Hydropower station scheduling method, device, equipment, storage medium and program product

Abstract

The present application relates to the technical field of power dispatching, and discloses a hydropower station dispatching method, device, equipment, storage medium and program product, the hydropower station dispatching method comprising: predicting power and load to obtain power and load prediction values; performing prediction deviation analysis on the power prediction values and the load prediction values to obtain first and second probability distribution functions; performing scene analysis on the first and second probability distribution functions to generate a plurality of first power scenes and a plurality of first load scenes; performing clustering processing on the plurality of first power scenes and the plurality of first load scenes to obtain a plurality of first power and loads, a plurality of first and second occurrence probabilities; and taking the maximum residual load expectation, the minimum downstream tailwater level fluctuation expectation and the minimum downstream discharge fluctuation expectation as targets to determine a hydropower station dispatching scheme. The present application considers the downstream peak shaving effect, accurately dispatches the hydropower station, and improves practicability.

Description

Technical Field

[0001] This invention relates to the field of power dispatching technology, specifically to dispatching methods, devices, equipment, storage media, and program products for hydropower stations. Background Technology

[0002] Currently, new energy systems based on clean energy are becoming increasingly common. Multi-energy complementarity, as an important strategy in new energy systems, enhances the peak-shaving capacity of the power system and the stability of energy supply by integrating the advantages of different energy forms.

[0003] Wind power, photovoltaic power, and other new energy sources are generally considered non-regulatory power sources. Hydropower plays a crucial regulatory role in peak shaving at hydropower stations. In a typical cascade hydropower structure, upstream reservoirs with significant regulation capacity are usually constructed, while downstream reservoirs provide counter-regulation to reduce the impact of unstable upstream flow. Current methods for cascade hydropower stations participating in peak shaving only consider upstream peak shaving and downstream counter-regulation, neglecting the downstream station's counter-regulation needs and failing to fully utilize its peak shaving capacity. This results in inaccurate regulation processes that do not reflect reality and lack practicality. Summary of the Invention

[0004] In view of this, the present invention provides a method, apparatus, equipment, storage medium and program product for dispatching hydropower stations to solve the problem that the dispatching process is not accurate enough and does not conform to the actual situation.

[0005] In a first aspect, the present invention provides a method for scheduling a hydropower station, comprising: predicting the power of wind power or photovoltaic power based on historical power data to obtain a predicted power value; and predicting the load of the hydropower station based on historical load data to obtain a predicted load value; the historical power data is used to characterize the power data of wind power or photovoltaic power over a preset time period, and the historical load data is used to characterize the load data of the hydropower station over a preset time period; performing a prediction deviation analysis on the predicted power value and the measured power value to obtain a first probability distribution function corresponding to a first prediction deviation; performing a prediction deviation analysis on the predicted load value and the measured load value to obtain a second probability distribution function corresponding to a second prediction deviation; performing scenario analysis on the first probability distribution function to generate multiple first power scenarios; and performing scenario analysis on the second probability distribution function to generate multiple first power scenarios. Load scenarios; clustering is performed on multiple first power scenarios to obtain multiple first powers and multiple first occurrence probabilities corresponding to multiple target power typical scenarios; clustering is performed on multiple first load scenarios to obtain multiple first loads and multiple second occurrence probabilities corresponding to multiple target load typical scenarios; multiple first occurrence probabilities are used to characterize the probability of multiple target power typical scenarios occurring, and multiple second occurrence probabilities are used to characterize the probability of multiple target load typical scenarios occurring; based on multiple first powers, multiple first occurrence probabilities, multiple first loads, and multiple second occurrence probabilities, the hydropower station dispatching scheme is determined with the minimum expected maximum value of remaining load as the first optimization objective function, the minimum expected fluctuation of downstream tailwater level as the second optimization objective function, and the minimum expected fluctuation of downstream discharge flow as the third optimization objective function.

[0006] This invention first predicts the power output of a hydropower station based on wind or solar power power data for a preset time period, obtaining a predicted power value. It then predicts the load of the hydropower station based on historical load data used to characterize the load data for that preset time period, obtaining a predicted load value. Predicting future power and load based on historical data facilitates subsequent analysis based on future power and load, providing a data foundation for generating subsequent hydropower station scheduling plans. This invention performs prediction deviation analysis on the predicted power value and the measured power value, obtaining a first probability distribution function corresponding to the first prediction deviation; it also performs prediction deviation analysis on the predicted load value and the measured load value, obtaining a second probability distribution function corresponding to the second prediction deviation. This prediction deviation analysis identifies the deviations between the predicted power value and the predicted load value, facilitating the analysis of the causes of deviations, reducing the occurrence of similar problems, and making subsequent hydropower station scheduling plans more accurate. This invention performs scenario analysis on a first probability distribution function to generate multiple first power scenarios; performs scenario analysis on a second probability distribution function to generate multiple first load scenarios; performs clustering processing on the multiple first power scenarios to obtain multiple first powers and multiple first occurrence probabilities corresponding to multiple typical target power scenarios; and performs clustering processing on the multiple first load scenarios to obtain multiple first loads and multiple second occurrence probabilities corresponding to multiple typical target load scenarios. This invention analyzes typical scenarios of power and load to make the subsequently generated hydropower station dispatching scheme more consistent with the actual situation. This invention, based on multiple first power levels, multiple first occurrence probabilities, multiple first load levels, and multiple second occurrence probabilities, uses minimizing the expected maximum value of the remaining load as the first optimization objective function, minimizing the expected fluctuation of the downstream tailwater level as the second optimization objective function, and minimizing the expected fluctuation of the downstream discharge flow as the third optimization objective function to determine the hydropower station dispatching scheme. Compared with related technologies that only consider the peak-shaving of upstream power stations, this invention integrates the operational constraints of the downstream counter-regulating reservoirs into the multi-energy complementary dispatching of water, wind, and solar power. It considers the counter-regulation needs of downstream hydropower stations, fully utilizes the peak-shaving role of downstream hydropower stations, and takes into account the uncertainties of wind power, photovoltaic power output, and day-ahead load forecasting to generate a hydropower station dispatching scheme. This effectively coordinates the relationship between the operating status and dispatching capacity of the cascade counter-regulating reservoirs. Under the comprehensive consideration of the operational constraints of the cascade counter-regulating reservoirs, it maximizes the dispatching role of multi-energy complementary water, wind, and solar power, making the regulation process more accurate, more in line with actual conditions, and improving practicality.

[0007] In one optional implementation, a hydropower station scheduling scheme is determined based on multiple first power values, multiple first occurrence probabilities, multiple first load values, and multiple second occurrence probabilities, with the minimum expected maximum value of remaining load as the first optimization objective function, the minimum expected fluctuation of downstream tailwater level as the second optimization objective function, and the minimum expected fluctuation of downstream discharge flow as the third optimization objective function. This includes: constructing a multi-objective scheduling model based on the multiple first power values, multiple first occurrence probabilities, multiple first load values, and multiple second occurrence probabilities; the optimization objectives of the multi-objective scheduling model include minimizing the expected maximum value of remaining load as the first optimization objective function, minimizing the expected fluctuation of downstream tailwater level as the second optimization objective function, and minimizing the expected fluctuation of downstream discharge flow as the third optimization objective function; the inputs to the multi-objective scheduling model are the multiple first power values, multiple first occurrence probabilities, multiple first load values, and multiple second occurrence probabilities, and the output of the multi-objective scheduling model is the optimized solution set; solving the multi-objective scheduling model yields the optimized solution set; the optimized solution set is used to characterize the solution set of optimized data for scheduling the hydropower station; selecting target scheduling data from the optimized solution set, and generating a hydropower station scheduling scheme based on the target scheduling data; wherein, the target scheduling data is used to characterize the optimal scheduling data.

[0008] This invention integrates the operational constraints of downstream counter-regulating reservoirs into the multi-energy complementary scheduling of hydropower, wind power, and solar power, taking into account the uncertainties of wind power, solar power output, and day-ahead load forecasting. Combining multiple typical scenarios, it constructs a multi-objective optimization scheduling model under the constraints of cascade counter-regulation, solves the multi-objective scheduling model to obtain an optimal solution set, which includes multiple scheduling data with good scheduling effects. The optimal scheduling data is selected from the optimal solution set to generate a hydropower station scheduling scheme, thereby improving the accuracy of multi-energy complementary scheduling of hydropower, wind power, and solar power.

[0009] In one optional implementation, the power of wind power or photovoltaic power is predicted based on historical power data to obtain a power prediction value, and the load of hydropower station is predicted based on historical load data to obtain a load prediction value. This includes: inputting historical power data into a trained power prediction model to obtain a power prediction value, wherein the input of the power prediction model is historical power data and the output of the power prediction model is the power prediction value; and inputting historical load data into a trained load prediction model to obtain a load prediction value, wherein the input of the load prediction model is historical load data and the output of the load prediction model is the load prediction value.

[0010] This invention is based on a power prediction model and a load prediction model. It predicts power and load based on historical power data and historical load data, ensuring the accuracy of the predicted power and load values, thereby improving the accuracy of the subsequent hydropower station dispatching scheme.

[0011] In one optional implementation, a prediction deviation analysis is performed on the predicted power value and the measured power value to obtain a first probability distribution function corresponding to the first prediction deviation; a prediction deviation analysis is performed on the predicted load value and the measured load value to obtain a second probability distribution function corresponding to the second prediction deviation, including: taking the difference between the measured power value and the predicted power value as the first prediction deviation; performing a probability distribution analysis on the first prediction deviation to obtain the first probability distribution function; taking the difference between the measured load value and the predicted load value as the second prediction deviation; and performing a probability distribution analysis on the second prediction deviation to obtain the second probability distribution function.

[0012] In one optional implementation, scenario analysis is performed on the first probability distribution function to generate multiple typical first power scenarios; scenario analysis is performed on the second probability distribution function to generate multiple typical first load scenarios, including: performing a preset number of random samplings on the first probability distribution function of the hydropower station dispatch scheme to obtain multiple first sampling results; generating multiple typical first power scenarios based on the multiple first sampling results and the first prediction deviations corresponding to the multiple first sampling results; performing a preset number of random samplings on the second probability distribution function to obtain multiple second sampling results; and generating multiple typical first load scenarios based on the second prediction deviations corresponding to the multiple second sampling results and the multiple first sampling results.

[0013] In one optional implementation, clustering is performed on multiple first power scenarios to obtain multiple first powers and multiple first occurrence probabilities corresponding to multiple target power typical scenarios; clustering is performed on multiple first load scenarios to obtain multiple first loads and multiple second occurrence probabilities corresponding to multiple target load typical scenarios, including: selecting a preset number of first power scenarios as initial power typical scenarios from the multiple first power scenarios; calculating the distance from each first power scenario to the initial power typical scenario to obtain multiple first target distances; assigning each first power scenario to the initial power typical scenario with the closest first target distance to obtain multiple first clustering groups; and grouping according to the multiple first clusters. In the first power scenario of the group, multiple target power typical scenarios are generated; multiple first powers and multiple first occurrence probabilities are obtained corresponding to the multiple target power typical scenarios; among the multiple first load scenarios, a preset number of first load scenarios are selected as initial load typical scenarios; the distance from each first load scenario to the initial load typical scenario is calculated to obtain multiple second target distances; each first load scenario is assigned to the initial load typical scenario with the closest second target distance to obtain multiple second clustering groups; multiple target load typical scenarios are generated based on the first load scenarios in the multiple second clustering groups; multiple first loads and multiple second occurrence probabilities are obtained corresponding to the multiple target load typical scenarios.

[0014] In one alternative implementation, the first optimization objective function is:

[0015]

[0016] Where F1 represents the first optimization objective function, min represents taking the minimum value, max represents taking the maximum value, and p k P represents the first probability of occurrence corresponding to typical scenario k of target power or the second probability of occurrence corresponding to typical scenario k of target load, where K represents the total number of typical scenarios of target power or the total number of typical scenarios of target load. k,t This represents the first power of the target power typical scenario k during the time period t, or the first load of the target load typical scenario k during the time period t. This represents the power generation of hydropower in time period t under typical scenario k of target power or typical scenario k of target load. This represents the power generation of wind power in the time period t under the typical scenario k of the target power or the typical scenario k of the target load. This represents the power generation of photovoltaics in time period t under the typical scenario k of the target power or the typical scenario k of the target load.

[0017] In one alternative implementation, the second optimization objective function is:

[0018]

[0019] Where F2 represents the second optimization objective function, min represents taking the minimum value, max represents taking the maximum value, and p k Z represents the first probability of occurrence corresponding to typical scenario k of target power or the second probability of occurrence corresponding to typical scenario k of target load, where K represents the total number of typical scenarios of target power or the total number of typical scenarios of target load. k,t+1 Z represents the water level during time period t+1 under typical scenario k of target power or target load. k,t This represents the water level over time period t under typical scenario k of target power or typical scenario k of target load.

[0020] In one alternative implementation, the third optimization objective function is:

[0021]

[0022] Where F3 represents the third optimization objective function, min represents taking the minimum value, and p k Q represents the first probability of occurrence corresponding to typical scenario k of target power or the second probability of occurrence corresponding to typical scenario k of target load. k,t+1 Q represents the flow rate in time period t+1 under typical target power scenario k or typical target load scenario k. k,t This represents the flow rate over time period t under typical target power scenario k or typical target load scenario k.

[0023] Secondly, the present invention provides a hydropower station dispatching device, comprising: a power and load prediction module, used to predict the power of wind power or photovoltaic power based on historical power data to obtain a power prediction value, and to predict the load of the hydropower station based on historical load data to obtain a load prediction value; the historical power data is used to characterize the power data of wind power or photovoltaic power over a preset time period, and the historical load data is used to characterize the load data of the hydropower station over a preset time period; a prediction deviation analysis module, used to perform prediction deviation analysis on the power prediction value and the measured power value to obtain a first probability distribution function corresponding to a first prediction deviation; and to perform prediction deviation analysis on the load prediction value and the measured load value to obtain a second probability distribution function corresponding to a second prediction deviation; and a scene generation module, used to perform scene analysis on the first probability distribution function to generate multiple first power scenes; and to perform scene analysis on the second probability distribution function. The system generates multiple first-load scenarios; a clustering analysis module is used to perform clustering analysis on multiple first-power scenarios to obtain multiple first-power and multiple first-occurrence probabilities corresponding to multiple target-power typical scenarios; a clustering analysis is also performed on multiple first-load scenarios to obtain multiple first-load and multiple second-occurrence probabilities corresponding to multiple target-load typical scenarios; multiple first-occurrence probabilities are used to characterize the probability of multiple target-power typical scenarios occurring, and multiple second-occurrence probabilities are used to characterize the probability of multiple target-load typical scenarios occurring; an optimization scheduling module is used to determine the hydropower station scheduling scheme based on multiple first-power, multiple first-occurrence probabilities, multiple first-load, and multiple second-occurrence probabilities, with the minimum expected maximum value of remaining load as the first optimization objective function, the minimum expected fluctuation of downstream tailwater level as the second optimization objective function, and the minimum expected fluctuation of downstream discharge as the third optimization objective function.

[0024] Thirdly, 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 computer instructions to perform the hydropower station scheduling method described in the first aspect or any corresponding embodiment thereof.

[0025] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the hydropower station scheduling method described in the first aspect or any corresponding embodiment thereof.

[0026] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute the hydropower station scheduling method described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of the present invention, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 This is a flowchart illustrating the scheduling method of a hydropower station according to an embodiment of the present invention;

[0029] Figure 2 This is a flowchart illustrating another hydropower station dispatching method according to an embodiment of the present invention;

[0030] Figure 3 This is a flowchart illustrating another hydropower station dispatching method according to an embodiment of the present invention;

[0031] Figure 4 This is a flowchart illustrating the scheduling method of another hydropower station according to an embodiment of the present invention;

[0032] Figure 5 These are schematic diagrams of power curves under different photovoltaic scenarios at different times according to embodiments of the present invention;

[0033] Figure 6 These are schematic diagrams of power curves under different wind power scenarios at different times according to embodiments of the present invention;

[0034] Figure 7 These are schematic diagrams of power curves under different time periods and load scenarios according to embodiments of the present invention;

[0035] Figure 8 This is a structural block diagram of a hydropower station dispatching device according to an embodiment of the present invention;

[0036] Figure 9 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] Currently, the use of new energy sources, primarily clean energy, is becoming increasingly widespread, and it is becoming increasingly important to effectively improve the clean utilization level of new energy. Multi-energy complementarity, as an important means of utilizing new energy, enhances the peak-shaving capacity of the power system and the stability of energy supply by integrating different forms of energy.

[0039] In response to the widening peak-valley load difference in some regional power systems, the participation of hydropower stations in grid peak shaving is particularly important. Hydropower stations can utilize the regulating capacity of hydropower, combined with the intermittent nature of wind and solar power generation, to achieve more flexible and economical power production.

[0040] In a typical cascade hydropower structure, a reservoir with significant regulation capacity is usually built upstream, while a counter-regulation reservoir is configured downstream to reduce the impact of unstable water flow from the upstream reservoir on the downstream. How to leverage the downstream peak-shaving capacity of a multi-energy complementary system containing typical cascade reservoirs (hydropower, wind power, and solar power) is a pressing problem that needs to be solved.

[0041] This invention provides a method for scheduling a hydropower station, which integrates the operational constraints of the downstream counter-regulating reservoirs into the peak-shaving scheduling of a hydro-wind-solar multi-energy complementary system to maximize the peak-shaving effect.

[0042] According to an embodiment of the present invention, a method for scheduling a hydropower station is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0043] This embodiment provides a method for scheduling a hydropower station, which can be used with computer equipment. Figure 1 This is a flowchart of a hydropower station scheduling method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0044] Step S101: Based on historical power data, predict the power of wind power or photovoltaic power to obtain a power prediction value, and based on historical load data, predict the load of hydropower station to obtain a load prediction value; historical power data is used to characterize the power data of wind power or photovoltaic power in a preset time period, and historical load data is used to characterize the load data of hydropower station in a preset time period.

[0045] In some optional implementations, the power of wind power or photovoltaic power is predicted based on historical power data to obtain a power prediction value, and the load of hydropower station is predicted based on historical load data to obtain a load prediction value. This includes: inputting historical power data into a trained power prediction model to obtain a power prediction value, wherein the input of the power prediction model is historical power data and the output of the power prediction model is the power prediction value; and inputting historical load data into a trained load prediction model to obtain a load prediction value, wherein the input of the load prediction model is historical load data and the output of the load prediction model is the load prediction value.

[0046] In some alternative implementations, the power of wind power and / or photovoltaic power is predicted based on historical power data to obtain a power prediction value, which can be a wind power and / or photovoltaic power prediction value.

[0047] The power forecast values ​​are for wind power or solar power. Since wind power or solar power variations are affected by meteorological factors, generator characteristics, and generator status, historical power data includes historical wind power or solar power data, meteorological factors such as wind speed, radiation intensity, and temperature at the corresponding time, and generator status data for hydropower stations. Grid load variations are affected by their own characteristics, meteorological factors, and date type; therefore, historical load data includes historical load, meteorological, and weekday data.

[0048] In some optional implementations, the power prediction model is a wind power / solar power short-term prediction model built on a Long Short-Term Memory (LSTM) network. The wind power / solar power short-term prediction model can make short-term predictions of wind power or solar power. For example, the wind power or solar power of the next day can be predicted based on the historical wind power or solar power data of the previous day.

[0049] In some alternative implementations, the load forecasting model is a day-ahead load forecasting model built on a Long Short-Term Memory (LSTM) network. The day-ahead load forecasting model can predict the day-ahead load. For example, it can use historical load data from the previous day to predict the load for the next day.

[0050] In some alternative implementations, the hydropower station scheduling method further includes: predicting the power output of wind or solar power based on historical runoff data to obtain predicted runoff values.

[0051] The process of predicting wind or solar power output based on historical runoff data to obtain runoff prediction values ​​includes: inputting historical runoff data into a trained runoff prediction model to obtain runoff prediction values. The input to the runoff prediction model is historical runoff data, and the output of the runoff prediction model is the runoff prediction value.

[0052] Runoff variation is influenced by hydrological and meteorological factors; therefore, historical runoff data includes historical runoff, rainfall, and evaporation data. The runoff prediction model is a day-ahead runoff prediction model built on a Long Short-Term Memory (LSTM) network. This model is used to predict day-ahead runoff; for example, it uses the previous day's historical runoff data to predict the runoff for the following day.

[0053] Step S102: Perform prediction deviation analysis on the predicted power value and the measured power value to obtain the first probability distribution function corresponding to the first prediction deviation; perform prediction deviation analysis on the predicted load value and the measured load value to obtain the second probability distribution function corresponding to the second prediction deviation.

[0054] Since the power prediction value is the wind power or photovoltaic power prediction value, a prediction deviation analysis is performed on the power prediction value and the measured power value to obtain the first probability distribution function corresponding to the first prediction deviation. This includes: performing a prediction deviation analysis on the wind power prediction value and the measured wind power value to obtain the first probability distribution function corresponding to the first prediction deviation, or performing a prediction deviation analysis on the photovoltaic power prediction value and the measured photovoltaic power value to obtain the first probability distribution function corresponding to the first prediction deviation.

[0055] In some optional implementations, the first prediction deviation is the difference between the predicted power value and the measured power value, and the formula for the first prediction deviation is:

[0056] E1 = P 1 -P 2 ;

[0057] Where E1 is the first prediction bias, P 1 P represents the predicted power output of wind or solar power. 2 This represents the measured power output of wind or solar power.

[0058] Specifically, the kernel density estimation method is used to calculate the first probability distribution function corresponding to the first prediction deviation.

[0059] In some optional implementations, the second prediction deviation is the difference between the predicted load value and the measured load value, and the formula for the second prediction deviation is:

[0060] E2 = P 3 -P 4 ;

[0061] Where E2 is the second prediction bias, P 3 P is the load forecast value. 4 This is the actual measured load value.

[0062] Specifically, the kernel density estimation method is used to calculate the second probability distribution function corresponding to the second prediction bias.

[0063] Step S103: Perform scenario analysis on the first probability distribution function to generate multiple first power scenarios; perform scenario analysis on the second probability distribution function to generate multiple first load scenarios.

[0064] In some optional implementations, multiple random samplings are performed in the first probability distribution function to obtain a first sampling result, and the first sampling result is added to the power prediction value to obtain multiple first power scenarios; multiple random samplings are performed in the second probability distribution function to obtain a second sampling result, and the second sampling result is added to the load prediction value to obtain multiple first load scenarios.

[0065] For example, the formula for the power corresponding to the first power scenario is:

[0066]

[0067] in, Let be the power in time period t under the i-th first power scenario; The predicted wind or solar power output for time period t. This represents the first prediction bias of the vth sampling in time period t.

[0068] The formula for the load corresponding to the first load scenario is:

[0069]

[0070] in, Let be the load during time period t under the i-th first load scenario; The load forecast value for time period t. This represents the second prediction bias of the vth sampling in time period t.

[0071] Step S104: Cluster the multiple first power scenarios to obtain multiple first powers and multiple first occurrence probabilities corresponding to multiple target power typical scenarios; cluster the multiple first load scenarios to obtain multiple first loads and multiple second occurrence probabilities corresponding to multiple target load typical scenarios; the multiple first occurrence probabilities are used to characterize the probability of multiple target power typical scenarios occurring, and the multiple second occurrence probabilities are used to characterize the probability of multiple target load typical scenarios occurring.

[0072] In some optional implementations, a preset number of scenarios are randomly selected from a variety of first power scenarios as initial typical scenarios. The distance from each first power scenario to the initial typical scenario is calculated, and the first power scenario is assigned to the nearest initial typical scenario. The average power of all first power scenarios in each initial typical scenario is taken as the target power typical scenario. The target power typical scenarios to which each first power scenario belongs are reassigned until the target power typical scenarios no longer change, thus obtaining multiple first powers corresponding to the final K target power typical scenarios and multiple first occurrence probabilities of K1 target power typical scenarios.

[0073] For example, the formula for calculating the distance from each first power scenario to the typical target power scenario is as follows:

[0074]

[0075] in, Let i be the first distance from the first power scenario i to the target power typical scenario k. Let be the power in time period t under the i-th first power scenario. Let K1 be the power of the target power typical scenario k in time period t, N1 be the total number of the first power scenario, and K1 be the total number of the target power typical scenarios.

[0076] The formula for calculating the power of target power k in a typical scenario over time period t is as follows:

[0077]

[0078] in, For a typical scenario of target power, k represents the power during time interval t. Let be the number of first power scenarios belonging to the target power typical scenario k. Let k be the power of the target power in a typical scenario during the time period t.

[0079] In some optional implementations, the formula for calculating the first occurrence probability of a typical scenario with the first power scenario target power is:

[0080]

[0081] in, The probability of occurrence is the first. N1 represents the number of first power scenarios belonging to the target power typical scenario k, and N1 represents the total number of first power scenarios.

[0082] In some optional implementations, a preset number of scenarios are randomly selected from a variety of first load scenarios as initial typical scenarios. The distance from each first load scenario to the initial typical scenario is calculated, and the first load scenario is assigned to the nearest initial typical scenario. The average load corresponding to all first load scenarios in each initial typical scenario is taken as the target load typical scenario. The target load typical scenarios to which each first load scenario belongs are redistributed until the target load typical scenarios no longer change, resulting in multiple first loads corresponding to the final K target load typical scenarios and multiple second occurrence probabilities of K2 target load typical scenarios.

[0083] For example, the formula for calculating the distance from each first load scenario to the typical target load scenario is as follows:

[0084]

[0085] in, The second distance is the distance from the first load scenario i to the target load typical scenario k. Let be the load during time period t in the i-th first load scenario. Let K2 be the load of typical target load scenario k in time period t, N2 be the total number of the first load scenario, and K2 be the total number of typical target load scenarios.

[0086] The formula for calculating the load of target load k in a typical scenario over time period t is as follows:

[0087]

[0088] in, For a typical scenario of target load k, the load during time period t. This represents the number of the first load scenarios belonging to the typical target load scenario k. The target load is the load of a typical scenario k during the time period t.

[0089] In some optional implementations, the formula for calculating the second occurrence probability of a typical scenario of the target load in the first load scenario is as follows:

[0090]

[0091] in, The second probability of occurrence, N1 represents the number of first load scenarios belonging to the typical scenario k of the target load, and N2 represents the total number of first load scenarios.

[0092] Step S105: Based on multiple first power, multiple first occurrence probabilities, multiple first loads and multiple second occurrence probabilities, the hydropower station dispatching scheme is determined with the minimum expected maximum value of the remaining load as the first optimization objective function, the minimum expected fluctuation of the downstream tailwater level as the second optimization objective function, and the minimum expected fluctuation of the downstream discharge flow as the third optimization objective function.

[0093] In this embodiment of the invention, the hydropower station is scheduled according to the hydropower station scheduling scheme. Specifically, the parameters of the hydropower station are adjusted according to the target scheduling data in the hydropower station scheduling scheme. For example, the target scheduling data may be hydropower generation capacity, wind power generation capacity, photovoltaic power generation capacity, water level, and flow rate, etc.

[0094] In some alternative implementations, the first optimization objective function is:

[0095]

[0096] Where F1 represents the first optimization objective function, min represents taking the minimum value, max represents taking the maximum value, and p k P represents the first probability of occurrence corresponding to typical scenario k of target power or the second probability of occurrence corresponding to typical scenario k of target load, where K represents the total number of typical scenarios of target power or the total number of typical scenarios of target load. k,t This represents the first power of the target power typical scenario k during the time period t, or the first load of the target load typical scenario k during the time period t. This represents the power generation of hydropower in time period t under typical scenario k of target power or typical scenario k of target load. This represents the power generation of wind power in the time period t under the typical scenario k of the target power or the typical scenario k of the target load. This represents the power generation of photovoltaics in time period t under the typical scenario k of the target power or the typical scenario k of the target load.

[0097] In some alternative implementations, the second optimization objective function is:

[0098]

[0099] Where F2 represents the second optimization objective function, min represents taking the minimum value, max represents taking the maximum value, and p k Z represents the first probability of occurrence corresponding to typical scenario k of target power or the second probability of occurrence corresponding to typical scenario k of target load, where K represents the total number of typical scenarios of target power or the total number of typical scenarios of target load. k,t+1 Z represents the water level during time period t+1 under typical scenario k of target power or target load. k,t This represents the water level over time period t under typical scenario k of target power or typical scenario k of target load.

[0100] In some optional implementations, the third optimization objective function is:

[0101]

[0102] Where F3 represents the third optimization objective function, min represents taking the minimum value, and p k Q represents the first probability of occurrence corresponding to typical scenario k of target power or the second probability of occurrence corresponding to typical scenario k of target load. k,t+1 Q represents the flow rate in time period t+1 under typical target power scenario k or typical target load scenario k. k,t This represents the flow rate over time period t under typical target power scenario k or typical target load scenario k.

[0103] The hydropower station scheduling method provided in this embodiment first predicts the power of the hydropower station based on the power data of wind power or photovoltaic power within a preset time period, obtaining a power prediction value. It then predicts the load of the hydropower station based on historical load data used to characterize the load data of the hydropower station within the preset time period, obtaining a load prediction value. Predicting future power and load based on historical data facilitates subsequent analysis based on future power and load, providing a data foundation for generating subsequent hydropower station scheduling plans. This embodiment of the invention performs prediction deviation analysis on the predicted power value and the measured power value to obtain a first probability distribution function corresponding to the first prediction deviation; it also performs prediction deviation analysis on the predicted load value and the measured load value to obtain a second probability distribution function corresponding to the second prediction deviation. This prediction deviation analysis identifies the deviation between the predicted power value and the predicted load value, facilitating the analysis of the causes of the deviation, reducing the occurrence of similar problems, and making subsequent hydropower station scheduling plans more accurate. This invention performs scenario analysis on a first probability distribution function to generate multiple first power scenarios; performs scenario analysis on a second probability distribution function to generate multiple first load scenarios; performs clustering processing on the multiple first power scenarios to obtain multiple first powers and multiple first occurrence probabilities corresponding to multiple typical target power scenarios; and performs clustering processing on the multiple first load scenarios to obtain multiple first loads and multiple second occurrence probabilities corresponding to multiple typical target load scenarios. This invention analyzes typical scenarios of power and load to make the subsequently generated hydropower station dispatching scheme more consistent with the actual situation. This invention, based on multiple first power levels, multiple first occurrence probabilities, multiple first load levels, and multiple second occurrence probabilities, determines a hydropower station dispatching scheme by minimizing the expected maximum value of the remaining load as the first optimization objective function, minimizing the expected fluctuation of the downstream tailwater level as the second optimization objective function, and minimizing the expected fluctuation of the downstream discharge flow as the third optimization objective function. Compared with related technologies that only consider the peak-shaving of upstream power stations, this invention integrates the operational constraints of the downstream counter-regulating reservoirs into the multi-energy complementary dispatching of hydropower, wind power, and solar power. It considers the counter-regulating needs of downstream hydropower stations, fully utilizes the peak-shaving function of downstream hydropower stations, and takes into account the uncertainty of wind power, solar power output, and day-ahead load forecasting to generate a hydropower station dispatching scheme. This effectively coordinates the relationship between the operating status and dispatching capacity of the cascade counter-regulating reservoirs. Under the comprehensive consideration of the operational constraints of the cascade counter-regulating reservoirs, it maximizes the dispatching effect of multi-energy complementary hydropower, wind power, and solar power, making the regulation process more accurate, more in line with actual conditions, and improving practicality.

[0104] This embodiment provides a method for scheduling a hydropower station, which can be used with computer equipment. Figure 2 This is a flowchart of another hydropower station scheduling method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0105] Step S201 involves predicting the power output of wind or solar power based on historical power data to obtain a predicted power value, and predicting the load of hydropower stations based on historical load data to obtain a predicted load value. Historical power data is used to characterize the power output of wind or solar power over a preset time period, and historical load data is used to characterize the load of hydropower stations over the preset time period. For details, please refer to [link to details]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0106] Step S202: Perform prediction deviation analysis on the predicted power value and the measured power value to obtain the first probability distribution function corresponding to the first prediction deviation; perform prediction deviation analysis on the predicted load value and the measured load value to obtain the second probability distribution function corresponding to the second prediction deviation. For details, please refer to [link to details]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0107] Step S203: Perform scenario analysis on the first probability distribution function to generate multiple first power scenarios; perform scenario analysis on the second probability distribution function to generate multiple first load scenarios. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0108] Step S204: Cluster the various first power scenarios to obtain multiple first powers and multiple first occurrence probabilities corresponding to multiple typical target power scenarios; cluster the various first load scenarios to obtain multiple first loads and multiple second occurrence probabilities corresponding to multiple typical target load scenarios; the multiple first occurrence probabilities are used to characterize the probability of multiple typical target power scenarios occurring, and the multiple second occurrence probabilities are used to characterize the probability of multiple typical target load scenarios occurring. For details, please refer to [link to details]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0109] Step S205: Based on multiple first power, multiple first occurrence probabilities, multiple first loads and multiple second occurrence probabilities, the hydropower station scheduling scheme is determined with the minimum expected maximum value of the remaining load as the first optimization objective function, the minimum expected fluctuation of the downstream tailwater level as the second optimization objective function, and the minimum expected fluctuation of the downstream discharge flow as the third optimization objective function. The hydropower station is then scheduled according to the hydropower station scheduling scheme.

[0110] Specifically, step S205 includes:

[0111] Step S2051: Construct a multi-objective scheduling model based on multiple first powers, multiple first occurrence probabilities, multiple first loads, and multiple second occurrence probabilities.

[0112] The optimization objectives of the multi-objective scheduling model include minimizing the expected maximum value of the remaining load as the first optimization objective function, minimizing the expected fluctuation of the downstream tailwater level as the second optimization objective function, and minimizing the expected fluctuation of the downstream discharge as the third optimization objective function. The inputs of the multi-objective scheduling model are multiple first power, multiple first occurrence probabilities, multiple first loads, and multiple second occurrence probabilities. The output of the multi-objective scheduling model is the optimized solution set.

[0113] In some optional implementations, based on multiple first power, multiple first occurrence probabilities, multiple first loads, and multiple second occurrence probabilities, a short-term peak-shaving model for the hydro-wind-solar multi-energy complementary system is constructed with the minimum expected maximum value of the remaining load as the first optimization objective function. A downstream tailwater level fluctuation model is constructed with the minimum expected fluctuation of the downstream tailwater level as the second optimization objective function. A flow restriction model is constructed with the minimum expected fluctuation of the downstream discharge flow as the third optimization objective function. The short-term peak-shaving model, the downstream tailwater level fluctuation model, and the flow restriction model of the hydro-wind-solar multi-energy complementary system are then fused to obtain a multi-objective scheduling model.

[0114] The constraints of the short-term peak-shaving model for the hydro-wind-solar multi-energy complementary system include: power plant output limits, reservoir water level limits, downstream discharge limits, and water balance equations. Since there are downstream counter-regulation limitations, a downstream tailwater level fluctuation model needs to be constructed based on the short-term peak-shaving model of the hydro-wind-solar multi-energy complementary system, with the goal of minimizing the expected fluctuation of the downstream tailwater level. Downstream counter-regulation limits the downstream discharge flow; therefore, a flow restriction model needs to be constructed with the goal of minimizing the expected fluctuation of the downstream discharge flow.

[0115] Step S2052: Solve the multi-objective scheduling model to obtain the optimal solution set; the optimal solution set is used to characterize the solution set of the optimal data for scheduling hydropower stations.

[0116] In this embodiment of the invention, a decomposition-based multi-objective evolutionary algorithm (MOEA / D algorithm) is used to solve the multi-objective scheduling model to obtain a Pareto optimal solution set. The MOEA / D algorithm decomposes the multi-objective optimization problem into a set of single-objective optimization sub-problems, and approximates the solution set of the original multi-objective optimization problem by solving these sub-problems.

[0117] Step S2053: Select target scheduling data from the optimized solution set, and generate a hydropower station scheduling scheme based on the target scheduling data; wherein, the target scheduling data is used to characterize the optimal scheduling data.

[0118] This invention integrates the operational constraints of downstream counter-regulating reservoirs into the multi-energy complementary scheduling of hydropower, wind power, and solar power, taking into account the uncertainties of wind power, solar power output, and day-ahead load forecasting. Combining multiple typical scenarios, a multi-objective optimization scheduling model under cascade counter-regulating constraints is constructed. The multi-objective scheduling model is solved to obtain an optimized solution set, which includes multiple scheduling data with good scheduling effects. The optimal scheduling data is selected from the optimized solution set to generate a hydropower station scheduling scheme, thereby improving the accuracy of multi-energy complementary scheduling of hydropower, wind power, and solar power.

[0119] This embodiment provides a method for scheduling a hydropower station, which can be used with computer equipment. Figure 3 This is a flowchart of another hydropower station scheduling method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0120] Step S301: Predict the power output of wind or solar power based on historical power data to obtain a predicted power value; and predict the load of the hydropower station based on historical load data to obtain a predicted load value. Historical power data is used to characterize the power output of wind or solar power within a preset time period, and historical load data is used to characterize the load of the hydropower station within the preset time period. For details, please refer to [link to details]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0121] Step S302: Perform prediction deviation analysis on the predicted power value and the measured power value to obtain the first probability distribution function corresponding to the first prediction deviation; perform prediction deviation analysis on the predicted load value and the measured load value to obtain the second probability distribution function corresponding to the second prediction deviation.

[0122] Specifically, step S302 includes:

[0123] Step S3021: The difference between the measured power value and the predicted power value is taken as the first prediction deviation; the first prediction deviation is analyzed by probability distribution to obtain the first probability distribution function.

[0124] Among them, probability distribution analysis can be calculated using the kernel density estimation method to calculate the first probability distribution function corresponding to the first prediction deviation.

[0125] Step S3022: The difference between the measured load value and the predicted load value is taken as the second prediction deviation; the second prediction deviation is analyzed by probability distribution to obtain the second probability distribution function.

[0126] Among them, probability distribution analysis can be calculated by using the kernel density estimation method to calculate the second probability distribution function corresponding to the second prediction bias.

[0127] Step S303: Perform scenario analysis on the first probability distribution function to generate multiple first power scenarios; perform scenario analysis on the second probability distribution function to generate multiple first load scenarios.

[0128] Specifically, step S303 includes:

[0129] Step S3031: Random sampling is performed on the first probability distribution function a preset number of times to obtain multiple first sampling results; based on the multiple first sampling results and the first prediction deviation corresponding to the multiple first sampling results, multiple typical scenarios of first power are generated.

[0130] In this process, multiple first sampling results are added to the first prediction deviation corresponding to each sampling result to obtain various typical scenarios of first power.

[0131] The preset number of attempts can be set according to actual needs.

[0132] Step S3032: Perform a preset number of random samplings on the second probability distribution function to obtain multiple second sampling results; generate multiple typical scenarios of the first load based on the second prediction deviations corresponding to the multiple second sampling results and the multiple first sampling results.

[0133] In this process, multiple second sampling results are added to the second prediction deviation corresponding to each sampling result to obtain various typical scenarios of the first load.

[0134] The preset number of attempts can be set according to actual needs.

[0135] Step S304: Cluster the multiple first power scenarios to obtain multiple first powers and multiple first occurrence probabilities corresponding to multiple target power typical scenarios; cluster the multiple first load scenarios to obtain multiple first loads and multiple second occurrence probabilities corresponding to multiple target load typical scenarios; the multiple first occurrence probabilities are used to characterize the probability of multiple target power typical scenarios occurring, and the multiple second occurrence probabilities are used to characterize the probability of multiple target load typical scenarios occurring.

[0136] Specifically, step S304 includes:

[0137] Step S3041: Select a preset number of first power scenarios as initial power typical scenarios from multiple first power scenarios; calculate the distance from each first power scenario to the initial power typical scenario to obtain multiple first target distances; assign each first power scenario to the initial power typical scenario with the closest first target distance to obtain multiple first cluster groups; generate multiple target power typical scenarios based on the first power scenarios in the multiple first cluster groups; obtain multiple first powers and multiple first occurrence probabilities corresponding to the multiple target power typical scenarios.

[0138] Among them, the average value of the first power scenario in multiple first cluster groups is used as the target power typical scenario to obtain multiple target power typical scenarios.

[0139] In some optional implementations, a preset number of scenarios are randomly selected from a variety of first power scenarios as initial typical scenarios. The distance from each first power scenario to the initial typical scenario is calculated, and the first power scenario is assigned to the nearest initial typical scenario. The average power of all first power scenarios in each initial typical scenario is taken as the target power typical scenario. The target power typical scenarios to which each first power scenario belongs are redistributed until the target power typical scenarios no longer change, resulting in multiple first powers corresponding to the final K target power typical scenarios and multiple first occurrence probabilities of the occurrence of each target power typical scenario.

[0140] Step S3042: Select a preset number of first load scenarios as initial load typical scenarios from multiple first load scenarios; calculate the distance from each first load scenario to the initial load typical scenario to obtain multiple second target distances; assign each first load scenario to the initial load typical scenario with the closest second target distance to obtain multiple second cluster groups; generate multiple target load typical scenarios based on the first load scenarios in the multiple second cluster groups; obtain multiple first loads and multiple second occurrence probabilities corresponding to the multiple target load typical scenarios.

[0141] Among them, the average value of the first load scenario in multiple second cluster groups is used as the typical target load scenario to obtain multiple typical target load scenarios.

[0142] In some optional implementations, a preset number of scenarios are randomly selected from a variety of first load scenarios as initial typical scenarios. The distance from each first load scenario to the initial typical scenario is calculated, and the first load scenario is assigned to the nearest initial typical scenario. The average load corresponding to all first load scenarios in each initial typical scenario is taken as the target load typical scenario. The target load typical scenarios to which each first load scenario belongs are redistributed until the target load typical scenarios no longer change, resulting in multiple first loads corresponding to the final K target load typical scenarios and multiple second occurrence probabilities of each target load typical scenario.

[0143] Step S305: Based on multiple first power levels, multiple first occurrence probabilities, multiple first load levels, and multiple second occurrence probabilities, the hydropower station dispatching scheme is determined with the following objectives: minimizing the expected maximum value of the remaining load as the first optimization objective function, minimizing the expected fluctuation of the downstream tailwater level as the second optimization objective function, and minimizing the expected fluctuation of the downstream discharge as the third optimization objective function. For details, please refer to [link to relevant documentation]. Figure 1Step S105 of the illustrated embodiment will not be described again here.

[0144] This embodiment provides a method for scheduling a hydropower station, which can be used with computer equipment. Figure 4 This is a flowchart of a scheduling method for another hydropower station according to an embodiment of the present invention, as shown below. Figure 4 As shown, the process includes the following steps:

[0145] Step S401: Short-term wind or solar power, day-ahead load curve, and day-ahead runoff forecast.

[0146] In some optional implementations, wind / solar power variations are influenced by meteorological factors, turbine characteristics, and status. Meteorological factors such as wind speed, radiation intensity, and temperature, along with turbine status data corresponding to the wind / solar power data at the time of the data release, are collected as model input factors. A short-term wind / solar power prediction model is constructed based on an LSTM network to achieve short-term prediction of wind and solar power.

[0147] In some optional implementations, wind / solar power variations are influenced by meteorological factors, turbine characteristics, and status. Meteorological factors such as wind speed, radiation intensity, and temperature, along with turbine status data corresponding to the wind / solar power data at the time of the data release, are collected as model input factors. A short-term wind / solar power prediction model is constructed based on an LSTM network to achieve short-term prediction of wind and solar power.

[0148] In some alternative implementations, runoff variation is influenced by hydrological and meteorological factors. Historical runoff, rainfall, and evaporation data are collected as key input factors to the model, and a day-ahead runoff prediction model is constructed based on an LSTM network to achieve day-ahead runoff prediction.

[0149] Step S402: Uncertainty analysis of wind power or photovoltaic forecasting errors and load forecasting errors.

[0150] In some optional implementations, the prediction bias is calculated based on the wind / photovoltaic power prediction results and the actual observation results, and the probability distribution function of the prediction bias is calculated using the kernel density estimation method.

[0151] In some optional implementations, the prediction deviation is calculated based on the load forecast results and the actual observation results, and the probability distribution function of the prediction deviation is calculated using the kernel density estimation method.

[0152] Step S403: Generating typical wind power or photovoltaic power and load scenarios.

[0153] In some alternative implementations, multiple random samplings are performed on the probability distribution of the prediction deviation, and the sampling results are added to the prediction results to obtain various power / load scenarios that may occur at that moment.

[0154] In some optional implementations, the generated scenes are clustered and reduced, and an initial scene is randomly selected from multiple scenes as the initial typical scenes. The distance from each scene to each typical scene is calculated, and the scene is assigned to the nearest typical scene. After all scenes are assigned, the mean of all scenes in the typical scenes at each time point is used as the new typical scene, and each scene is reassigned to a new typical scene until the typical scenes no longer change. This results in several final new typical scenes and their probabilities of occurrence.

[0155] Step S404: Construction of short-term multi-objective scheduling model.

[0156] In some optional implementations, based on generating typical power / load scenarios, a short-term peak-shaving model for the hydro-wind-solar multi-energy complementary system is constructed with the goal of minimizing the expected maximum value of the remaining load. Since there are downstream counter-regulation constraints, a downstream tailwater level fluctuation model is constructed based on the short-term peak-shaving model with the goal of minimizing the expected fluctuation of the downstream tailwater level. Since downstream counter-regulation limits the downstream discharge flow, a flow restriction model is constructed with the goal of minimizing the expected fluctuation of the discharge flow. A short-term multi-objective scheduling model is constructed from the short-term peak-shaving model of the hydro-wind-solar multi-energy complementary system, the downstream tailwater level fluctuation model, and the flow restriction model.

[0157] Step S405: The multi-objective intelligent optimization algorithm is used to optimize and solve the problem.

[0158] In some alternative implementations, the MOEA / D algorithm is used to solve the multi-objective scheduling model, and finally a set of Pareto optimal solutions for the multi-objective scheduling model is obtained. Based on the Pareto optimal solution set, a hydropower station scheduling scheme is generated.

[0159] For example, such as Figure 5 The diagram shows power curves for different photovoltaic scenarios at different times. The power output varies depending on the photovoltaic scenario and the time period. Photovoltaic scenario 3 has a higher power output than photovoltaic scenario 1, which in turn has a higher power output than photovoltaic scenario 2. Figure 6 The diagram shows power curves for different wind power scenarios at different times. The power output varies depending on the wind power scenario and the time period. The power output for wind power scenario 6 is greater than that for wind power scenario 5, which in turn is greater than that for wind power scenario 4. Figure 7 The diagram shows the power curves under different load scenarios at different times. The loads corresponding to different time periods are different under different load scenarios. The load corresponding to load scenario 9 is greater than the load corresponding to load scenario 7, which is greater than the load corresponding to load scenario 8.

[0160] This embodiment also provides a hydropower station dispatching device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0161] This embodiment provides a dispatching device for a hydropower station, such as... Figure 8 As shown, it includes:

[0162] The power and load prediction module 801 is used to predict the power of wind power or photovoltaic power based on historical power data to obtain the power prediction value, and to predict the load of hydropower station based on historical load data to obtain the load prediction value; the historical power data is used to represent the power data of wind power or photovoltaic power in a preset time period, and the historical load data is used to represent the load data of hydropower station in a preset time period.

[0163] The prediction deviation analysis module 802 is used to perform prediction deviation analysis on the predicted power value and the measured power value to obtain the first probability distribution function corresponding to the first prediction deviation; and to perform prediction deviation analysis on the predicted load value and the measured load value to obtain the second probability distribution function corresponding to the second prediction deviation.

[0164] The scenario generation module 803 is used to perform scenario analysis on the first probability distribution function to generate multiple first power scenarios; and to perform scenario analysis on the second probability distribution function to generate multiple first load scenarios.

[0165] The clustering analysis module 804 is used to perform clustering analysis on multiple first power scenarios to obtain multiple first powers and multiple first occurrence probabilities corresponding to multiple target power typical scenarios; and to perform clustering analysis on multiple first load scenarios to obtain multiple first loads and multiple second occurrence probabilities corresponding to multiple target load typical scenarios; the multiple first occurrence probabilities are used to characterize the probability of multiple target power typical scenarios occurring, and the multiple second occurrence probabilities are used to characterize the probability of multiple target load typical scenarios occurring.

[0166] The optimization scheduling module 805 is used to determine the hydropower station scheduling scheme based on multiple first power, multiple first occurrence probabilities, multiple first loads and multiple second occurrence probabilities, with the minimum expected value of the remaining load as the first optimization objective function, the minimum expected fluctuation of the downstream tailwater level as the second optimization objective function and the minimum expected fluctuation of the downstream discharge flow as the third optimization objective function.

[0167] In some alternative implementations, the optimized scheduling module 805 includes:

[0168] The model building unit is used to construct a multi-objective scheduling model based on multiple first power, multiple first occurrence probabilities, multiple first loads, and multiple second occurrence probabilities. The optimization objectives of the multi-objective scheduling model include minimizing the expected maximum value of the remaining load as the first optimization objective function, minimizing the expected fluctuation of the downstream tailwater level as the second optimization objective function, and minimizing the expected fluctuation of the downstream discharge as the third optimization objective function. The inputs of the multi-objective scheduling model are multiple first power, multiple first occurrence probabilities, multiple first loads, and multiple second occurrence probabilities, and the output of the multi-objective scheduling model is the optimized solution set.

[0169] The model solving unit is used to solve the multi-objective scheduling model to obtain the optimal solution set; the optimal solution set is used to characterize the solution set of the optimal data for scheduling hydropower stations.

[0170] The hydropower station scheduling scheme generation unit is used to select target scheduling data from the optimal solution set and generate a hydropower station scheduling scheme based on the target scheduling data; wherein, the target scheduling data is used to characterize the optimal scheduling data.

[0171] In some alternative implementations, the power and load forecasting module 801 includes:

[0172] The power prediction unit is used to input historical power data into the trained power prediction model to obtain the power prediction value. The input of the power prediction model is the historical power data, and the output of the power prediction model is the power prediction value.

[0173] The load forecasting unit is used to input historical load data into the trained load forecasting model to obtain load forecast values. The input of the load forecasting model is historical load data, and the output of the load forecasting model is the load forecast value.

[0174] In some alternative implementations, the prediction bias analysis module 802 includes:

[0175] The first prediction deviation analysis unit is used to take the difference between the measured power value and the predicted power value as the first prediction deviation; and to perform probability distribution analysis on the first prediction deviation to obtain the first probability distribution function.

[0176] The second prediction deviation analysis unit is used to take the difference between the measured load value and the predicted load value as the second prediction deviation; and to perform probability distribution analysis on the second prediction deviation to obtain the second probability distribution function.

[0177] In some alternative implementations, the scene generation module 803 includes:

[0178] The power scenario generation unit is used to randomly sample the first probability distribution function of the hydropower station dispatch scheme a preset number of times to obtain multiple first sampling results; and to generate multiple first power typical scenarios based on the multiple first sampling results and the first prediction deviations corresponding to the multiple first sampling results.

[0179] The load scenario generation unit is used to perform a preset number of random samplings on the second probability distribution function to obtain multiple second sampling results; based on the second prediction deviations corresponding to the multiple second sampling results and the multiple first sampling results, it generates multiple typical first load scenarios.

[0180] In some alternative implementations, the clustering analysis module 804 includes:

[0181] The first clustering analysis unit is used to select a preset number of first power scenarios as initial power typical scenarios from multiple first power scenarios; calculate the distance from each first power scenario to the initial power typical scenario to obtain multiple first target distances; assign each first power scenario to the initial power typical scenario with the closest first target distance to obtain multiple first cluster groups; generate multiple target power typical scenarios based on the first power scenarios in the multiple first cluster groups; and obtain multiple first powers and multiple first occurrence probabilities corresponding to the multiple target power typical scenarios.

[0182] The second clustering analysis unit is used to select a preset number of first load scenarios as initial load typical scenarios from multiple first load scenarios; calculate the distance from each first load scenario to the initial load typical scenario to obtain multiple second target distances; assign each first load scenario to the initial load typical scenario with the closest second target distance to obtain multiple second cluster groups; generate multiple target load typical scenarios based on the first load scenarios in the multiple second cluster groups; and obtain multiple first loads and multiple second occurrence probabilities corresponding to the multiple target load typical scenarios.

[0183] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0184] In this embodiment, the hydropower station dispatching device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, or other devices that can provide the above functions.

[0185] This invention also provides a computer device having the above-described features. Figure 8 The diagram shows the dispatching device for a hydroelectric power station.

[0186] Please see Figure 9 , Figure 9 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 9 As shown, the computer device includes one or more processors 910, memory 920, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 9 Take the 910 processor as an example.

[0187] The processor 910 may be a central processing unit, a network processor, or a combination thereof. The processor 910 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0188] The memory 920 stores instructions executable by at least one processor 910 to cause the at least one processor 910 to perform the method shown in the above embodiments.

[0189] The memory 920 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 920 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 920 may optionally include memory remotely located relative to the processor 910, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0190] The memory 920 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 920 may also include a combination of the above types of memory.

[0191] The computer device also includes a communication interface 930 for communicating with other devices or communication networks.

[0192] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0193] A portion of this invention can be applied to computer program products, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in computer-readable media include, but are not limited to, source files, executable files, and installation package files. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions; the computer compiling the instructions and then executing the corresponding compiled program; the computer reading and executing the instructions; or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0194] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for dispatching a hydropower station, characterized in that, The method includes: The power of wind power or photovoltaic power is predicted based on historical power data to obtain a power prediction value, and the load of hydropower station is predicted based on historical load data to obtain a load prediction value; the historical power data is used to characterize the power data of wind power or photovoltaic power over a preset time period, and the historical load data is used to characterize the load data of hydropower station over a preset time period. A prediction deviation analysis is performed on the predicted power value and the measured power value to obtain a first probability distribution function corresponding to the first prediction deviation; a prediction deviation analysis is performed on the predicted load value and the measured load value to obtain a second probability distribution function corresponding to the second prediction deviation. Scenario analysis is performed on the first probability distribution function to generate multiple first power scenarios; scenario analysis is performed on the second probability distribution function to generate multiple first load scenarios; Clustering is performed on the various first power scenarios to obtain multiple first powers and multiple first occurrence probabilities corresponding to multiple target power typical scenarios; clustering is performed on the various first load scenarios to obtain multiple first loads and multiple second occurrence probabilities corresponding to multiple target load typical scenarios; the multiple first occurrence probabilities are used to characterize the probability of multiple target power typical scenarios occurring, and the multiple second occurrence probabilities are used to characterize the probability of multiple target load typical scenarios occurring; Based on the plurality of first power, the plurality of first occurrence probabilities, the plurality of first loads, and the plurality of second occurrence probabilities, the hydropower station scheduling scheme is determined with the minimum expected maximum value of remaining load as the first optimization objective function, the minimum expected fluctuation of downstream tailwater level as the second optimization objective function, and the minimum expected fluctuation of downstream discharge as the third optimization objective function.

2. The method according to claim 1, characterized in that, The process of determining a hydropower station dispatching scheme based on the plurality of first power, the plurality of first occurrence probabilities, the plurality of first loads, and the plurality of second occurrence probabilities, with the minimum expected maximum value of remaining load as the first optimization objective function, the minimum expected fluctuation of downstream tailwater level as the second optimization objective function, and the minimum expected fluctuation of downstream discharge as the third optimization objective function, includes: A multi-objective scheduling model is constructed based on the plurality of first powers, the plurality of first occurrence probabilities, the plurality of first loads, and the plurality of second occurrence probabilities. The optimization objectives of the multi-objective scheduling model include a first optimization objective function that aims to minimize the expected maximum value of the remaining load, a second optimization objective function that aims to minimize the expected fluctuation of the downstream tailwater level, and a third optimization objective function that aims to minimize the expected fluctuation of the downstream discharge flow. The inputs of the multi-objective scheduling model are the plurality of first powers, the plurality of first occurrence probabilities, the plurality of first loads, and the plurality of second occurrence probabilities, and the output of the multi-objective scheduling model is the optimized solution set. Solving the multi-objective scheduling model yields the optimized solution set; the optimized solution set is used to characterize the set of optimized data for scheduling the hydropower station. Select target scheduling data from the optimized solution set, and generate the hydropower station scheduling scheme based on the target scheduling data; wherein, the target scheduling data is used to characterize the optimal scheduling data.

3. The method according to claim 1 or 2, characterized in that, The process of predicting wind or solar power power based on historical power data to obtain predicted power values, and predicting hydropower station load based on historical load data to obtain predicted load values, includes: The historical power data is input into the trained power prediction model to obtain the power prediction value. The input of the power prediction model is the historical power data, and the output of the power prediction model is the power prediction value. The historical load data is input into the trained load prediction model to obtain the load prediction value. The input of the load prediction model is the historical load data, and the output of the load prediction model is the load prediction value.

4. The method according to claim 1 or 2, characterized in that, The step of performing prediction deviation analysis on the predicted power value and the measured power value to obtain a first probability distribution function corresponding to the first prediction deviation; and performing prediction deviation analysis on the predicted load value and the measured load value to obtain a second probability distribution function corresponding to the second prediction deviation, including: The difference between the measured power value and the predicted power value is taken as the first prediction deviation; Perform probability distribution analysis on the first prediction deviation to obtain the first probability distribution function; The difference between the measured load value and the predicted load value is taken as the second prediction deviation; A probability distribution analysis is performed on the second prediction deviation to obtain the second probability distribution function.

5. The method according to claim 1 or 2, characterized in that, The first probability distribution function is analyzed to generate multiple typical scenarios of first power; the second probability distribution function is analyzed to generate multiple typical scenarios of first load, including: A preset number of random samples are performed on the first probability distribution function to obtain multiple first sampling results; Based on the multiple first sampling results and the first prediction deviation corresponding to the multiple first sampling results, the multiple first power typical scenarios are generated; A preset number of random samplings are performed on the second probability distribution function to obtain multiple second sampling results; Based on the second prediction deviations corresponding to the multiple second sampling results and the multiple first sampling results, the multiple typical scenarios of the first load are generated.

6. The method according to claim 1 or 2, characterized in that, The clustering process is performed on the various first power scenarios to obtain multiple first powers and multiple first occurrence probabilities corresponding to multiple typical target power scenarios; Clustering is performed on the various first load scenarios to obtain multiple first loads and multiple second occurrence probabilities corresponding to multiple typical target load scenarios, including: Among the various first power scenarios, a preset number of first power scenarios are selected as initial power typical scenarios; the distance from each first power scenario to the initial power typical scenario is calculated to obtain multiple first target distances; each first power scenario is assigned to the initial power typical scenario with the closest first target distance to obtain multiple first cluster groups; multiple target power typical scenarios are generated based on the first power scenarios in the multiple first cluster groups; multiple first powers and multiple first occurrence probabilities corresponding to the multiple target power typical scenarios are obtained; Among the various first load scenarios, a preset number of first load scenarios are selected as initial load typical scenarios; the distance from each first load scenario to the initial load typical scenario is calculated to obtain multiple second target distances; each first load scenario is assigned to the initial load typical scenario with the closest second target distance to obtain multiple second cluster groups; multiple target load typical scenarios are generated based on the first load scenarios in the multiple second cluster groups; multiple first loads and multiple second occurrence probabilities corresponding to the multiple target load typical scenarios are obtained.

7. The method according to claim 1 or 2, characterized in that, The first optimization objective function is: Where F1 represents the first optimization objective function, min represents taking the minimum value, max represents taking the maximum value, and p k P represents the first probability of occurrence corresponding to typical scenario k of target power or the second probability of occurrence corresponding to typical scenario k of target load, where K represents the total number of typical scenarios of target power or the total number of typical scenarios of target load. k,t This represents the first power of the typical target power scenario k during the time period t, or the first load of the typical target load scenario k during the time period t. This represents the power generation capacity of hydropower during time period t under the typical target power scenario k or the typical target load scenario k. This represents the power generation of wind power during time period t under the typical target power scenario k or the typical target load scenario k. This represents the power generation of photovoltaics during time period t under the target power typical scenario k or the target load typical scenario k.

8. The method according to claim 1 or 2, characterized in that, The second optimization objective function is: Where F2 represents the second optimization objective function, min represents taking the minimum value, max represents taking the maximum value, and p k Z represents the first probability of occurrence corresponding to typical scenario k of target power or the second probability of occurrence corresponding to typical scenario k of target load, where K represents the total number of typical scenarios of target power or the total number of typical scenarios of target load. k,t+1 Z represents the water level during time period t+1 under the typical target power scenario k or the typical target load scenario k. k,t This represents the water level during time period t under the typical target power scenario k or the typical target load scenario k.

9. The method according to claim 1 or 2, characterized in that, The third optimization objective function is: Where F3 represents the third optimization objective function, min represents taking the minimum value, and p k Q represents the first probability of occurrence corresponding to typical scenario k of target power or the second probability of occurrence corresponding to typical scenario k of target load. k,t+1 Q represents the flow rate during time period t+1 under the typical target power scenario k or the typical target load scenario k. k,t This represents the flow rate over time period t under the typical target power scenario k or the typical target load scenario k.

10. A dispatching device for a hydropower station, characterized in that, The device includes: The power and load prediction module is used to predict the power of wind power or photovoltaic power based on historical power data to obtain a power prediction value, and to predict the load of hydropower station based on historical load data to obtain a load prediction value; the historical power data is used to represent the power data of wind power or photovoltaic power over a preset time period, and the historical load data is used to represent the load data of hydropower station over a preset time period. The prediction deviation analysis module is used to perform prediction deviation analysis on the predicted power value and the measured power value to obtain a first probability distribution function corresponding to the first prediction deviation; and to perform prediction deviation analysis on the predicted load value and the measured load value to obtain a second probability distribution function corresponding to the second prediction deviation. The scenario generation module is used to perform scenario analysis on the first probability distribution function to generate multiple first power scenarios; and to perform scenario analysis on the second probability distribution function to generate multiple first load scenarios. The clustering analysis module is used to perform clustering analysis on the multiple first power scenarios to obtain multiple first powers and multiple first occurrence probabilities corresponding to multiple target power typical scenarios; and to perform clustering analysis on the multiple first load scenarios to obtain multiple first loads and multiple second occurrence probabilities corresponding to multiple target load typical scenarios; the multiple first occurrence probabilities are used to characterize the probability of multiple target power typical scenarios occurring, and the multiple second occurrence probabilities are used to characterize the probability of multiple target load typical scenarios occurring; The optimization scheduling module is used to determine the hydropower station scheduling scheme based on the plurality of first power, the plurality of first occurrence probabilities, the plurality of first loads and the plurality of second occurrence probabilities, with the minimum expected value of the remaining load as the first optimization objective function, the minimum expected fluctuation of the downstream tailwater level as the second optimization objective function and the minimum expected fluctuation of the downstream discharge as the third optimization objective function.

11. A computer device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the computer instructions to perform the hydropower station scheduling method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the hydropower station scheduling method according to any one of claims 1 to 9.

13. A computer program product, characterized in that, It includes computer instructions for causing a computer to execute the hydropower station scheduling method according to any one of claims 1 to 9.

Images