Method and system for long-term optimal scheduling of hydropower station considering power output uncertainty

Abstract

This application relates to the field of hydropower energy optimization scheduling technology, and discloses a medium- and long-term optimization scheduling method and system for hydropower stations that takes into account output uncertainty. The scheduling method includes: establishing an optimization scheduling model, which is constructed based on Bayesian stochastic dynamic programming with the objective of maximizing the expected revenue of the hydropower station; obtaining the runoff probability forecast distribution function for the future scheduling period, and discretizing the runoff probability forecast distribution function to generate a cumulative probability sequence and a runoff forecast discrete value sequence; generating an output plan sequence based on the runoff forecast discrete value sequence and using the scheduling rules in the model; obtaining the expected value of the power generation plan according to the output plan sequence, and using the expected value as the power generation plan; implementing the power generation plan during the scheduling period, and evaluating the power generation benefits. The embodiments of this application can effectively improve the power generation efficiency of hydropower stations.

Description

Technical Field

[0001] This application relates to the field of hydropower energy optimization and dispatching technology, specifically to a method and system for medium- and long-term optimization and dispatching of hydropower stations that takes into account output uncertainty. Background Technology

[0002] With the continuous development of runoff forecasting technology and hydropower station optimal scheduling theory, forecast-scheduling coupling models have become an important way to improve the operational efficiency of hydropower stations. However, due to the complexity of hydrological processes and the inherent limitations of forecasting models, runoff forecasts inevitably contain uncertainties, which affect the formulation of scheduling decisions and the final power generation benefits. How to effectively utilize forecast information, especially the uncertainties inherent in probabilistic forecasts, has become a research hotspot in the field of reservoir optimal scheduling.

[0003] In existing technologies, various evaluation and optimization methods have been proposed for forecast-schedule coupling. For example, the evaluation method for runoff forecasting systems based on hydropower station scheduling decision-making methods described in application number CN116911440A generates hypothetical forecasting systems of different qualities through an improved generalized maintenance variance expansion method, and evaluates the impact of different forecast attributes on the power generation benefits and risks of cascade hydropower stations based on multiple scheduling decision-making models. This method focuses on evaluating the "value" of the forecasting system and the "feedback" of the scheduling method, without directly utilizing the complete distribution information of probabilistic forecasts to formulate specific power generation plans. Furthermore, in practice, it is common to optimize scheduling based on deterministic runoff forecast results or by using only the expected value of probabilistic forecasts as a single input. However, such methods fail to fully explore and utilize the quantitative information about uncertainty in probabilistic forecasts, and do not consider how the uncertainty of runoff forecasts propagates and affects the distribution characteristics of the optimal power generation plan itself. This leads to the possibility that the formulated power generation plan may not be optimal when there are biases or inaccuracies in the forecast, thus limiting the improvement of hydropower station power generation benefits. Summary of the Invention

[0004] In view of the above-mentioned defects or deficiencies in the existing technology, it is desirable to provide a method and system for medium- and long-term optimal scheduling of hydropower stations that takes into account the uncertainty of output, so as to effectively improve the power generation efficiency of hydropower stations.

[0005] In a first aspect, embodiments of this application provide a method for medium- and long-term optimal scheduling of hydropower stations that takes into account output uncertainty, including: An optimal scheduling model is established, wherein the optimal scheduling model is constructed based on Bayesian stochastic dynamic programming with the objective of maximizing the expected value of hydropower generation revenue. Obtain the runoff probability forecast distribution function for the future scheduling period, and discretize the runoff probability forecast distribution function to generate a cumulative probability sequence and a corresponding runoff forecast discrete value sequence. Based on the discrete value sequence of runoff forecast, the power output plan sequence corresponding to each discrete value in the discrete value sequence of runoff forecast is generated using the scheduling rules in the optimized scheduling model. The power output plan sequence constitutes the probability distribution of the optimal power generation plan. Based on the output plan sequence, the expected value of the power generation plan is obtained, and the expected value is used as the final power generation plan to be executed; The power generation plan will be implemented during the scheduling period, and the power generation benefits will be evaluated.

[0006] In some examples, the construction process of the optimized scheduling model is as follows: A target function is constructed with the objective of maximizing the expected revenue of the hydropower station during the scheduling period. The recursive relationship of the objective function is constructed based on Bayesian stochastic dynamic programming; A constraint system is constructed, including water balance constraints, upper and lower limits of water level constraints, discharge capacity constraints, power generation constraints, water level-reservoir capacity correspondence constraints, and water level-discharge relationship constraints.

[0007] In some examples, obtaining the runoff probability forecast distribution function for the future scheduling period and discretizing the runoff probability forecast distribution function to generate a cumulative probability sequence and a corresponding runoff forecast discrete value sequence includes: Obtain the runoff probability forecast distribution function for each time period within the future scheduling period; Based on a preset discretization precision, the cumulative probability is uniformly discretized within a predetermined interval to generate a cumulative probability sequence. Based on the runoff probability forecast distribution function, the runoff forecast value corresponding to each cumulative probability value in the cumulative probability sequence is extracted to form a runoff forecast discrete value sequence.

[0008] In some examples, generating a power output plan sequence corresponding to each discrete value in the runoff forecast discrete value sequence includes: For each discrete runoff forecast value in the runoff forecast discrete value sequence, the corresponding power output plan value is calculated based on the scheduling rules determined in the optimized scheduling model, forming a power output plan sequence, wherein the cumulative probability corresponding to each power output plan value in the power output plan sequence is consistent with the cumulative probability sequence.

[0009] In some examples, obtaining the expected value of the power generation plan based on the power output plan sequence includes: The expected value of the power generation plan is obtained by performing a weighted average operation on the power generation plan sequence based on the difference between adjacent cumulative probability values ​​in the cumulative probability sequence as the probability weight corresponding to each planned power output value.

[0010] In some examples, the implementation of the power generation plan during the scheduling period also includes: The process of real-time feedback and correction of the reservoir's operational status based on actual water inflow is as follows: At the beginning of each time period, the state variables of the scheduling model are updated and optimized based on the current reservoir water storage and the actual observed runoff of the previous time period. Based on the updated state variables and the runoff probability forecast distribution for the next time period, the discretization process, power output plan sequence generation and weighted averaging steps are re-executed to generate the power generation plan for the current time period.

[0011] In some examples, when calculating the probability distribution of the optimal power generation plan based on the power output plan sequence, the deviation between each power output plan value and the expected value of the power generation plan is extracted, and the operation risk index is calculated. The operation risk index includes the probability of insufficient power output under extreme water inflow scenarios, the maximum power output deficit, and the corresponding economic loss. When constructing the constraint system of the optimized scheduling model, the operation risk index is used as the risk constraint condition, and a preset control threshold is set for each operation risk index. The preset control threshold is determined based on the hydropower station engineering design parameters, the characteristics of historical extreme hydrological events in the basin, and the requirements for safe and stable operation of the power grid. By employing a recursive solution process using Bayesian stochastic dynamic programming, the objective function of the optimized scheduling model is iteratively optimized while satisfying risk constraints, thereby achieving a synergistic optimal balance between maximizing expected power generation revenue and controlling operational risks during the scheduling period.

[0012] Secondly, embodiments of this application provide a medium- to long-term optimal dispatching system for hydropower stations that takes into account output uncertainty, including: The model building module is used to establish an optimal scheduling model, wherein the optimal scheduling model is constructed based on Bayesian stochastic dynamic programming with the objective of maximizing the expected value of hydropower generation revenue. The forecast processing module is used to obtain the runoff probability forecast distribution function for the future scheduling period, and to discretize the runoff probability forecast distribution function to generate a cumulative probability sequence and a corresponding runoff forecast discrete value sequence. The planning generation module is used to generate a power output plan sequence corresponding to each discrete value in the runoff forecast discrete value sequence based on the runoff forecast discrete value sequence and using the scheduling rules in the optimized scheduling model, wherein the power output plan sequence constitutes the probability distribution of the optimal power generation plan; The planning synthesis module is used to obtain the expected value of the power generation plan based on the output plan sequence, and use the expected value as the final power generation plan to be executed; The execution and feedback module is used to implement the power generation plan during the scheduling period and to provide real-time feedback and rolling correction of the reservoir's operating status based on the actual water inflow.

[0013] Thirdly, embodiments of this application provide a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the long-term optimal scheduling method for hydropower stations that takes into account output uncertainty, as described in the embodiments of the first aspect of this application.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the medium- and long-term optimal scheduling method for hydropower stations that takes into account output uncertainty, as described in the embodiments of the first aspect of this application.

[0015] In this embodiment, a Bayesian stochastic dynamic programming optimization scheduling model is established with the objective of maximizing the expected value of power generation revenue. The runoff probability forecast distribution function for the future scheduling period is obtained and discretized to obtain a cumulative probability sequence and the corresponding runoff forecast discrete value sequence. Based on the discrete value sequence and scheduling rules, an output plan sequence corresponding to each discrete value is generated to form the probability distribution of the optimal power generation plan. Finally, the expected value of the power generation plan is obtained from the output plan sequence as the final execution plan to implement the plan and evaluate the power generation benefits. This can effectively solve the problem that the existing long-term optimization scheduling strategy of hydropower stations fails to fully utilize the uncertainty information in the runoff probability forecast, resulting in suboptimal power generation plan formulation and limiting the improvement of power generation benefits. This can effectively improve the power generation benefits of hydropower stations.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart illustrating a method for medium- and long-term optimal scheduling of hydropower stations that takes into account output uncertainty, according to one embodiment of this application. Figure 2 This is a schematic diagram illustrating the calculation of the output distribution function in a long-term optimal scheduling method for hydropower stations that takes into account output uncertainty, according to an embodiment of this application. Figure 3 This is a structural block diagram of a long-term optimal dispatching system for a hydropower station that takes into account output uncertainty, according to an embodiment of this application. Figure 4 This is a structural block diagram of a long-term optimal dispatching system for a hydropower station that takes into account output uncertainty, according to another embodiment of this application. Figure 5This is a structural block diagram of a long-term optimal dispatching system for a hydropower station that takes into account output uncertainty, according to another embodiment of this application. Figure 6 A schematic diagram of a computing device suitable for implementing embodiments of this application is shown. Detailed Implementation

[0018] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the relevant application and not intended to limit the application. Furthermore, it should be noted that, for ease of description, only the parts relevant to the application are shown in the accompanying drawings.

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] The following describes, with reference to the accompanying drawings, a method and system for medium- and long-term optimal scheduling of hydropower stations that takes into account output uncertainty, according to embodiments of this application.

[0021] Figure 1 This is a flowchart of a long-term optimal scheduling method for hydropower stations that takes into account output uncertainty, according to an embodiment of this application. Figure 1 As shown, a long-term optimal scheduling method for hydropower stations that takes into account output uncertainty, according to an embodiment of this application, includes the following steps: S101: Establish an optimal scheduling model, wherein the optimal scheduling model is constructed based on Bayesian stochastic dynamic programming with the objective of maximizing the expected value of hydropower generation revenue.

[0022] This optimized scheduling model is a medium- to long-term optimized scheduling model. Specifically, the construction process of the medium- to long-term optimized scheduling model is as follows: With the objective of maximizing the expected revenue from hydropower generation during the scheduling period, an objective function is constructed, as shown in Formula 1: (1) in, ; Indicates the time period within the scheduling period The maximum expected revenue from the initial hydroelectric power plant; Number the current time period; This represents the total number of time periods during the scheduling period; For expected value operators; For the hydropower station during the period Electricity revenue; For time period Initial reservoir water storage capacity; For time period The power generation flow rate; For time period The reservoir's water storage capacity at the end; This refers to the power output coefficient of the hydropower station. For time period The head of the generator for clean water; For time period The on-grid electricity price; This represents the length of the time period.

[0023] The recursive relation of the objective function is constructed based on Bayesian stochastic dynamic programming, and the recursive equation is shown in Equation 2: (2) in, This indicates that, given the initial state and forecast information, from the time period... The initial maximum expected income; For time period The power generation flow rate; For time period Runoff forecast values; Indicates in Measured runoff during the time period was class, Forecast runoff for the period is At level 1, the measured runoff was The probability of level; Indicates in Measured runoff during the time period was Level 1, next time period ( ) Measured runoff The probability of level; This is the optimal expected income function for the next time period.

[0024] A constraint system is constructed, including water balance constraints, upper and lower limits of water level constraints, discharge capacity constraints, power generation constraints, water level-reservoir capacity correspondence constraints, and water level-discharge relationship constraints. The specific implementation standards of the constraints are determined based on the hydropower station engineering design parameters and the hydrological characteristics of the basin.

[0025] S102: Obtain the runoff probability forecast distribution function for the future scheduling period, and discretize the runoff probability forecast distribution function to generate a cumulative probability sequence and a corresponding runoff forecast discrete value sequence.

[0026] Specifically, the process of obtaining the runoff probability forecast distribution function for the future scheduling period, and discretizing the distribution function to generate the cumulative probability sequence and its corresponding runoff forecast discrete value sequence is as follows: Obtain the runoff probability forecast distribution function for each time period within the future scheduling period; Based on preset discrete precision In the interval The cumulative probability is uniformly discretized to generate a cumulative probability sequence. ; Based on the runoff probability forecast distribution function, extract the cumulative probability sequence. The runoff forecast value corresponding to each cumulative probability value constitutes a discrete runoff forecast value sequence. ,in, This represents the runoff value obtained by inversion from the cumulative distribution function.

[0027] S103: Based on the discrete value sequence of runoff forecast, using the scheduling rules in the optimized scheduling model, generate a power output plan sequence corresponding to each discrete value in the discrete value sequence of runoff forecast, wherein the power output plan sequence constitutes the probability distribution of the optimal power generation plan. Figure 2 As shown, the power output plan distribution function can be calculated from the probability prediction distribution function.

[0028] In one embodiment of this application, the specific process for generating the power output plan sequence corresponding to each discrete value is as follows: For each discrete runoff forecast value in the runoff forecast discrete value sequence, the scheduling rules determined in the medium- and long-term optimization scheduling model are applied. The corresponding planned output values ​​are calculated, forming a planned output sequence. The cumulative probability corresponding to each planned output value in the sequence and the cumulative probability sequence Maintain consistency.

[0029] S104: Based on the output plan sequence, obtain the expected value of the power generation plan, and use the expected value as the final power generation plan to be executed.

[0030] For example, a probability-weighted average is calculated on the power output plan sequence to obtain the expected value of the power generation plan, and this expected value is used as the final power generation plan to be executed. Specifically, this is based on the cumulative probability sequence. The difference between adjacent cumulative probability values ​​is used as the probability weight corresponding to each planned output value for the planned output sequence. The expected value of the power generation plan is obtained by performing a weighted average calculation, as shown in Formula 3 below: (3) in, For time period The expected value of the power generation plan; For discretized index variables, the value range is from arrive An integer is used to iterate through all discretized cumulative probability points; The th in the cumulative probability sequence The nth value represents the nth... The cumulative probability of a discrete point; The th in the cumulative probability sequence Each value represents the cumulative probability of the next discrete point; For the corresponding cumulative probability The planned output value.

[0031] S105: Implement the power generation plan during the dispatch period and conduct a power generation benefit assessment.

[0032] The power generation plan, when implemented during the scheduling period, also includes a process of real-time feedback and correction of the reservoir's operational status based on actual water inflow conditions. Specifically: At the beginning of each time period, the state variables of the medium- and long-term optimization scheduling model are updated based on the current reservoir water storage and the actual observed runoff of the previous time period. Based on the updated state variables and the runoff probability forecast distribution of the next time period, the discretization process, power output plan sequence generation and weighted averaging steps are re-executed to generate the power generation plan for the current time period.

[0033] In one embodiment of this application, based on the probability distribution of the optimal power generation plan constituted by the power output plan sequence, the deviation between each power output plan value and the expected value of the power generation plan is extracted, and an operational risk index is calculated. The operational risk index includes the probability of insufficient power output under extreme water inflow scenarios, the maximum power output deficit, and the corresponding economic loss.

[0034] When constructing the constraint system of the medium- and long-term optimization scheduling model, the operational risk indicators are used as risk constraints, and preset control thresholds are set for each risk indicator. The preset control thresholds are determined based on the hydropower station engineering design parameters, the characteristics of historical extreme hydrological events in the basin, and the requirements for safe and stable operation of the power grid.

[0035] By employing a recursive solution process using Bayesian stochastic dynamic programming, the objective function of the medium- to long-term optimal scheduling model is iteratively optimized while satisfying the aforementioned risk constraints, thereby achieving a synergistic optimal balance between maximizing expected power generation revenue and ensuring controllable operational risks during the scheduling period.

[0036] The long-term optimal scheduling method for hydropower stations that takes into account output uncertainty, according to an embodiment of this application, establishes a Bayesian stochastic dynamic programming optimal scheduling model with the objective of maximizing the expected value of power generation revenue. It obtains and discretizes the runoff probability forecast distribution function for the future scheduling period to obtain a cumulative probability sequence and the corresponding runoff forecast discrete value sequence. Based on the discrete value sequence and scheduling rules, it generates a power output plan sequence corresponding to each discrete value, forming the probability distribution of the optimal power generation plan. Finally, it obtains the expected value of the power generation plan based on the power output plan sequence as the final execution plan to implement the plan and evaluate the power generation benefits. This method effectively solves the problem that existing long-term optimal scheduling strategies for hydropower stations fail to fully utilize the uncertainty information in runoff probability forecasts, leading to suboptimal power generation plan formulation and limiting the improvement of power generation benefits. Therefore, it can effectively improve the power generation benefits of hydropower stations.

[0037] The embodiments of this application have the following advantages: By introducing the distribution function of runoff probability forecast and constructing an optimization model based on Bayesian stochastic dynamic programming, the impact of runoff uncertainty on scheduling decisions can be fully quantified. When formulating power generation plans, not only the expected value of the forecast is considered, but also the power generation revenue under different possible runoff scenarios is comprehensively considered, thereby generating an optimal scheduling scheme that balances expected benefits and risk control, and improving the power generation revenue of hydropower stations.

[0038] By discretizing the probability forecast distribution and generating a power output plan sequence corresponding to each discrete value, the probability distribution of the optimal power generation plan is constructed. This clearly depicts the transmission mechanism of runoff forecast uncertainty to the power generation plan distribution, making the final adopted power generation plan more statistically representative and practically operable, and reducing the scheduling risk caused by forecast deviation.

[0039] By using probabilistic forecasts as direct input to the optimization model, the entire chain of coupling from forecasting to scheduling decisions is realized. By dynamically updating the runoff state probability and adjusting the power output plan, it can flexibly respond to random changes in runoff, thereby continuously approaching the theoretical optimal operating state in long-term scheduling and improving the overall operating efficiency and adaptability of the hydropower station.

[0040] Figure 3 This is a structural block diagram of a long-term optimal dispatching system for a hydropower station that takes into account output uncertainty, according to an embodiment of this application. Figure 3 As shown, a medium- and long-term optimal scheduling system for hydropower stations that takes into account output uncertainty according to an embodiment of this application specifically includes: a model building module 310, a forecast processing module 320, a plan generation module 330, a plan synthesis module 340, and an execution and feedback module 350, wherein: The model building module 310 is used to establish an optimal scheduling model, wherein the optimal scheduling model is constructed based on Bayesian stochastic dynamic programming with the objective of maximizing the expected value of hydropower generation revenue. The forecast processing module 320 is used to obtain the runoff probability forecast distribution function for the future scheduling period, and to discretize the runoff probability forecast distribution function to generate a cumulative probability sequence and a corresponding runoff forecast discrete value sequence. The planning generation module 330 is used to generate a power output plan sequence corresponding to each discrete value in the runoff forecast discrete value sequence based on the runoff forecast discrete value sequence and using the scheduling rules in the optimized scheduling model, wherein the power output plan sequence constitutes the probability distribution of the optimal power generation plan; The planning synthesis module 340 is used to obtain the expected value of the power generation plan based on the output plan sequence, and use the expected value as the final power generation plan to be executed; The execution and feedback module 350 is used to implement the power generation plan during the scheduling period and to provide real-time feedback and rolling correction of the reservoir operation status based on the actual water inflow.

[0041] The execution and feedback module 350 can execute the power generation plan on one hand, and provide feedback and corrections on the other. Figure 4 As shown, the execution and feedback module 350 can also be connected to the model building module, so that feedback can be given to the model building module.

[0042] In some embodiments, such as Figure 5 As shown, the execution and feedback module includes a rolling optimization unit, which is used to update the state variables in the model building module at the beginning of each scheduling period based on the current actual reservoir water storage and observed runoff, and trigger the forecast processing module, the plan generation module and the plan synthesis module to re-execute their functions in order to generate and update the power generation plan for the current period.

[0043] In some embodiments, combined with Figure 5 As shown, the medium- and long-term optimal dispatch system for hydropower stations that takes into account output uncertainty may further include a risk constraint module, which is connected to the model building module and the plan generation module. The risk constraint module is used to: calculate operational risk indicators, including the probability of insufficient output and the maximum output deficit, based on the optimal power generation plan probability distribution output by the plan generation module; and input the operational risk indicators as risk constraint conditions into the constraint system of the model building module, so as to coordinate the optimization of expected power generation revenue and operational risk during the solution process of the medium- and long-term optimal dispatch model.

[0044] According to the embodiments of this application, a medium- and long-term optimal scheduling system for hydropower stations that takes into account output uncertainty is established. A Bayesian stochastic dynamic programming optimal scheduling model is established with the objective of maximizing the expected value of power generation revenue. The runoff probability forecast distribution function in the future scheduling period is obtained and discretized to obtain a cumulative probability sequence and the corresponding runoff forecast discrete value sequence. Based on the discrete value sequence and scheduling rules, the output plan sequence corresponding to each discrete value is generated to form the probability distribution of the optimal power generation plan. Finally, the expected value of the power generation plan is obtained from the output plan sequence as the final execution plan to implement the plan and evaluate the power generation benefits. This system can effectively solve the problem that the existing medium- and long-term optimal scheduling strategies for hydropower stations fail to fully utilize the uncertainty information in the runoff probability forecast, resulting in suboptimal power generation plan formulation and limiting the improvement of power generation benefits. This system can effectively improve the power generation benefits of hydropower stations.

[0045] It should be noted that the specific implementation of the long-term optimal scheduling system for hydropower stations that takes into account output uncertainty in the embodiments of this application is similar to the specific implementation of the long-term optimal scheduling method for hydropower stations that takes into account output uncertainty in the embodiments of this application. For details, please refer to the description in the method section, which will not be repeated here.

[0046] The following is for reference. Figure 6 , Figure 6 A schematic diagram of a computing device structure suitable for implementing embodiments of this application is shown.

[0047] like Figure 6 As shown, the computer system 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 1002 or programs loaded from storage section 1008 into random access memory (RAM) 1003. The RAM 1003 also stores various programs and data required for the system's operating instructions. The CPU 1001, ROM 1002, and RAM 1003 are interconnected via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0048] The following components are connected to I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to I / O interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 1010 as needed so that computer programs read from it can be installed into storage section 1008 as needed.

[0049] Specifically, according to embodiments of this application, the flowchart above refers to... Figure 1 The described process can be implemented as a computer software program. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such an embodiment, the computer program contains program code for performing the methods shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by central processing unit (CPU) 1001, it performs the functions defined in the system of this application.

[0050] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0051] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operational instructions of possible implementations of systems, methods, and computer program products according to various embodiments of this application. 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 connected blocks may actually be executed substantially in parallel, or 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 functions or operational instructions, or using a combination of dedicated hardware and computer instructions.

[0052] The units or modules described in the embodiments of this application can be implemented in software or hardware. The described units or modules can also be located in a processor. The names of these units or modules do not, in certain circumstances, constitute a limitation on the unit or module itself.

[0053] In another aspect, this application also provides a computer-readable storage medium, which may be included in the computing device described in the above embodiments, or may exist independently and not assembled into the computing device. The aforementioned computer-readable storage medium stores one or more programs that, when used by one or more processors, execute the long-term optimal scheduling method for hydropower stations considering output uncertainty described in this application. Specifically: An optimized scheduling model is established, which is constructed based on Bayesian stochastic dynamic programming with the objective of maximizing the expected revenue of hydropower generation; the runoff probability forecast distribution function for the future scheduling period is obtained, and the runoff probability forecast distribution function is discretized to generate a cumulative probability sequence and a corresponding runoff forecast discrete value sequence; based on the runoff forecast discrete value sequence, using the scheduling rules in the optimized scheduling model, a power output plan sequence corresponding to each discrete value in the runoff forecast discrete value sequence is generated, wherein the power output plan sequence constitutes the probability distribution of the optimal power generation plan; according to the power output plan sequence, the expected value of the power generation plan is obtained, and the expected value is used as the final executed power generation plan; the power generation plan is implemented during the scheduling period, and the power generation benefit is evaluated.

[0054] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application 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 foregoing disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for medium- and long-term optimal scheduling of hydropower stations considering output uncertainty, characterized in that, include: An optimal scheduling model is established, wherein the optimal scheduling model is constructed based on Bayesian stochastic dynamic programming with the objective of maximizing the expected value of hydropower generation revenue. Obtain the runoff probability forecast distribution function for the future scheduling period, and discretize the runoff probability forecast distribution function to generate a cumulative probability sequence and a corresponding runoff forecast discrete value sequence. Based on the discrete value sequence of runoff forecast, the power output plan sequence corresponding to each discrete value in the discrete value sequence of runoff forecast is generated using the scheduling rules in the optimized scheduling model. The power output plan sequence constitutes the probability distribution of the optimal power generation plan. Based on the output plan sequence, the expected value of the power generation plan is obtained, and the expected value is used as the final power generation plan to be executed; The power generation plan will be implemented during the scheduling period, and the power generation benefits will be evaluated.

2. The long-term optimal scheduling method for hydropower stations considering output uncertainty according to claim 1, characterized in that, The construction process of the optimized scheduling model is as follows: A target function is constructed with the objective of maximizing the expected revenue of the hydropower station during the scheduling period. The recursive relationship of the objective function is constructed based on Bayesian stochastic dynamic programming; A constraint system is constructed, including water balance constraints, upper and lower limits of water level constraints, discharge capacity constraints, power generation constraints, water level-reservoir capacity correspondence constraints, and water level-discharge relationship constraints.

3. The long-term optimal scheduling method for hydropower stations considering output uncertainty according to claim 1, characterized in that, The step of obtaining the runoff probability forecast distribution function for the future scheduling period, and discretizing the runoff probability forecast distribution function to generate a cumulative probability sequence and a corresponding runoff forecast discrete value sequence, includes: Obtain the runoff probability forecast distribution function for each time period within the future scheduling period; Based on a preset discretization precision, the cumulative probability is uniformly discretized within a predetermined interval to generate a cumulative probability sequence. Based on the runoff probability forecast distribution function, the runoff forecast value corresponding to each cumulative probability value in the cumulative probability sequence is extracted to form a runoff forecast discrete value sequence.

4. The long-term optimal scheduling method for hydropower stations considering output uncertainty according to claim 3, characterized in that, The generation of the power output plan sequence corresponding to each discrete value in the runoff forecast discrete value sequence includes: For each discrete runoff forecast value in the runoff forecast discrete value sequence, the corresponding power output plan value is calculated based on the scheduling rules determined in the optimized scheduling model, forming a power output plan sequence, wherein the cumulative probability corresponding to each power output plan value in the power output plan sequence is consistent with the cumulative probability sequence.

5. The long-term optimal scheduling method for hydropower stations considering output uncertainty according to claim 4, characterized in that, The step of obtaining the expected value of the power generation plan based on the output plan sequence includes: The expected value of the power generation plan is obtained by performing a weighted average operation on the power generation plan sequence based on the difference between adjacent cumulative probability values ​​in the cumulative probability sequence as the probability weight corresponding to each planned power output value.

6. The long-term optimal scheduling method for hydropower stations considering output uncertainty according to claim 1, characterized in that, The implementation of the power generation plan during the scheduling period also includes: The process of real-time feedback and correction of the reservoir's operational status based on actual water inflow is as follows: At the beginning of each time period, the state variables of the scheduling model are updated and optimized based on the current reservoir water storage and the actual observed runoff of the previous time period. Based on the updated state variables and the runoff probability forecast distribution for the next time period, the discretization process, power output plan sequence generation and weighted averaging steps are re-executed to generate the power generation plan for the current time period.

7. The long-term optimal scheduling method for hydropower stations considering output uncertainty according to claim 1, characterized in that, When calculating the probability distribution of the optimal power generation plan based on the power output plan sequence, the deviation between each power output plan value and the expected value of the power generation plan is extracted, and the operation risk index is calculated. The operation risk index includes the probability of insufficient power output under extreme water inflow scenarios, the maximum power output deficit and the corresponding economic loss. When constructing the constraint system of the optimized scheduling model, the operation risk index is used as the risk constraint condition, and a preset control threshold is set for each operation risk index. The preset control threshold is determined based on the hydropower station engineering design parameters, the characteristics of historical extreme hydrological events in the basin, and the requirements for safe and stable operation of the power grid. During the recursive solution process of Bayesian stochastic dynamic programming, while satisfying the risk constraints, the objective function of the optimized scheduling model is iteratively optimized to achieve the synergistic optimality of maximizing the expected value of power generation revenue and keeping the operational risk under control during the scheduling period.

8. A medium- and long-term optimal dispatching system for hydropower stations that takes into account output uncertainty, characterized in that, include: The model building module is used to establish an optimal scheduling model, wherein the optimal scheduling model is constructed based on Bayesian stochastic dynamic programming with the objective of maximizing the expected value of hydropower generation revenue. The forecast processing module is used to obtain the runoff probability forecast distribution function for the future scheduling period, and to discretize the runoff probability forecast distribution function to generate a cumulative probability sequence and a corresponding runoff forecast discrete value sequence. The planning generation module is used to generate a power output plan sequence corresponding to each discrete value in the runoff forecast discrete value sequence based on the runoff forecast discrete value sequence and using the scheduling rules in the optimized scheduling model, wherein the power output plan sequence constitutes the probability distribution of the optimal power generation plan; The planning synthesis module is used to obtain the expected value of the power generation plan based on the output plan sequence, and use the expected value as the final power generation plan to be executed; The execution and feedback module is used to implement the power generation plan during the scheduling period and to provide real-time feedback and rolling correction of the reservoir's operating status based on the actual water inflow.

9. A computing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the long-term optimal scheduling method for hydropower stations that takes into account output uncertainty, as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the long-term optimal scheduling method for hydropower stations that takes into account output uncertainty, as described in any one of claims 1-7.

Images