme drought conditions through runoff prediction and resource allocation.

[0005] In a first aspect, the present invention provides a method for runoff prediction and joint scheduling of a hydropower-hydrogen system, the method comprising: Obtain historical drought data of the target hydropower station, perform data enhancement processing on the historical drought data, and obtain a runoff enhancement data set of the target hydropower station; The preset prediction model is trained using the runoff enhancement dataset to obtain a trained prediction model; Using the prediction model to obtain the runoff prediction data of the target hydropower station according to the preset sampling time, the runoff prediction data includes the predicted runoff volume at each preset sampling time; Energy dispatch of the hydropower-hydrogen system is carried out based on the annual revenue demand and predicted runoff of the hydropower-hydrogen system.

[0006] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided by the present invention increases the number of training samples of the prediction model by enhancing historical runoff data, improves the performance of the trained prediction model, performs energy scheduling based on the annual revenue demand of the hydropower-hydrogen system, ensures the maximum annual revenue of the target hydropower station, and improves the resilience of the hydropower system under extreme drought conditions.

[0007] In an optional implementation, historical drought data of a target hydropower station is obtained, and data enhancement processing is performed on the historical drought data to obtain a runoff enhancement data set of the target hydropower station, including: Obtain the hydrological frequency of historical runoff data of the target hydropower station according to a preset period, and classify the drought years according to the hydrological frequency of the historical runoff data; The historical runoff data in drought years are used as drought sample data. The drought sample data are enhanced based on the preset generative adversarial network to obtain enhanced sample data. The enhanced sample data and the drought sample data constitute the runoff enhanced data set of the target hydropower station.

[0008] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided by the present invention performs data enhancement processing on the historical runoff data of drought years, and combines the enhanced sample data and the real sample data into a runoff enhancement data set, so as to analyze the characteristics of the runoff data in drought years in a targeted manner, avoid the influence of the small number of runoff samples and the long cycle on the data prediction accuracy under extreme drought conditions, and improve the prediction accuracy of the runoff data in drought years.

[0009] In an optional implementation, a preset prediction model is trained using a runoff enhancement dataset to obtain a trained prediction model, including: The runoff enhancement dataset is divided into a training set, an experimental set, and a test set according to a preset ratio; Using the training set and the test set to train multiple preset prediction models, to obtain multiple trained prediction models; The test set is used to evaluate the performance of multiple trained prediction models, and the prediction model for runoff prediction is determined based on the evaluation results.

[0010] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided by the present invention utilizes the runoff enhancement data set to train multiple preset prediction models, and through evaluating the performance of each model, selects the model with the best performance as the prediction model for runoff prediction, so as to improve the accuracy of runoff prediction.

[0011] In an optional implementation, using a prediction model to obtain runoff prediction data of a target hydropower station according to a preset sampling time includes: Obtaining input features of the prediction model, the input features including: the runoff of the target hydropower station at a preset historical time, the runoff on the same day of the previous year, statistical features, and calendar features; Input features are fed into the prediction model to obtain the runoff prediction data for the target hydropower station on the day; The rolling window method is used to obtain the runoff prediction data of the target hydropower station according to the preset sampling time interval.

[0012] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided by the present invention extracts input features from three aspects: historical information, calendar features and statistical features, obtains the runoff prediction data of the day according to the input features, and uses a rolling window method to update the runoff prediction data to ensure the validity of the runoff prediction data.

[0013] In an optional implementation, energy scheduling of the hydropower-hydrogen system is performed based on the annual revenue demand and predicted runoff of the hydropower-hydrogen system, including: Construct the objective function of the annual revenue of the hydropower-hydrogen system:

[0014] Among them, Maximize means maximizing annual income, express The load of time, For the Hydropower stations in The amount of load loss at the moment, In addition, the parameter express The electricity price at the time, It represents the unit load loss, is a discrete scheduling time period, Scheduling time windows for units, The first hydroelectric power stations; When the objective function is the largest, the output ratio of hydrogen fuel cells and hydropower is obtained, and the output ratio is used as the optimal scheduling result for energy scheduling. Hydropower stations in The load loss at the moment is given by The output ratio of hydrogen fuel cells and hydropower at that moment is determined.

[0015] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided by the present invention sets the objective function of the hydropower-hydrogen system scheduling, calculates the annual profit according to the scheduling result, takes the maximum annual profit as the goal, determines the scheduling strategy when the annual profit is maximum, and ensures that the load loss of the hydropower-hydrogen system is minimized and the annual profit is maximized.

[0016] In an optional embodiment, the method further includes: According to the energy dispatch results, the first sensitivity of different hydropower proportions to load loss, the second sensitivity of different hydrogen equipment capacities to load loss under different hydropower proportions, and the third sensitivity of runoff to load loss under different hydropower proportions are analyzed; The runoff prediction data of the target hydropower station is obtained, and the hydropower ratio and hydrogen equipment capacity of the target hydropower station are adjusted according to the first sensitivity, the second sensitivity, and the third sensitivity.

[0017] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided by the present invention determines the influence of different hydropower proportions, hydrogen equipment capacities, and runoff volumes on load loss by conducting sensitivity analysis from three aspects, which is conducive to adjusting energy scheduling according to the sensitivity analysis results, improving the accuracy of energy scheduling, and reducing load loss.

[0018] In a second aspect, the present invention provides a runoff prediction and hydropower-hydrogen system joint scheduling device, the device comprising: A data enhancement module is used to obtain the historical drought data of the target hydropower station and perform data enhancement processing on the historical drought data to obtain a runoff enhancement data set of the target hydropower station; A model training module is used to train a preset prediction model using a runoff enhancement data set to obtain a trained prediction model; A runoff prediction module is used to obtain the runoff prediction data of the target hydropower station according to the preset sampling time using the prediction model, and the runoff prediction data includes the predicted runoff volume at each preset sampling time; The energy dispatching module is used to dispatch the energy of the hydropower-hydrogen system based on the annual revenue demand and predicted runoff of the hydropower-hydrogen system.

[0019] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0020] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to cause a computer to execute the method of the first aspect or any corresponding embodiment thereof.

[0021] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 is a flow chart of a method for joint scheduling of runoff prediction and hydropower-hydrogen system according to an embodiment of the present invention; Figure 2 is a bar chart of hydrogen equipment capacity required to eliminate load loss at different hydropower ratios in the runoff prediction and hydropower-hydrogen system joint scheduling method according to an embodiment of the present invention; Figure 3 It is a schematic diagram of the reduction of load loss under different hydrogen energy capacities and hydropower proportions in the runoff prediction and hydropower-hydrogen system joint scheduling method according to an embodiment of the present invention; Figure 4 is a schematic diagram of monthly load loss caused by drought under different hydropower ratios in a runoff prediction and a joint dispatching method of a hydropower-hydrogen system according to an embodiment of the present invention; Figure 5 is a schematic diagram of monthly load loss under different runoff levels and hydropower ratios during drought in a runoff prediction and a joint dispatching method for a hydropower-hydrogen system according to an embodiment of the present invention; Figure 6 is a flow chart of another runoff prediction and hydropower-hydrogen system joint scheduling method according to an embodiment of the present invention; Figure 7 is a schematic diagram of a joint scheduling process in a joint scheduling method for runoff prediction and a hydropower-hydrogen system according to an embodiment of the present invention; Figure 8 , Fig. 9 , Fig.10 They are schematic diagrams of daily runoff data of three hydropower stations in the same river basin in the past ten years (2010 to 2022) in the runoff prediction and joint dispatching method of the hydropower-hydrogen system according to an embodiment of the present invention; Fig.11 , Fig.12 , Fig.13 They are respectively schematic diagrams of QQ graphs of generated runoff data and real runoff data of three hydropower stations in the runoff prediction and joint dispatching method of hydropower-hydrogen system according to an embodiment of the present invention and probability distribution fitting results; Fig.14 , Fig.15 , Fig.16They are schematic diagrams of prediction results of three power stations by the XGBoost model in the runoff prediction and the joint dispatching method of the hydropower-hydrogen system according to an embodiment of the present invention; Fig.17 is a schematic diagram of typical load curves of three cascade hydropower stations taking into account seasonal changes in a runoff prediction and a joint dispatching method of a hydropower-hydrogen system according to an embodiment of the present invention; Fig.18 is a schematic diagram of optimized scheduling results in a joint scheduling method for runoff prediction and hydropower-hydrogen system according to an embodiment of the present invention; Fig.19 It is a schematic diagram of an optimal dispatching scheme for three cascade hydropower stations to discharge hydrogen fuel cells under load shedding in a runoff prediction and a combined dispatching method for a hydropower-hydrogen system according to an embodiment of the present invention; Fig. 20 is a schematic diagram of the recovery capacity of a hydropower system in an extreme drought year in a runoff prediction and a joint dispatching method of a hydropower-hydrogen system according to an embodiment of the present invention; Fig.21 is a structural block diagram of a runoff prediction and joint dispatching device for a hydropower-hydrogen system according to an embodiment of the present invention; Fig. 22 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0025] Given the urgency of climate change and growing energy demand, it is essential to develop clean, efficient and sustainable energy supply systems. Dynamic water resource redistribution is the basis for balancing the multi-purpose use of hydropower stations, while coordination with other renewable energy sources can improve the resilience of power systems that rely primarily on hydropower. However, such coordination requires a comprehensive consideration of the resource endowment of renewable energy. While most studies focus on responding to short-term flood disasters and long-term sustainability, scholars have also explored the use of various forms of energy and seasonal energy storage to promote cross-scale conversion and regulation of water, hydropower resources and energy to cope with the extreme drought disasters that have occurred frequently around the world in recent years.

[0026] Hydrogen is widely recognized as a clean, low-carbon energy source that can play a key role in decarbonizing challenging industries and achieving carbon reduction targets. Compared with pumped storage, it provides a more adaptable form of energy storage, enriches seasonal renewable energy storage methods, and contributes to the stability of energy supply.

[0027] Runoff prediction has been widely studied in various fields such as meteorology, hydrology and environmental science, resulting in the development of various runoff prediction models, which can be roughly divided into two categories: physical models and data-driven models. Physical models are built based on the operating mechanism of runoff and explicitly represent hydrological state variables and fluxes. Although physical models are widely used and have good interpretability, they require specific catchment parameters, expert knowledge and high-quality data. Data-driven models can learn complex behaviors from runoff data. Existing models are mainly designed for conventional scenarios and are not suitable for unconventional situations such as extreme droughts. Runoff patterns during extreme droughts are complex and difficult to extract from historical data. To address this issue, researchers have attempted to incorporate meteorological droughts into hydrological drought predictions and have partially demonstrated that incorporating antecedent precipitation can enhance runoff predictions during droughts. However, given that runoff involves multiple regions, it is difficult to establish the relationship between runoff and meteorological factors in these regions.

[0028] In order to improve the economic efficiency of the system, a large number of studies have been conducted on the optimal scheduling of hydropower-hydropower combined systems. These studies mainly use hydrogen energy for peak shaving arbitrage, participate in hydropower optimal scheduling through water electrolysis hydrogen production technology and hydrogen energy storage and conversion technology, and consider the volatility of electricity prices. In order to cope with the impact of runoff randomness in the environment, commonly used optimization scheduling methods include stochastic optimization methods considering short-term or long-term runoff distribution, online and multi-stage adaptive robust optimization methods, and model predictive control. Most of these studies are based on large sample historical runoff data or strong assumptions about the distribution of runoff data, and mainly focus on unit commitment strategies in hydropower scheduling and how to solve the nonlinear non-convex programming problem of hydropower generation more efficiently and accurately.

[0029] Runoff forecasting involves analyzing complex time series data with a high degree of randomness. However, few studies have combined runoff time series forecasting methods with hydropower scheduling decisions. Related research mainly focuses on applying grey system theory to hydropower generation, but this approach cannot accurately predict short-term events, especially extreme events.

[0030] To solve the above problems, an embodiment of the present invention provides a method for joint scheduling of runoff prediction and hydropower-hydrogen system, which can enhance the resilience of the system through advance prediction and early warning of extreme drought disasters and optimized scheduling during the event.

[0031] According to an embodiment of the present invention, an embodiment of a method for joint scheduling of runoff prediction and hydropower-hydrogen system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0032] In this embodiment, a runoff prediction and a combined dispatching method of a hydropower-hydrogen system is provided, which can be used in the above-mentioned computer system. Figure 1 is a flow chart of a method for joint scheduling of runoff prediction and hydropower-hydrogen system according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps: Step S101, obtaining historical drought data of a target hydropower station, and performing data enhancement processing on the historical drought data to obtain a runoff enhancement data set of the target hydropower station.

[0033] Specifically, due to changes in meteorological conditions, hydrological scenarios include many types: such as flood and dry years. In order to distinguish extremely dry years, the hydrological frequency of historical runoff data (the probability that a hydrological characteristic value appears greater than or less than a specified value) is calculated using the hydrological classification method Pearson III distribution, and the flood year, drought year, and extremely dry year are determined based on the hydrological frequency in the historical runoff data. This embodiment studies the runoff data of drought years and extremely dry years, so the historical drought data includes historical runoff data of drought years and extremely dry years. The runoff data of extremely dry years are usually very small, and it is difficult to support accurate runoff prediction in future extremely dry years, so it is necessary to enhance the small sample runoff data, convert the runoff data of extremely dry years into real runoff data, and use the real runoff data for data enhancement to obtain enhanced data. The real runoff data and enhanced data together constitute the runoff enhancement data set of the target hydropower station.

[0034] Step S102: Use the runoff enhancement data set to train the preset prediction model to obtain a trained prediction model. Specifically, perform an outlier test on the runoff enhancement data set and process the outlier data to obtain a valid runoff enhancement data set. The valid runoff enhancement data set is divided into a training set and a test set. Generally, the training set data accounts for 80% of the total data, and the test set data accounts for 20% of the total data. This is only an example, but not limited to this. To avoid the influence of data dimension, the formula is used. The training set is normalized, where is the maximum value in the training set, is the minimum value in the training set.

[0035] Step S103, using the prediction model to obtain the runoff prediction data of the target hydropower station according to the preset sampling time, the runoff prediction data including the predicted runoff volume at each preset sampling time.

[0036] Specifically, accurate runoff prediction relies on feature engineering. For univariate runoff series, the input features of the prediction model are extracted from historical information, calendar features and statistical features. The input features include but are not limited to: historical runoff data of the previous seven days, historical runoff data of the same day of the previous year, and the mean, variance, median, maximum and minimum values ​​of the past three days.

[0037] The input features are fed into the trained prediction model to obtain the runoff prediction data for the day. In order to obtain the runoff prediction value for the upcoming drought year, the rolling window method can be used to update the runoff prediction data every seven days.

[0038] Step S104, based on the annual revenue demand and predicted runoff of the hydropower-hydrogen system, energy scheduling is performed on the hydropower-hydrogen system. Specifically, in extremely dry years, the hydropower generation cannot meet the electricity demand of users, resulting in reduced revenue of the hydropower station. To increase the revenue of the hydropower station, water and hydrogen energy equipment are used to generate electricity together to increase the annual revenue of the hydropower station. In addition to using hydrogen energy equipment, thermal power generation, nuclear power generation and other methods can also be combined with hydropower generation to meet electricity demand and increase revenue. This is only an example, but not limited to this.

[0039] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided in this embodiment enhances the historical runoff data, increases the number of training samples of the prediction model, improves the performance of the trained prediction model, performs energy scheduling based on the annual revenue demand of the hydropower-hydrogen system, ensures the maximum annual revenue of the target hydropower station, and improves the resilience of the hydropower system under extreme drought conditions.

[0040] In some optional embodiments, the method further comprises: Step S105, based on the energy dispatch result, analyze the first sensitivity of different hydropower ratios to load loss, the second sensitivity of different hydrogen equipment capacities to load loss under different hydropower ratios, and the third sensitivity of runoff to load loss under different hydropower ratios.

[0041] Specifically, the proportion of hydropower refers to the proportion of total electricity demand that hydropower generation needs to bear. Load loss refers to the loss caused by the system's inability to meet load supply due to a shortage of power generation capacity or other reasons. The greater the load loss, the lower the profit. Therefore, the sensitivity of different hydropower proportions, different hydrogen equipment capacities under different hydropower proportions, and runoff under different hydropower proportions to load loss can be analyzed. Adjustments can be made based on the results of the sensitivity analysis to reduce load loss and increase profits.

[0042] (1) First sensitivity analysis: As shown in Table 1, it is the quantitative relationship between the proportion of hydropower in a hydropower station and the loss of load. The loss of load factor is selected as an indicator to measure the overall economic impact of drought on the system. It can be seen from Table 1 that when the proportion of hydropower exceeds 30%, the third hydropower station (HP3) will experience a loss of load, that is, the hydropower-hydrogen system will experience a loss of load; the first hydropower station (HP1), the second hydropower station (HP2), and the third hydropower station (HP3) are from upstream to downstream. The loss of load in the downstream hydropower station is more serious than that in the upstream hydropower station, which shows that compared with large hydropower stations, small hydropower stations are more sensitive to runoff changes and have higher requirements for runoff conditions. In the face of extreme drought disasters, the power generation capacity of large hydropower stations has become an important pillar for ensuring power supply.

[0043] Table 1

[0044] (2) Second sensitivity analysis: Assume that each power station is equipped with exactly the same hydrogen fuel cells, such as Fig.10 As shown in Table 2, the capacity of hydrogen equipment required to eliminate load loss under different hydropower ratios is shown. The vertical axis represents the capacity of hydrogen batteries and the horizontal axis represents the hydropower ratio. In increments of 10%, the bar chart shows the capacity of hydrogen equipment required for each power station to achieve zero load loss. Figure 2 The results show that starting from a 40% hydropower ratio, the system requires a certain amount of hydrogen energy equipment to ensure zero load loss of the corresponding power station. Figure 2 It can also be seen that when the hydrogen energy equipment capacity of the three power stations is three times the required maximum value, zero load loss can be guaranteed for all power stations. When the proportion of hydropower reaches 100%, the total required hydrogen energy equipment capacity is 78MW.

[0045] Table 2

[0046] Figure 3 The figure shows the reduction of load loss (VOLL) under different hydrogen energy capacities and hydropower ratios. The z-axis represents the reduction of load loss under the corresponding hydropower ratio compared with the scenario without hydrogen energy equipment, the y-axis represents the change in the hydropower ratio, and the x-axis represents the hydrogen energy equipment capacity under different hydropower ratios. It can be seen from the figure that when the hydropower ratio is the same, the larger the hydrogen energy equipment capacity, the greater the reduction in VOLL, but the marginal utility will decrease, and the threshold of marginal utility is proportional to the hydropower ratio. In addition, when the hydropower ratio remains at a low level, only the third hydropower station (blue bar chart) shows a reduction in VOLL, which is consistent with the Figure 2 The situation is consistent with .

[0047] (3) Third sensitivity analysis: According to runoff forecast, December is usually the month with the lowest runoff and the highest load demand. Therefore, December was selected as a representative drought month for monthly sensitivity analysis. Figure 4 The figure shows the monthly load loss caused by drought under different hydropower ratios. It can be clearly seen that the trend shown in the bar chart is consistent with Figure 2 The situation described in is very similar. Figure 5 The 3D bar graph in Figure 1 shows the monthly VOLL at different runoff levels and hydropower ratios during the drought period. It can be seen that when the runoff is in the range of 5 m³ / s to 42 m³ / s and the hydropower ratio is between 40% and 100%, the system's VOLL experiences an approximately exponential increase. In addition, as the hydropower ratio increases and the runoff decreases, the system's VOLL increases.

[0048] Step S106, obtaining the runoff prediction data of the target hydropower station, and adjusting the hydropower ratio and hydrogen equipment capacity of the target hydropower station according to the first sensitivity, the second sensitivity, and the third sensitivity.

[0049] Specifically, the impact of different runoff volumes on the system VOLL can better assist in prediction and early warning. For example, in the case where hydropower accounts for 100% of the supply, if the goal is to keep VOLL below 100 million kWh, the runoff volume needs to be monitored monthly. If the runoff volume is less than 23 cubic meters per second, hydrogen equipment needs to be introduced to maintain the normal operation of the system, just as an example, but not limited to this.

[0050] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided in this embodiment determines the influence of different hydropower proportions, hydrogen equipment capacities, and runoff volumes on load loss by conducting sensitivity analysis from three aspects, which is conducive to adjusting energy scheduling according to the sensitivity analysis results, improving the accuracy of energy scheduling, and reducing load loss.

[0051] In this embodiment, a runoff prediction and a combined dispatching method of a hydropower-hydrogen system is provided, which can be used in the above-mentioned computer system. Figure 6 is a flow chart of a method for joint scheduling of runoff prediction and hydropower-hydrogen system according to an embodiment of the present invention. Figure 6 As shown, the process includes the following steps: Step S201, obtaining historical drought data of a target hydropower station, and performing data enhancement processing on the historical drought data to obtain a runoff enhancement data set of the target hydropower station.

[0052] Specifically, the above step S201 includes: Step S2011, obtaining the hydrological frequency of historical runoff data of the target hydropower station according to a preset period, and classifying and determining drought years according to the hydrological frequency of the historical runoff data.

[0053] Specifically, Figure 7 The figure shows a schematic diagram of the process of runoff prediction and joint dispatch of hydropower-hydrogen system provided in this embodiment. The hydrological frequency of historical runoff data is analyzed using Pearson III distribution, and historical years are divided into five types according to the size of hydrological frequency: normal years, drought years, extremely drought years, wet years and extremely wet years.

[0054] The expression of Pearson type III distribution is: (1) Among them, F represents the hydrological frequency value, x represents the runoff value, , is the mean of x, are the coefficient of variation and the coefficient of skewness, respectively.

[0055] The classification standard formula is: (2) The hydrological frequency of annual runoff data is calculated according to formula (1), and each year is divided into corresponding types according to formula (2).

[0056] Step S2012, taking the historical runoff data of drought years as drought sample data, performing data enhancement processing on the drought sample data based on a preset generative adversarial network to obtain enhanced sample data, and the enhanced sample data and the drought sample data constitute a runoff enhanced data set of the target hydropower station.

[0057] Specifically, the data augmentation processing is implemented by using the DoppelGANger model, a data augmentation technique based on Generative Adversarial Networks (GAN). GAN is a popular scene generation method that involves the interaction between a generator and a discriminator, with the goal of refining the artificially generated data distribution until it approaches the real data distribution, eventually making the two indistinguishable. By carefully adjusting the parameters that control the generator and the discriminator, the model seeks to optimize the performance of the discriminator on real runoff series during extreme droughts while ensuring that synthetic samples obtain relatively high scores. This iterative process promotes the model's ability to internalize the unique distribution characteristics of actual sample data representing extreme drought conditions. The DoppelGANger model is a variant of GAN that is more suitable for time series such as runoff data, combining insights from specific fields with the latest advances in GAN to address fidelity challenges. On the one hand, in order to build a correlation model between measurements and their metadata, the DoppelGANger model separates the generation of metadata from the time series, inputs the corresponding metadata to the time series generator at each time step, and also introduces an auxiliary discriminator for generating metadata. Second, to solve the mode collapse problem, the GAN architecture of the DoppelGANger model generates randomized maximum and minimum boundaries and normalized time series, respectively, which can then be rescaled to the actual range. Third, to capture temporal correlation, the DoppelGANger model outputs batch samples instead of single samples. In addition, the DoppelGANger model can efficiently capture temporal correlation in long time series data.

[0058] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided in this embodiment performs data enhancement processing on the historical runoff data of drought years, and combines the enhanced sample data and the real sample data into a runoff enhancement data set, so as to analyze the characteristics of the runoff data in drought years in a targeted manner, avoid the influence of the small number of runoff samples and the long cycle on the data prediction accuracy under extreme drought conditions, and improve the prediction accuracy of the runoff data in drought years.

[0059] Step S202: using the runoff enhancement data set to train a preset prediction model to obtain a trained prediction model.

[0060] Specifically, the above step S202 includes: Step S2021, dividing the runoff enhancement dataset into a training set, a trial set and a test set according to a preset ratio.

[0061] Specifically, the runoff enhancement data set is divided into, for example: 70% as a training set, 10% as a trial set, and 20% as a test set, which is only used as an example, but not limited to this order.

[0062] Step S2022, using the training set and the test set to train multiple preset prediction models, to obtain multiple trained prediction models. Specifically, the preset prediction models may include: XGBoost, ARIMA and Prophet. The ARIMA model is a statistical method widely used in time series prediction, which is good at capturing various time structure characteristics in the data; the Prophet model is built based on the additive principle, including modules such as trend, seasonality and holiday effects, and is particularly suitable for processing time series data with significant seasonal fluctuations, and shows strong adaptability to missing data and trend changes.

[0063] The same runoff enhancement dataset is used to train three preset prediction models with different architectures to obtain the trained corresponding prediction models. The specific training process is a mature existing technology and will not be repeated here.

[0064] Step S2023, using the test set to perform performance evaluation on the trained multiple prediction models, and determining the prediction model for runoff prediction based on the evaluation results.

[0065] Specifically, in order to evaluate the performance of ARIMA, Prophet and XGBoost, two commonly used evaluation indicators, normalized root mean square error (NRMSE) and normalized mean absolute error (NMAE), were used. The evaluation results show that XGBoost has the smallest NRMSE and NMAE values ​​under mixed data, indicating that XGBoost has the best prediction effect, so XGBoost is used as the prediction model for runoff prediction.

[0066] The XGBoost model has the characteristics of low computational complexity, fast running speed and high accuracy, and is widely used in time series prediction. The XGBoost model consists of multiple decision trees. By continuously adding decision trees and splitting features until the growth conditions are met, a new function is learned to fit the residual of the final prediction, thereby completely growing a tree. After completing the model training process and obtaining multiple trees, each sample is classified into a leaf node according to the characteristics of the historical runoff data. Each tree corresponds to a score, and the sum of the scores of all trees is the predicted value of the sample.

[0067] The goal of the XGBoost model is to make the predicted runoff values ​​of all trees as close as possible to the corresponding true runoff values ​​while maximizing the generalization ability. The predicted runoff value can be expressed by the following formula: (3) in, represents the predicted runoff value, Represents the weight function of the kth tree.

[0068] In order to fit the residuals between the predicted values ​​of the previous trees and the corresponding true values, a new decision tree is introduced. The objective function (equivalent to the decision tree) is introduced by combining the loss function and the regularization function. The expression of the objective function is: (4) in, Indicates the actual runoff value corresponding to the predicted runoff value, Used to quantify the difference between the predicted outflow value and the true value, regularization term Used to adjust the complexity of the model. The calculation formula is as follows: (5) in, represents the complexity of the decision tree leaf node, Represents the number of leaf nodes in the decision tree. represents the regularization coefficient, Represents weight.

[0069] The XGBoost model uses the gradient boosting method to optimize the objective function and applies the second-order Taylor expansion in the loss function to accelerate the optimization process. The objective function of the first iteration is expressed as the second-order Taylor expansion: (6) in, is the first-order derivative, is the second-order derivative, is a constant term.

[0070] For formula (6), it can be simplified as: (7) Wherein, formula (7) is obtained by deleting all constant terms in formula (6).

[0071] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided in the embodiment of the present invention uses the runoff enhancement data set to train multiple preset prediction models, and through evaluating the performance of each model, selects the model with the best performance as the prediction model for runoff prediction to improve the accuracy of runoff prediction.

[0072] Step S203, using the prediction model to obtain the runoff prediction data of the target hydropower station according to the preset sampling time, and calculating the predicted hydropower generation according to the runoff prediction data.

[0073] Specifically, in the above step S203, the prediction model is used to obtain the runoff prediction data of the target hydropower station according to the preset sampling time, including: Step S2031, obtaining input features of the prediction model, the input features including: the runoff of the target hydropower station at a preset historical time, the runoff on the same day of the previous year, statistical features and calendar features.

[0074] Specifically, the preset historical time can be the previous seven days, and the statistical features include the mean, variance and median of the runoff data of the previous three days. The input features are the runoff values ​​of the previous seven days, the runoff values ​​on the same day of the previous year, the mean, variance and median of the runoff data of the previous three days, and calendar features.

[0075] Step S2032, input the input features into the prediction model to obtain the current day runoff prediction data of the target hydropower station. Specifically, input the input features into the prediction model, and use formula (7) to predict the current runoff prediction data of the target hydropower station.

[0076] Step S2033, using a rolling window method, obtaining the runoff prediction data of the target hydropower station according to a preset sampling time interval. Specifically, using the rolling window method, the runoff prediction data is updated every seven days to determine the runoff prediction value in future drought years.

[0077] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided in this embodiment extracts input features from three aspects: historical information, calendar features, and statistical features, obtains the runoff prediction data for the day based on the input features, and uses a rolling window method to update the runoff prediction data to ensure the validity of the runoff prediction data.

[0078] Step S204: energy scheduling of the hydropower-hydrogen system based on the annual revenue demand and predicted runoff of the hydropower-hydrogen system.

[0079] Specifically, the above step S204 includes: Step S2041, constructing the objective function of the annual revenue of the hydropower-hydrogen system: (8) Among them, Maximize means maximizing annual income, express The load of time, For the Hydropower stations in The amount of load loss at the moment, In addition, the parameter express The electricity price at the time, It represents the unit load loss, is a discrete scheduling time period, Scheduling time windows for units, The first A hydroelectric power station.

[0080] Specifically, in the constructed objective function, the load loss of the i-th hydropower station at time t is determined according to the power of the fuel cell and the scheduling results of hydropower generation. The predicted hydropower generation can be determined according to the runoff prediction value, and then the power of the hydrogen fuel cell is adjusted in combination with the predicted hydropower generation to maximize the objective function of annual revenue.

[0081] Energy dispatch based on the power of hydrogen fuel cells and predicted hydroelectric power generation must meet the following constraints: (1) Power balance constraints: ,in, Indicates Hydropower stations in The effort of the moment, Indicated in Moment The output of hydrogen fuel cells installed in each hydropower station; (2) The reservoir capacity of the target hydropower station is equal to the difference between the inflow and outflow of water. The reservoir capacity constraint is: ,in, and Respectively Moment The upper and lower limits of the water storage capacity of the reservoir; (3) Discharge flow constraints: , Respectively represent The minimum and maximum discharge of a reservoir; (4) Power generation flow constraints: ,in, Represents the The maximum flow capacity that a hydropower unit in a power station can withstand, For the The maximum overflow capacity of the aqueduct of each power station; (5) Constraints on hydropower generation: ,in, and They are Moment The maximum and minimum values ​​of power generation allowed for a hydropower station of this level; ,in, For the The output coefficient of a hydropower station, For the The water head of a hydropower station, For the Power stations in The power generation flow at the moment; (6) The power and hydrogen volume of hydrogen fuel cells are subject to the following constraints:

[0082] in, and They respectively represent the upper limit of hydrogen fuel cell power and the maximum hydrogen production per unit time.

[0083] Step S2042, when the objective function is the maximum, the output ratio of the hydrogen fuel cell and the hydropower is obtained, and the output ratio is used as the optimal scheduling result for energy scheduling. Hydropower stations in The load loss at the moment is given by The output ratio of hydrogen fuel cells and hydropower at that moment is determined.

[0084] Specifically, by adjusting the power of the hydrogen fuel cell, changing the hydrogen power generation, and combining it with the hydropower generation obtained based on the runoff prediction value, the objective function formula (8) is changed. Hydropower stations in By adjusting the power of the hydrogen fuel cell and changing the amount of hydrogen power generation, the output ratio of the hydrogen fuel cell and hydropower can be adjusted to reduce the amount of load loss and maximize the objective function of annual revenue.

[0085] The runoff prediction and joint scheduling method of the hydropower-hydrogen system provided in this embodiment sets the objective function of the hydropower-hydrogen system scheduling, calculates the annual profit according to the scheduling result, takes the maximum annual profit as the goal, determines the scheduling strategy when the annual profit is maximized, and ensures that the load loss of the hydropower-hydrogen system is minimized and the annual profit is maximized.

[0086] In a specific embodiment, the first hydropower station, the second hydropower station and the third hydropower station are all diversion-type hydropower stations, wherein the first hydropower station is connected to a reservoir with a certain regulating capacity. The basic parameters of the three hydropower stations are shown in Table 3.

[0087] Table 3

[0088] Figure 8 , Fig. 9 , Fig.10 These are the daily runoff data of three hydropower stations in the same basin in the past ten years (2010 to 2022). Generally speaking, May to August is the rainy season and December to April is the dry season, but there are differences in daily and monthly runoff in different years. In terms of runoff, the runoff of the first hydropower station (HP1) and the second hydropower station (HP2) is greater than that of the third hydropower station (HP3).

[0089] For each hydropower station, the Pearson III curve is used to fit the runoff data of ten years, and the optimal curve fitting method is used for calibration, and the runoff frequency values ​​of the past ten years are calculated. The coefficient of variation and skewness coefficient are set in advance as: , the hydrological frequency is calculated using the expression of Pearson type III distribution, and the years are divided into five categories. The classification criteria are shown in formula (2).

[0090] (1) Hydrological classification: Taking the first hydropower station as an example, the classification results of its historical annual runoff are detailed in Table 4. Since the stations are located in the same basin, the classification results are basically the same. Years with an average annual runoff frequency greater than 90% are defined as extremely dry years (Extremely wet years), and such years are called extreme drought events. The results show that since 2010, the average runoff in the basins where the three hydropower stations are located has been in the drought and extreme drought scenarios for six years, among which 2016 is the only year classified as extremely dry.

[0091] In the dry season from December to February, hydropower is generally not the main source of electricity supply. Only in the wet season from March to November does hydropower become the main source of electricity for regional consumption. Under this condition, extreme drought disasters occurring during the wet season have a greater impact on regional power supply. Therefore, in subsequent case studies, the focus is on runoff prediction under extreme drought disasters during the wet season and coordinated scheduling of the hydropower-hydrogen system.

[0092] Table 4

[0093] (2) Sample data enhancement: Quantiles are used to evaluate the distribution of data, and double quantile-quantile plots (double QQ plots) are used to compare the similarity of the probability distribution between two variables, thereby ensuring the validity and reliability of small sample data. In the QQ plot, the vertical axis and horizontal axis represent the quantiles of the generated sample and the original sample, respectively. If the points on the plot are distributed near the diagonal line passing through the origin, the probability distributions of the two variables are considered to be similar. In addition, the validity and accuracy of the generated samples can be further confirmed by comparing the probability distributions of the generated samples with those of the original samples.

[0094] The DoppelGANger algorithm is used to enhance the runoff data of three hydropower stations. Fig.11 , Fig.12 , Fig.13The QQ plots and probability distribution fitting results of the generated runoff data and real runoff data of the three hydropower stations are displayed. The results show that the real samples are generally consistent with the synthetic samples generated by the DoppelGANger algorithm in distribution, indicating that the DoppelGANger algorithm has successfully learned the runoff characteristics under extreme drought conditions and generated new samples that can reflect the characteristics of the real samples.

[0095] (3) Runoff prediction: In order to predict runoff more accurately, the data generated above are combined with the actual runoff data to create the initial data set for the prediction model (a total of 24 years of data are available in this embodiment). The data from the first 22 years are selected as the training set, and the remaining 2 years of data are used as the validation set and test set respectively. For input features, historical runoff (including runoff from the previous seven days), runoff on the same day of the previous year, statistical features (including the mean, variance, and median of runoff data from the past three days), and calendar features are selected.

[0096] In order to verify the effectiveness of XGBoost, ARIMA and Prophet can also be selected as comparison benchmarks. Two commonly used evaluation indicators, normalized root mean square error (NRMSE) and normalized mean absolute error (NMAE), are used.

[0097] Fig.14 , Fig.15 , Fig.16 The prediction results of the XGBoost model for three power stations are shown. In this figure, the black line represents the model's prediction value, while the red line represents the actual runoff. It can be found that the prediction value is similar to the actual runoff change trend of the three hydropower stations and is relatively close, indicating that the XGBoost model is a good choice for runoff prediction in extremely dry years.

[0098] Table 5 lists the prediction results of different models. It can be seen that XGBoost has the smallest NRMSE and NMAE values ​​under mixed data, indicating that the XGBoost model has the best prediction effect. Compared with the prediction model using original data, the prediction model using mixed data has better prediction effects on the three hydropower stations, indicating that more information can be discovered from mixed data with a larger sample size. In addition, for original data, ARIMA is usually better than Prophet and XGBoost because the ARIMA model is a statistical model and its parameter training does not rely on a large amount of data.

[0099] Table 5

[0100] (4) Energy dispatch: The runoff prediction results are used as input data. Fig.17The typical load curves of three cascade hydropower stations considering seasonal changes are shown. In order to verify the effectiveness of the prediction method and its impact on the system dispatch performance, Table 6 compares the absolute gap between the dispatch results using real runoff data and using different predicted data as input. The results show that the data generated by XGBoost+GAN is closest to the real system performance, and the system dispatch performance gap can be narrowed to 1.97%.

[0101] Table 6

[0102] Fig.18 The optimized dispatch results of three hydropower stations using XGBoost+GAN input runoff data are shown. The bar charts represent the monthly hydropower dispatch results of the hydropower stations, and the line charts represent the monthly load loss in extreme drought years. Fig.18 It can be seen that even with the support of relatively accurate runoff forecasts across seasons, load losses occur almost every month except January, and the load losses in the dry season are higher than those in the flood season. The trend of hydropower generation planning is consistent with the load curve.

[0103] Fig.19 The optimal dispatching scheme of three cascade hydropower stations using 10MW hydrogen fuel cells is shown. The bar graph shows the monthly hydropower dispatching results of the hydropower station, and the red bar graph shows the output of hydrogen fuel cells (HFC). The line graph shows the VOLL (loss load value) of each month in the drought year. When equipped with hydrogen fuel cells, the loss of load of HP1 and HP2 approaches 0. Although HP3 still has loss of load in the second half of the year, the total loss has shown a significant reduction. With the help of fuel cells, the hydropower generation in the dry season is relatively high, which can better support the hydropower supply in the dry season even in drought years.

[0104] Fig. 20 The blue shaded area indicates that the load shedding provided by the 10 MW hydrogen equipment was reduced by 196.92 million kWh compared to the case without hydrogen. The load shedding was reduced by 65.09% when the hydrogen equipment was used compared to the case without hydrogen.

[0105] In this embodiment, a runoff prediction and a joint scheduling device for a hydropower-hydrogen system are also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0106] This embodiment provides a runoff prediction and hydropower-hydrogen system joint scheduling device, such as Fig.21 As shown, including: The data enhancement module 501 is used to obtain historical drought data of a target hydropower station and perform data enhancement processing on the historical drought data to obtain a runoff enhancement data set of the target hydropower station.

[0107] The model training module 502 is used to train a preset prediction model using the runoff enhancement data set to obtain a trained prediction model.

[0108] The runoff prediction module 503 is used to obtain the runoff prediction data of the target hydropower station according to the preset sampling time using the prediction model, and the runoff prediction data includes the predicted runoff volume at each preset sampling time.

[0109] The energy scheduling module 504 is used to schedule the energy of the hydropower-hydrogen system based on the annual revenue demand and predicted runoff of the hydropower-hydrogen system.

[0110] In some optional implementations, the data enhancement module 501 includes: The drought year determination unit is used to obtain the hydrological frequency of the historical runoff data of the target hydropower station according to a preset period, and classify the drought year according to the hydrological frequency of the historical runoff data.

[0111] The sample data enhancement unit is used to use the historical runoff data of drought years as drought sample data, perform data enhancement processing on the drought sample data based on a preset generative adversarial network, and obtain enhanced sample data. The enhanced sample data and the drought sample data constitute the runoff enhancement data set of the target hydropower station.

[0112] In some optional implementations, the model training module 502 includes: The data division unit is used to divide the runoff enhancement data set into a training set, an experimental set and a test set according to a preset ratio.

[0113] The model training unit is used to train multiple preset prediction models using a training set and a test set to obtain multiple trained prediction models.

[0114] The performance evaluation unit is used to perform performance evaluation on multiple trained prediction models using a test set, and determine the prediction model for runoff prediction based on the evaluation results.

[0115] In some optional implementations, the runoff prediction module 503 includes: The input feature acquisition unit is used to acquire input features of the prediction model, and the input features include: the runoff of the target hydropower station at a preset historical time, the runoff on the same day of the previous year, statistical features and calendar features.

[0116] The current day runoff prediction unit is used to input the input features into the prediction model to obtain the current day runoff prediction data of the target hydropower station.

[0117] The prediction data acquisition unit is used to obtain the runoff prediction data of the target hydropower station according to a preset sampling time interval using a rolling window method.

[0118] In some optional implementations, the energy scheduling module 504 includes: The objective function construction unit is used to construct the objective function of the annual revenue of the hydropower-hydrogen system:

[0119] Among them, represents the maximization of annual income, express The load of time, For the Hydropower stations in The amount of load loss at the moment, In addition, the parameter express The electricity price at the time, It represents the unit load loss, is a discrete scheduling time period, Scheduling time windows for units, The first A hydroelectric power station.

[0120] The energy dispatching unit is used to obtain the output ratio of hydrogen fuel cells and hydropower when the objective function is the largest, and use the output ratio as the optimal dispatching result for energy dispatching. Hydropower stations in The load loss at the moment is given by The output ratio of hydrogen fuel cells and hydropower at that moment is determined.

[0121] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0122] The runoff prediction and joint scheduling device of the hydropower-hydrogen system in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0123] The embodiment of the present invention also provides a computer device having the above Fig.21 The runoff prediction and joint dispatching device of the hydropower-hydrogen system are shown.

[0124] See also Fig. 22 , Fig. 22 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Fig. 22 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig. 22 A processor 10 is taken as an example.

[0125] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0126] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0127] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0128] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory. The computer device also includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0129] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0130] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. The existence form of the computer program instruction in the computer-readable medium includes but is not limited to source files, executable files, installation package files, etc. Correspondingly, the way in which the computer program instruction is executed by the computer includes but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0131] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for runoff prediction and joint scheduling of hydropower-hydrogen system, characterized in that: The method comprises: Acquire historical drought data of a target hydropower station, and perform data enhancement processing on the historical drought data to obtain a runoff enhancement data set of the target hydropower station; Using the runoff enhancement data set to train a preset prediction model to obtain a trained prediction model; Using the prediction model to obtain runoff prediction data of the target hydropower station according to preset sampling times, the runoff prediction data including predicted runoff volumes at each preset sampling time; Energy dispatch of the hydropower-hydrogen system is performed based on the annual revenue demand of the hydropower-hydrogen system and the predicted runoff.

2. The method according to claim 1, characterized in that The historical drought data of the target hydropower station is obtained, and the historical drought data is subjected to data enhancement processing to obtain a runoff enhancement data set of the target hydropower station, including: Obtain the hydrological frequency of historical runoff data of the target hydropower station according to a preset period, and classify the drought years according to the hydrological frequency of the historical runoff data; The historical runoff data of the drought year is used as drought sample data, and data enhancement processing is performed on the drought sample data based on a preset generative adversarial network to obtain enhanced sample data. The enhanced sample data and the drought sample data constitute a runoff enhancement data set of the target hydropower station.

3. The method according to claim 1, characterized in that The preset prediction model is trained using the runoff enhancement data set to obtain a trained prediction model, including: Dividing the runoff enhancement dataset into a training set, a trial set and a test set according to a preset ratio; Using the training set and the test set to train multiple preset prediction models to obtain multiple trained prediction models; The test set is used to perform performance evaluation on the trained multiple prediction models, and a prediction model for runoff prediction is determined based on the evaluation results.

4. The method according to claim 1, characterized in that: The prediction model is used to obtain the runoff prediction data of the target hydropower station according to the preset sampling time, including: Acquiring input features of the prediction model, the input features including: runoff of a target hydropower station at a preset historical time, runoff on the same day of the previous year, statistical features, and calendar features; Inputting the input features into the prediction model to obtain the runoff prediction data of the target hydropower station on the same day; The rolling window method is used to obtain the runoff prediction data of the target hydropower station according to the preset sampling time interval.

5. The method according to claim 1, characterized in that Energy dispatching of the hydropower-hydrogen system is performed based on the annual revenue demand of the hydropower-hydrogen system and the predicted runoff, including: Construct the objective function of the annual revenue of the hydropower-hydrogen system: Among them, Maximize means maximizing annual income, express The load of time, For the Hydropower stations in The amount of load loss at the moment, In addition, the parameter express The electricity price at the time, It represents the unit load loss, is a discrete scheduling time period, Scheduling time windows for units, The first hydroelectric power stations; When the objective function is the largest, the output ratio of hydrogen fuel cells to hydropower is obtained, and the output ratio is used as the optimal scheduling result for energy scheduling. Hydropower stations in The load loss at the moment is given by The output ratio of hydrogen fuel cells and hydropower at that moment is determined.

6. The method according to claim 5, characterized in that The method further comprises: According to the energy dispatch results, the first sensitivity of different hydropower proportions to load loss, the second sensitivity of different hydrogen equipment capacities to load loss under different hydropower proportions, and the third sensitivity of runoff to load loss under different hydropower proportions are analyzed; The runoff prediction data of the target hydropower station is obtained, and the hydropower ratio and hydrogen equipment capacity of the target hydropower station are adjusted according to the first sensitivity, the second sensitivity, and the third sensitivity.

7. A runoff prediction and joint dispatching device for hydropower-hydrogen system, characterized in that: The device comprises: A data enhancement module is used to obtain historical drought data of a target hydropower station and perform data enhancement processing on the historical drought data to obtain a runoff enhancement data set of the target hydropower station; A model training module, used to train a preset prediction model using the runoff enhancement data set to obtain a trained prediction model; A runoff prediction module, used to obtain the runoff prediction data of the target hydropower station according to the preset sampling time by using the prediction model, wherein the runoff prediction data includes the predicted runoff volume at each preset sampling time; An energy scheduling module is used to schedule the energy of the hydropower-hydrogen system based on the annual revenue demand of the hydropower-hydrogen system and the predicted runoff.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method according to any one of claims 1 to 6.

Images