Hydropower station sound wave precipitation enhancement cooperative scheduling method, system and equipment based on power market signal driving and medium

Abstract

The invention belongs to the technical field of precipitation enhancement scheduling, and relates to a hydropower station sound wave precipitation enhancement cooperative scheduling method, system and device based on electric power market signal driving and a medium. The method comprises the steps of obtaining time-of-use electricity price prediction data, operation state data and short-term weather forecast data; calculating a target reservoir capacity which the hydropower station reservoir needs to reach before a future high electricity price period; the target reservoir capacity is compared with the current actual reservoir capacity of the reservoir, and according to short-term weather forecast data, the expected increment reservoir water amount which can be obtained through sound wave precipitation enhancement and the corresponding operation cost are predicted; calculating an expected net income based on the expected increment of the water storage amount, the average electricity price in the high electricity price period and the operation cost; when the expected net income is greater than the dynamic decision threshold, generating a sound wave precipitation enhancement operation instruction; and controlling the sound wave precipitation enhancement equipment array to execute the operation instruction. According to the invention, the problem of decision isolation of each system in a traditional mode is solved, and the precipitation enhancement operation can accurately serve the scheduling target of power generation income maximization.

Description

TECHNICAL FIELD

[0001] The present disclosure belongs to the technical field of rain enhancement dispatching, and relates to a method, system, device and medium for coordinated dispatching of sound wave rain enhancement of a hydropower station based on a power market signal. BACKGROUND

[0002] As an important part of clean and renewable energy, the operation benefit of hydropower generation highly depends on the scientificity and real-time of reservoir dispatching strategy. With the deepening of power market reform, the time-of-use price in the spot market presents significant fluctuation characteristics. If the hydropower station can dynamically adjust the power generation plan according to the price signal and release the reservoir capacity for power generation during the high price period, the economic operation level will be significantly improved. At the same time, the artificial weather modification technology, especially the sound wave rain enhancement, provides a new technical path for active regulation of inflow due to its environmental friendliness and no chemical pollution, which is expected to alleviate the constraints of water resource temporal and spatial distribution on water power dispatching to a certain extent.

[0003] However, there is currently a lack of effective coordination mechanism between the existing water power dispatching system and the sound wave rain enhancement operation. The traditional water power station dispatching focuses more on water regime prediction and unit combination optimization, and does not fully integrate the real-time price signal of the power market, making it difficult to maximize the power generation benefit. On the other hand, the sound wave rain enhancement operation is usually independently decided based on meteorological suitability, and cannot be matched with the real-time operation demand of the reservoir and the high value period of the power market, resulting in that the incremental water resources generated by the rain enhancement may not be effectively utilized during the peak price period, and even abandoned due to reservoir capacity limitation, causing resource waste and cost sunk.

[0004] In addition, the effect of sound wave rain enhancement is influenced by multiple factors such as cloud physical properties and atmospheric water vapor conditions, and has strong uncertainty. The existing technology lacks the ability to quantitatively model the causal relationship between rain enhancement effect and power generation benefit, and cannot accurately evaluate the economic contribution of a single rain enhancement operation to the final power generation benefit, resulting in a lack of reliable economic basis for operation decision-making. More prominently, the current system has not yet built a closed-loop optimization framework of "market demand-dispatching planning-rain enhancement execution-effect feedback", and the operation results cannot be used to continuously correct the prediction and decision-making model, limiting the self-adaptation and intelligent level of the system in long-term operation.

[0005] In summary, the prior art has obvious deficiencies in power market response capability, quantitative evaluation of rain enhancement operation economic benefits, and closed-loop coordination between dispatching and rain enhancement. This fragmented state makes it difficult for hydropower stations to achieve overall optimization of water resource value and power generation benefits in complex and variable market environments and natural conditions. Therefore, there is an urgent need for a collaborative dispatching method and system that can deeply integrate power market price signals, real-time operation status of reservoirs, and resource potential of acoustic rain enhancement, to overcome the key technical bottlenecks of isolated decision-making, uncontrollable benefits, and weak system adaptability in the traditional mode, and to improve the comprehensive competitiveness and sustainable operation capability of hydropower stations. SUMMARY

[0006] To overcome the above problems, the present disclosure provides a water power station acoustic rain enhancement collaborative dispatching method, system, device and medium based on power market signal driving.

[0007] The technical solution of the present disclosure is as follows: In a first aspect, the present disclosure provides a water power station acoustic rain enhancement collaborative dispatching method based on power market signal driving, comprising the following steps: Real-time acquisition of time-of-use electricity price prediction data, current operation state data of the water power station reservoir, and short-term weather forecast data of the operation area within a future set period; Based on the time-of-use electricity price prediction data and the current operation state data, calculate the target reservoir capacity that the water power station reservoir needs to reach before the high electricity price period in the future; Compare the target reservoir capacity with the current actual reservoir capacity of the reservoir. When the water gap exceeds the set threshold, predict the expected incremental reservoir inflow water quantity and the corresponding operation cost that can be obtained through acoustic rain enhancement based on the short-term weather forecast data; Based on the expected incremental reservoir inflow water quantity, the average electricity price of the high electricity price period, and the operation cost, calculate the expected net benefit. When the expected net benefit is greater than the dynamic decision threshold, generate an acoustic rain enhancement operation instruction; Control the acoustic rain enhancement equipment array to execute the operation instruction, and collect actual hydrological data after the operation. Based on the actual hydrological data, update the acoustic rain enhancement benefit prediction model.

[0008] Further, the target reservoir capacity is obtained by the following method: An optimal reservoir capacity planning model is constructed by a dynamic programming algorithm, with the goal of maximizing power generation benefits. Under the conditions of satisfying power generation constraints, ecological flow constraints, and reservoir capacity safety constraints, the target reservoir capacity is solved.

[0009] Further, the objective function of the optimal reservoir capacity planning model is: ; Wherein, is Forecasted electricity prices for different time periods For storage capacity The corresponding power generation water volume function is calculated by combining the turbine efficiency curve and the reservoir water level-capacity relationship curve. The penalty coefficient for warehouse capacity safety. This is the dead water level.

[0010] Furthermore, the expected incremental inflow of water into the reservoir and the corresponding operating costs are predicted using a sound wave rain enhancement benefit prediction model based on a gradient boosting decision tree algorithm. The input features of the sound wave rain enhancement benefit prediction model include cloud cover index, low-altitude water vapor flux, wind speed, and wind direction angle.

[0011] Furthermore, expected net income for: ; in, This represents the average electricity price during periods of high electricity prices. The cost of power generation includes operating energy costs, equipment depreciation costs, and monitoring costs; the revenue from power generation... for: ; in, For the expected increase in water inflow, For water conversion efficiency, The hydropower conversion coefficient is as follows: ; in, The density of water, It is the acceleration due to gravity. For power generation and water purification head, For the overall efficiency of the water turbine, This refers to the duration of periods with high electricity prices.

[0012] Furthermore, the dynamic decision threshold is dynamically adjusted based on historical electricity price fluctuation characteristics and basic operating costs. Specifically, the dynamic threshold... for: ; in, Basic operating costs, The standard deviation of electricity price fluctuations, , This is a constant determined by electricity prices.

[0013] Furthermore, a multi-protocol adaptation method supporting three communication protocols—OPC UA, IEC 60870-5-104, and RESTful API—is adopted to achieve seamless data exchange with power trading centers, hydropower station monitoring systems, and meteorological numerical forecasting platforms. The received time-of-use electricity price forecast data is subjected to a time series integrity check. The time series integrity check is used to check for missing or abnormal jumps in the time-of-use electricity price forecast data, and automatically fills in the missing data. The physical dimension consistency of the current operating status data is verified to ensure that the units of water level, reservoir capacity, and power generation flow conform to the International System of Units (SI) and to verify the monotonically increasing characteristics of the water level-reservoir capacity relationship curve. Spatial grid matching degree analysis is performed on the short-term weather forecast data, including superimposing the latitude and longitude grid in the short-term weather forecast data with the actual boundary of the reservoir catchment area to ensure that the grid resolution is not less than 0.25 degrees and the coverage reaches more than 95%.

[0014] Secondly, this disclosure provides a hydropower station acoustic rain enhancement coordinated dispatch system driven by electricity market signals, comprising: The data access module is used to acquire time-of-use electricity price forecast data, current operating status data of hydropower station reservoirs, and short-term weather forecast data of the operating area in real time for a future set period. The central decision-making engine includes: The reservoir capacity planning unit is used to calculate the target reservoir capacity based on the time-of-use electricity price forecast data and the current operating status data. The benefit prediction unit is used to predict the expected incremental inflow of water into the reservoir and the operating cost of sound wave rain enhancement when the water shortage exceeds a set threshold. An economic assessment unit is used to calculate the expected net income and generate a sound wave rain enhancement operation instruction when it exceeds the dynamic decision threshold. The acoustic rain enhancement execution unit is deployed in the upstream catchment area of ​​the reservoir to receive and execute the operation instructions; The feedback learning module is used to collect actual hydrological data after the operation and update the prediction model in the benefit prediction unit accordingly.

[0015] Furthermore, the data access module includes a multi-protocol adapter and a data quality verification unit.

[0016] Thirdly, this disclosure provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when executed by a processor, the program implements the hydropower station acoustic rain enhancement coordinated scheduling method based on power market signals as described in the first aspect. This disclosure has the following beneficial effects: This disclosure solves the problem of isolated decision-making among systems in the traditional model by integrating time-of-use electricity prices in the electricity market, reservoir operation status and weather forecast data, and using a dynamic programming model to calculate the target reservoir capacity that matches the high electricity price period. This enables rain enhancement operations to accurately serve the dispatching goal of maximizing power generation revenue.

[0017] This disclosure, by constructing a predictive model for the benefits of acoustic rain enhancement and an economic evaluation module, can quantify and predict the power generation revenue and operating costs of incremental water volume, and calculate the expected net profit accordingly. By comparing this with dynamic thresholds, a fundamental shift in operational decision-making from "meteorological suitability" to "economic feasibility" is achieved, ensuring controllable benefits.

[0018] This disclosure collects actual hydrological data after operations through a feedback learning module and continuously updates the benefit prediction model using an incremental learning strategy, constructing a closed loop of "decision-execution-feedback-optimization". This effectively reduces the uncertainty of decision-making, enables the system to have long-term adaptive and learning capabilities, and maintains a high decision accuracy rate. Attached Figure Description

[0019] Figure 1 A flowchart of a hydropower station acoustic rain enhancement collaborative scheduling method based on electricity market signals provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the data interface architecture in an embodiment of the present invention; Figure 3 This is a logic diagram for solving the objective function of the dynamic programming model in this embodiment of the invention; Figure 4 This is a control flowchart of the acoustic rain enhancement device array in an embodiment of the present invention; Figure 5 This is a diagram illustrating the working mechanism of the feedback learning module in an embodiment of the present invention. Detailed Implementation To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0020] Unless otherwise defined, the technical or scientific terms used in this disclosure shall have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms "first," "second," and similar terms used in this disclosure do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships, and these relative positional relationships may change accordingly when the absolute position of the described object changes. To keep the following description of the embodiments of this disclosure clear and concise, detailed descriptions of some known functions and components are omitted.

[0021] The present disclosure will now be described in detail with reference to the accompanying drawings and specific embodiments.

[0022] Firstly, reference Figure 1 This disclosure provides a method for coordinated scheduling of hydropower station acoustic rain enhancement based on electricity market signals, comprising the following steps: Real-time acquisition of time-of-use electricity price forecasts, current operating status data of hydropower station reservoirs, and short-term weather forecasts for the work area within a set future time period; Based on the time-of-use electricity price forecast data and the current operating status data, calculate the target reservoir capacity that the hydropower station reservoir needs to reach before the future high electricity price period; By comparing the target reservoir capacity with the current actual reservoir capacity, when the water shortage exceeds a set threshold, the expected incremental inflow of water and the corresponding operating cost can be predicted through sound wave rain enhancement based on the short-term weather forecast data. Based on the expected incremental water inflow, the average electricity price during periods of high electricity prices, and the operating costs, the expected net profit is calculated; when the expected net profit is greater than the dynamic decision threshold, a sound wave rain enhancement operation instruction is generated. The system controls the acoustic rain enhancement equipment array to execute the operation instructions and collects actual hydrological data after the operation. Based on the actual hydrological data, the acoustic rain enhancement benefit prediction model is updated.

[0023] In one embodiment of this disclosure, the target storage capacity is obtained by the following method: An optimal reservoir capacity planning model is constructed using a dynamic programming algorithm. With the goal of maximizing power generation revenue, the target reservoir capacity is obtained by solving the model while satisfying power generation constraints, ecological flow constraints, and reservoir capacity safety constraints.

[0024] refer to Figure 3 In the initialization phase of the dynamic programming model, parameters such as reservoir water level, unit output constraints, ecological flow requirements, and reservoir capacity safety limits are read, and the objective function is defined as follows: ; in, for Forecasted electricity prices for different time periods For storage capacity The corresponding power generation water volume function is calculated by combining the turbine efficiency curve and the reservoir water level-capacity relationship curve. The penalty coefficient for warehouse capacity safety. This is the dead water level.

[0025] The model solves for the optimal target reservoir capacity sequence over 24 time periods by recursively solving for constraints on power generation, ecological flow, and reservoir safety. Each time period considers four unit combination states and three inflow scenarios. The ecological flow requirement is transformed into a soft constraint using a penalty function method, and the optimal solution meeting the accuracy requirements is obtained within 120 seconds. The dynamic programming model then transmits the calculation results to the economic evaluation module for subsequent comparison of the target reservoir capacity with the current actual reservoir capacity.

[0026] When the water volume gap between the target reservoir capacity and the current actual reservoir capacity exceeds 5% of the total reservoir capacity, the rainfall enhancement benefit prediction model is activated. This model uses an integrated gradient boosting decision tree algorithm to predict the expected incremental inflow of water and its operational costs within a preset operational window. For example... Figure 1 As shown, the rain enhancement benefit prediction model extracts four core features from short-term weather forecast data: cloud cover index, low-level water vapor flux, wind speed, and wind direction angle. The cloud cover index is normalized to a continuous value from 0.1 to 1.0; the low-level water vapor flux retains its original physical units within the range of 200 to 800 g·cm⁻¹·hPa⁻¹·s⁻¹; wind speed data undergoes quality control to ensure values ​​are within the range of 0 to 15 m / s; and the wind direction angle is processed using trigonometric functions to achieve an azimuth of 0 to 360 degrees. During model inference, the input features are first standardized, and then ensemble prediction is performed using 100 decision trees of depth 8. The squared error is used as the splitting criterion for each tree, and the learning rate is set to 0.1. The model output is the expected incremental inflow of water into the reservoir and its 95% confidence interval, calculated using quantile regression. The rain enhancement benefit prediction model then transmits the prediction results to the economic evaluation module for calculating the comprehensive benefit index.

[0027] In one embodiment of this disclosure, the expected incremental inflow of water into the reservoir and the corresponding operating costs are predicted using a sound wave rain enhancement benefit prediction model based on a gradient boosting decision tree algorithm. The input features of the sound wave rain enhancement benefit prediction model include cloud cover index, low-altitude water vapor flux, wind speed, and wind direction angle.

[0028] In one embodiment of this disclosure, the expected net income for: ; in, This represents the average electricity price during periods of high electricity prices. The cost of power generation includes operating energy costs, equipment depreciation costs, and monitoring costs; the revenue from power generation... for: ; in, For the expected increase in water inflow, For water conversion efficiency, The hydropower conversion coefficient is as follows: ; in, The density of water, It is the acceleration due to gravity. For power generation and water purification head, For the overall efficiency of the water turbine, This refers to the duration of periods with high electricity prices.

[0029] In one embodiment of this disclosure, the dynamic decision threshold is dynamically adjusted based on historical electricity price fluctuation characteristics and basic operating costs. Specifically, the dynamic threshold... for: ; in, Basic operating costs, The standard deviation of electricity price fluctuations, , This is a constant determined by electricity prices.

[0030] In one embodiment of this disclosure, a multi-protocol adaptation method supporting three communication protocols—OPC UA, IEC 60870-5-104, and RESTful API—is adopted to achieve seamless data exchange with power trading centers, hydropower station monitoring systems, and meteorological numerical forecasting platforms. like Figure 2 As shown, a time series integrity check is performed on the received time-of-use electricity price forecast data. The time series integrity check is used to check for missing or abnormal jumps in the time-of-use electricity price forecast data, and automatically fills in the missing data. The physical dimension consistency of the current operating status data is verified to ensure that the units of water level, reservoir capacity, and power generation flow conform to the International System of Units (SI) and to verify the monotonically increasing characteristics of the water level-reservoir capacity relationship curve. Spatial grid matching degree analysis is performed on the short-term weather forecast data, including superimposing the latitude and longitude grid in the short-term weather forecast data with the actual boundary of the reservoir catchment area to ensure that the grid resolution is not less than 0.25 degrees and the coverage reaches more than 95%.

[0031] In one embodiment of this disclosure, an array of acoustic rain enhancement devices is deployed in the upstream catchment area of ​​a reservoir, including eight high-power acoustic generators and their local controllers. Figure 4 As shown, the acoustic rain enhancement operation command is transmitted to the local controller via an encrypted communication link. After receiving the command, the local controller executes the equipment self-test process, checking the resonant frequency of the acoustic generator, the power amplifier, and the operating parameters of the cooling system. A gradual power increase strategy is adopted during the operation execution phase. Initially, the system operates at 30% of its rated power for 5 minutes to adapt to the environment, and then gradually increases to 100% of its rated power over 10 minutes. The entire operation cycle is strictly controlled within the operation window confirmed by the weather forecast. The acoustic rain enhancement equipment array continuously monitors the actual inflow rate in the operation area and transmits the data to the feedback learning module.

[0032] In one embodiment of this disclosure, when the water volume gap between the target reservoir capacity and the current actual reservoir capacity exceeds 5% of the total reservoir capacity, the rainfall enhancement benefit prediction model is activated. This model uses an integrated gradient boosting decision tree algorithm to predict the expected incremental inflow of water and its operational costs within a preset operational window. Figure 1 As shown, Rain Enhancement Benefit Prediction Model 3 extracts four core features from short-term weather forecast data, including cloud cover index, low-level water vapor flux, wind speed, and wind direction angle. The cloud cover index is normalized to a continuous value ranging from 0.1 to 1.0, while the low-level water vapor flux retains its original physical units of 200 to 800 g·cm³. -1 ·hPa -1 ·s -1 Within the specified range, wind speed data undergoes quality control to ensure values ​​are between 0 and 15 m / s, and wind direction angles are converted to azimuth angles ranging from 0 to 360 degrees using trigonometric functions. During model inference, the input features are first standardized, then ensembled using 100 decision trees of depth 8. The squared error of each tree is used as the splitting criterion, and the learning rate is set to 0.1. The model output is the expected incremental inflow of water into the reservoir and its 95% confidence interval, calculated using quantile regression. The rainfall enhancement benefit prediction model transmits the prediction results to the economic evaluation module for calculating comprehensive benefit indicators.

[0033] The economic evaluation module receives data from the dynamic programming model and the rain enhancement benefit prediction model. It first calculates the water gap, i.e., the difference between the target reservoir capacity and the current actual reservoir capacity. The comprehensive benefit index is calculated using a multi-factor comprehensive method. The power generation revenue component considers the expected revenue generated during periods of high electricity prices after the expected incremental inflow of water is converted to a water conversion efficiency of 85% to 92%. The cost component covers the operating energy consumption cost of the acoustic rain enhancement equipment array 5, equipment depreciation costs calculated at a depreciation rate of 0.15% per use, and manual monitoring costs. The dynamic decision threshold adjustment mechanism is based on historical electricity price fluctuation characteristics. The economic evaluation module compares the expected net benefit with the dynamic decision threshold. When the expected net benefit is higher than the dynamic decision threshold, it generates an acoustic rain enhancement operation instruction and transmits it to the acoustic rain enhancement equipment array.

[0034] The acoustic rain enhancement array is deployed in the upstream catchment area of ​​the reservoir, comprising eight high-power acoustic generators and their local controllers. For example... Figure 4 As shown, the acoustic rain enhancement operation command is transmitted to the local controller via an encrypted communication link. After receiving the command, the local controller executes the equipment self-test process, checking the resonant frequency of the acoustic generator, the power amplifier, and the operating parameters of the cooling system. A gradual power increase strategy is adopted during the operation execution phase. Initially, the system operates at 30% of its rated power for 5 minutes to adapt to the environment, and then gradually increases to 100% of its rated power over 10 minutes. The entire operation cycle is strictly controlled within the operation window confirmed by the weather forecast. The acoustic rain enhancement equipment array continuously monitors the actual inflow rate in the operation area and transmits the data to the feedback learning module.

[0035] The feedback learning module initiates the data collection and analysis process after the assignment is completed, such as... Figure 5 As shown, actual inflow data were collected from hydrological monitoring stations, and incremental water volume characteristics during the operation period were extracted after eliminating random fluctuations using the moving average method. The feedback learning module simultaneously collected meteorological radar echo data, satellite cloud image evolution sequences, and on-site precipitation observation records for the operation area to construct an evaluation dataset for the operation's effectiveness. The model update employed an incremental learning strategy, collecting the deviation data between the actual incremental water volume and the predicted value after each operation. Model retraining was triggered when the accumulated sample size reached 50 sets. The update process retained the 1000 most correlated samples from historical data, maintaining the model's adaptability to seasonal climate changes through a sliding window mechanism. The feedback learning module then passed the updated model parameters to the rainfall enhancement benefit prediction model, completing closed-loop optimization.

[0036] In the above process, the data interface, dynamic programming model, rain enhancement benefit prediction model, economic evaluation module, acoustic rain enhancement equipment array, and feedback learning module are coordinated and controlled by a central decision engine. These modules work closely together through data flow and control signals. For example, the data interface transmits collected data to the dynamic programming model and the rain enhancement benefit prediction model; the calculation results of the dynamic programming model are transmitted to the economic evaluation module; the decision results of the economic evaluation module are transmitted to the acoustic rain enhancement equipment array; the operational data of the acoustic rain enhancement equipment array is fed back to the feedback learning module; and the updated results of the feedback learning module are then applied to the rain enhancement benefit prediction model. This closed-loop structure ensures the system's intelligence level and long-term adaptability, achieving collaborative optimization of "market demand—scheduling planning—rain enhancement execution—effect feedback."

[0037] In operation, the acoustic rain enhancement array alters cloud structure by emitting sound waves of specific frequencies, promoting the condensation of water vapor into raindrops and thus increasing the inflow into the reservoir. The key to this process lies in the selection of the sound wave frequency and the adjustment of its power, requiring precise control based on meteorological conditions and reservoir demand. Furthermore, the feedback learning module continuously learns from historical operational data and updates the model, gradually improving the accuracy of rain enhancement benefit predictions and optimizing the overall scheduling plan. This closed-loop optimization mechanism not only improves water resource utilization efficiency but also significantly enhances the economic benefits of hydropower stations, providing scientific decision-making support for the hydropower industry in a complex and ever-changing market environment.

[0038] Secondly, this disclosure provides a hydropower station acoustic rain enhancement coordinated dispatch system driven by electricity market signals, comprising: The data access module is used to acquire time-of-use electricity price forecast data, current operating status data of hydropower station reservoirs, and short-term weather forecast data of the operating area in real time for a future set period. The central decision-making engine includes: The reservoir capacity planning unit is used to calculate the target reservoir capacity based on the time-of-use electricity price forecast data and the current operating status data. The benefit prediction unit is used to predict the expected incremental inflow of water into the reservoir and the operating cost of sound wave rain enhancement when the water shortage exceeds a set threshold. An economic assessment unit is used to calculate the expected net income and generate a sound wave rain enhancement operation instruction when it exceeds the dynamic decision threshold. The acoustic rain enhancement execution unit is deployed in the upstream catchment area of ​​the reservoir to receive and execute the operation instructions; The feedback learning module is used to collect actual hydrological data after the operation and update the prediction model in the benefit prediction unit accordingly.

[0039] Furthermore, the data access module includes a multi-protocol adapter and a data quality verification unit.

[0040] Thirdly, this disclosure provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when executed by a processor, the program implements the hydropower station acoustic rain enhancement coordinated scheduling method based on power market signals as described in the first aspect. The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0041] The units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the units are not, in some cases, intended to limit the specific unit.

[0042] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0043] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0044] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0045] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

[0046] The following points should be noted regarding this disclosure: (1) The accompanying drawings of the embodiments of this disclosure only involve the structures involved in the embodiments of this disclosure. Other structures can be referred to the general design.

[0047] (2) Where there is no conflict, the embodiments of this disclosure and the features in the embodiments can be combined with each other to obtain new embodiments.

[0048] The above description is merely an embodiment of this disclosure and does not limit the patent scope of this disclosure. Any equivalent structure made using the content of this disclosure and its drawings, or directly or indirectly applied to other related technical fields, is similarly included within the patent protection scope of this disclosure.

Claims

1. A method for coordinated dispatching of acoustic rain enhancement of a hydropower station based on power market signals, characterized in that, The method comprises the following steps: obtaining, in real time, time-of-use electricity price prediction data in a future set period, current operation state data of a reservoir of a hydropower station, and short-term weather forecast data of an operation area; based on the time-of-use electricity price prediction data and the current operation state data, calculating a target reservoir capacity that the reservoir of the hydropower station needs to reach before a high electricity price period in the future; comparing the target reservoir capacity with a current actual reservoir capacity of the reservoir, and when a water quantity gap exceeds a set threshold, predicting, according to the short-term weather forecast data, an expected incremental reservoir water quantity obtainable through acoustic rain enhancement and a corresponding operation cost; based on the expected incremental reservoir water quantity, an average electricity price of the high electricity price period, and the operation cost, calculating an expected net benefit, and when the expected net benefit is greater than a dynamic decision threshold, generating an acoustic rain enhancement operation instruction; controlling an acoustic rain enhancement device array to execute the operation instruction, and collecting actual hydrological data after the operation, and updating an acoustic rain enhancement benefit prediction model based on the actual hydrological data.

2. The method of claim 1, wherein the method further comprises: The target reservoir capacity is obtained by: constructing an optimal reservoir capacity planning model by a dynamic programming algorithm, and taking maximization of power generation benefit as a target, and under conditions of satisfying power generation constraints, ecological flow constraints, and reservoir capacity safety constraints, solving the target reservoir capacity.

3. The method of claim 2, wherein the method further comprises: The objective function of the optimal reservoir capacity planning model is: ； wherein, is the period prediction price, is the reservoir capacity a corresponding power generation water volume function, which is calculated by compounding a water turbine efficiency curve and a reservoir water level-capacity relationship curve; is a capacity safety penalty coefficient, is the dead water level.

4. The method of claim 1, wherein the method further comprises: The expected incremental reservoir water quantity and the corresponding operation cost are predicted by an acoustic rain enhancement benefit prediction model based on a gradient boosting decision tree algorithm, and input features of the acoustic rain enhancement benefit prediction model include a cloud cover index, a low-altitude water vapor flux, a wind speed, and a wind direction angle.

5. The method of claim 1, wherein the method further comprises: Expected net revenue Is: ； wherein, is the average electricity price for the high electricity price period, is the generation cost including the operation energy consumption cost, the equipment depreciation cost and the monitoring cost, the generation revenue is: ； wherein, is the expected incremental water storage, is the water conversion efficiency, is the water energy conversion coefficient, in particular: ； wherein, is the density of water, is the acceleration of gravity, is the net head of electricity generation, is the overall efficiency of the turbine, is the duration of the high electricity price period.

6. The method of claim 1, wherein the method further comprises: The dynamic decision threshold is dynamically adjusted according to historical electricity price fluctuation characteristics and basic operation cost. Specifically, the dynamic threshold is: ； wherein, is the base operating cost, is the standard deviation of the electricity price fluctuations, , is a constant determined by the electricity price.

7. The method of claim 1, wherein the method further comprises: A multi-protocol adaptation mode supporting three communication protocols of OPC UA, IEC 60870-5-104, and RESTful API is adopted to realize seamless data exchange with a power trading center, a hydropower station monitoring system, and a numerical weather prediction platform of a meteorological department; time series integrity verification is performed on the received time-of-use electricity price prediction data, and the time series integrity verification is used to check missing or abnormal jumps of time-of-use electricity price prediction price data, and the data is automatically completed when missing; dimension consistency verification is implemented on the current operation state data, so as to ensure that water level, reservoir capacity, and power generation flow units conform to international system of units specifications, and to verify a monotonically increasing characteristic of a water level-reservoir capacity relationship curve; spatial grid matching degree analysis is carried out on the short-term weather forecast data, including superimposed calculation of longitude and latitude grids in the short-term weather forecast data and actual boundaries of a reservoir catchment area, so as to ensure that a grid resolution is not less than 0.25 degrees and a coverage rate is more than 95%.

8. A system for coordinated dispatching of acoustic rain enhancement of a hydropower station based on power market signals, characterized in that, The method comprises: a data access module, configured to obtain, in real time, time-of-use electricity price prediction data in a future set period, current operation state data of a reservoir of a hydropower station, and short-term weather forecast data of an operation area; a central decision engine, comprising: a reservoir capacity planning unit, configured to calculate a target reservoir capacity based on the time-of-use electricity price prediction data and the current operation state data; a benefit prediction unit, configured to predict, when a water quantity gap exceeds a set threshold, an expected incremental reservoir water quantity of acoustic rain enhancement and an operation cost; an economic evaluation unit, configured to calculate an expected net benefit, and generate an acoustic rain enhancement operation instruction when the expected net benefit is greater than a dynamic decision threshold. The acoustic wave rain enhancement execution unit is arranged in the water collecting area upstream of the reservoir and is used for receiving and executing the operation instruction. The feedback learning module is used for collecting actual hydrological data after operation and updating the prediction model in the benefit prediction unit.

9. The system according to claim 1, characterized in that, The data access module comprises a multi-protocol adapter and a data quality checking unit.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to realize the acoustic wave rain enhancement collaborative scheduling method of the hydropower station based on the power market signal driving as claimed in any one of claims 1 to 7.

Images