Flood control scheduling method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a flood control scheduling method and device, electronic equipment and a storage medium, and belongs to the technical field of flood control scheduling management. The method comprises the following steps: calculating upstream and downstream submerging loss, wherein the upstream and downstream submerging loss comprises upstream submerging loss and downstream submerging loss; determining an optimal Copula function according to the upstream and downstream flooding loss, and determining a joint probability density function of the upstream and downstream flooding loss according to the optimal Copula function; an objective function is constructed according to the upstream and downstream submerging loss and the joint probability density function, constraint conditions are defined, a scheduling model is constructed according to the objective function and the constraint conditions, and the constraint conditions comprise at least one of a water balance constraint, a reservoir capacity upper and lower limit constraint, a flow upper and lower limit constraint and a non-negative constraint; and optimizing the scheduling model through a random dynamic programming method to obtain a target decision. According to the embodiment of the invention, the upstream and downstream flooding risk of the reservoir can be quantified, and the scientificity, reliability and applicability of a scheduling decision are improved.

Description

Technical Field

[0001] The present application relates to the technical field of flood control scheduling management, and in particular to a flood control scheduling method and device, electronic equipment and storage medium. Background Art

[0002] In the field of flood control dispatching management, existing technologies mainly have the following problems:

[0003] (1) Traditional methods rely on expert experience and lack scientificity and reliability.

[0004] (2) Most existing scheduling methods focus only on upstream or downstream risks. For example, excessively lowering reservoir water levels may exacerbate the risk of downstream over-discharge, while prioritizing downstream water levels may exacerbate flooding in upstream reservoir areas. Existing scheduling models are not closely integrated with the actual needs of flood control scheduling and are therefore not very applicable.

[0005] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0006] The main purpose of the embodiments of the present application is to propose a flood control scheduling method and device, electronic equipment and storage medium, aiming to quantify the flooding risk upstream and downstream of the reservoir and improve the scientificity, reliability and applicability of scheduling decisions.

[0007] To achieve the above objectives, an embodiment of the present application provides a flood control scheduling method, which includes the following steps:

[0008] Calculating upstream and downstream flooding losses, wherein the upstream and downstream flooding losses include upstream flooding losses and downstream flooding losses;

[0009] Determine an optimal Copula function based on the upstream and downstream flooding losses, and determine a joint probability density function of the upstream and downstream flooding losses based on the optimal Copula function;

[0010] constructing an objective function based on the upstream and downstream flooding losses and the joint probability density function, defining constraints, and constructing a scheduling model based on the objective function and the constraints, wherein the constraints include at least one of a water balance constraint, a reservoir capacity upper and lower limit constraint, a flow upper and lower limit constraint, and a non-negative constraint;

[0011] The scheduling model is optimized by a stochastic dynamic programming method to obtain a target decision.

[0012] In some embodiments, the method further comprises:

[0013] Get the current inflow runoff;

[0014] The current inflow runoff is input into the target decision to obtain the conditional risk value of minimizing the combined upstream and downstream flooding losses.

[0015] In some embodiments, calculating upstream and downstream flooding losses includes:

[0016] Obtain historical flooded area, historical unit area loss, historical water depth loss rate curve, historical excess safety discharge flow, historical downstream discharge and historical river channel safety discharge;

[0017] Calculate upstream flooding losses based on historical flooded area, historical unit area loss, and historical water depth loss rate curves;

[0018] The downstream flooding losses are calculated based on the historical super-safe discharge flow, historical downstream discharge flow and historical river safety discharge.

[0019] In some embodiments, determining an optimal Copula function according to the upstream and downstream flooding losses, and determining a joint probability density function of the upstream and downstream flooding losses according to the optimal Copula function, includes:

[0020] Fitting probability distributions for the upstream flooding loss and the downstream flooding loss respectively to obtain marginal probability distributions of the upstream and downstream flooding losses;

[0021] Converting the marginal probability distribution of the upstream and downstream flooding losses into a uniform distribution variable of the upstream and downstream flooding losses by probability integral transformation;

[0022] Determining the optimal Copula function based on the uniformly distributed variables of the upstream and downstream flooding losses;

[0023] Determine the parameters of the optimal Copula function by maximum likelihood estimation, and determine the expression of the optimal Copula function;

[0024] The goodness of fit is verified based on the expression of the optimal Copula function, and the joint probability density function of the upstream and downstream flooding losses is obtained.

[0025] In some embodiments, determining the optimal Copula function based on the uniformly distributed variables of the upstream and downstream flooding losses includes:

[0026] Calculating a rank correlation coefficient based on the uniformly distributed variables of the upstream and downstream flooding losses;

[0027] determining tail dependence based on the rank correlation coefficient;

[0028] The optimal Copula function is selected according to the tail dependency by using an information criterion or Euclidean distance.

[0029] In some embodiments, verifying the goodness of fit based on the expression of the optimal Copula function to obtain the joint probability density function of the upstream and downstream flooding losses includes:

[0030] The KS test is used to verify the goodness of fit of the expression of the optimal Copula function;

[0031] If the KS test fails, the process returns to the step of determining the parameters in the optimal Copula function by maximum likelihood estimation and determining the expression of the optimal Copula function until the goodness of fit of the expression of the optimal Copula function passes the KS test.

[0032] In some embodiments, constructing an objective function based on the upstream and downstream flooding losses and the joint probability density function, defining constraints, and constructing a scheduling model based on the objective function and the constraints include:

[0033] Determine the confidence level and risk coordination coefficient;

[0034] determining a value-at-risk threshold based on the confidence level and the joint probability density function;

[0035] Constructing an objective function based on the upstream and downstream flooding losses, the joint probability density function, the risk value threshold and the risk coordination coefficient;

[0036] Define constraints;

[0037] A scheduling model is constructed according to the objective function and the constraint conditions.

[0038] To achieve the above objectives, another aspect of the present application provides a flood control scheduling device, comprising:

[0039] A loss calculation module, used to calculate upstream and downstream flooding losses, wherein the upstream and downstream flooding losses include upstream flooding losses and downstream flooding losses;

[0040] a function determination module, configured to determine an optimal Copula function according to the upstream and downstream flooding losses, and determine a joint probability density function of the upstream and downstream flooding losses according to the optimal Copula function;

[0041] a model construction module, configured to construct an objective function based on the upstream and downstream flooding losses and the joint probability density function, define constraints, and construct a scheduling model based on the objective function and the constraints, wherein the constraints include at least one of a water balance constraint, a reservoir capacity upper and lower limit constraint, a flow upper and lower limit constraint, and a non-negative constraint;

[0042] The model optimization module is used to optimize the scheduling model through a stochastic dynamic programming method to obtain a target decision.

[0043] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned method when executing the computer program.

[0044] To achieve the above objectives, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described above is implemented.

[0045] The embodiments of the present application include at least the following beneficial effects: the present application provides a flood control scheduling method and device, an electronic device and a storage medium, which calculates upstream and downstream flooding losses; determines the optimal Copula function based on the upstream and downstream flooding losses, and determines the joint probability density function of the upstream and downstream flooding losses based on the optimal Copula function, which is conducive to capturing tail dependencies, improving joint risk measurement, and improving the modeling accuracy and risk prediction ability of multivariate loss correlation; constructs an objective function based on the upstream and downstream flooding losses and the joint probability density function, defines constraints, and constructs a scheduling model based on the objective function and constraints, and incorporates upstream and downstream losses into the objective function at the same time, which is conducive to improving the accuracy and applicability of the model; optimizes the scheduling model through a random dynamic programming method to obtain a target decision, simultaneously optimizes upstream reservoir capacity control and downstream flood discharge control, improves the robustness of full-cycle scheduling, and improves the scientificity, reliability and applicability of scheduling decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flow chart of the flood control scheduling method provided in an embodiment of the present application;

[0047] Figure 2 yes Figure 1 Flowchart of step S102 in FIG.

[0048] Figure 3 yes Figure 1 Flowchart of step S103 in FIG.

[0049] Figure 4 This is a specific implementation flow chart of the flood control scheduling method provided in the embodiment of the present application when it is applied to a reservoir flood control optimization scheduling system;

[0050] Figure 5 Schematic diagram of the transition probability matrix (Markov process) provided in the embodiment of the present application;

[0051] Figure 6 This is a schematic diagram of the optimal flood discharge sequence provided by the embodiment of the present application;

[0052] Figure 7 Schematic diagram of the influence of weight w provided in the embodiment of the present application;

[0053] Figure 8 1 is a schematic diagram of the influence of confidence level α provided in an embodiment of the present application;

[0054] Figure 9 Schematic diagram of the structure of the flood control scheduling device provided in the embodiment of the present application;

[0055] Figure 10 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are merely examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the appended claims.

[0057] It will be understood that the terms "first", "second", etc. used in this application may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0058] The terms "at least one", "plurality", "each", "any", etc. used in this application include "at least one", "two" or more, "plurality" or "each", "any" or "any one", "each" or "any one" as used herein.

[0059] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0060] Before explaining the embodiments of the present application in detail, some of the nouns and terms involved in the embodiments of the present application are first explained. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0061] 1) Copula functions are used to describe the dependency structure between multivariate distributions. Copula functions link multiple marginal distributions (distributions of a single variable) to a common joint distribution. Copula functions model the marginal behavior of different variables (individual distributions) separately from the correlation between them, allowing for more flexible descriptions of complex multidimensional distributions.

[0062] In the field of flood control dispatching management, existing technologies mainly have the following problems:

[0063] (1) Traditional methods rely on expert experience and lack scientificity and reliability.

[0064] (2) Most existing scheduling methods focus only on upstream or downstream risks. For example, excessively lowering reservoir water levels may exacerbate the risk of downstream over-discharge, while prioritizing downstream water levels may exacerbate flooding in upstream reservoir areas. Existing scheduling models are not closely integrated with the actual needs of flood control scheduling and are therefore not very applicable.

[0065] In summary, the technical problems existing in the relevant technologies need to be improved.

[0066] In view of this, a flood control scheduling method, device, equipment and medium are provided in an embodiment of the present application. The scheme calculates the upstream and downstream flooding losses; determines the optimal Copula function based on the upstream and downstream flooding losses, and determines the joint probability density function of the upstream and downstream flooding losses based on the optimal Copula function, which is conducive to capturing tail dependencies, improving joint risk measurement, and improving the modeling accuracy and risk prediction ability of multivariate loss correlation; constructs an objective function based on the upstream and downstream flooding losses and the joint probability density function, defines constraints, and constructs a scheduling model based on the objective function and constraints, and incorporates upstream and downstream losses into the objective function at the same time, which is conducive to improving the accuracy and applicability of the model; optimizes the scheduling model through a random dynamic programming method to obtain a target decision, and simultaneously optimizes the upstream reservoir capacity control and downstream flood discharge control, thereby improving the robustness of the full-cycle scheduling and improving the scientificity, reliability and applicability of the scheduling decision.

[0067] The flood control scheduling method provided in the embodiment of the present application relates to the field of flood control scheduling management technology. The flood control scheduling method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or can be configured as a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application that implements the flood control scheduling method, etc., but is not limited to the above forms.

[0068] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0069] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0070] Figure 1 This is an optional flow chart of the flood control scheduling method provided in the embodiment of the present application. Figure 1The method may include but is not limited to steps S101 to S104.

[0071] Step S101: Calculate upstream and downstream flooding losses.

[0072] Specifically, upstream and downstream flooding losses include upstream flooding losses and downstream flooding losses.

[0073] Optionally, upstream and downstream flooding losses are calculated using historical data.

[0074] In some embodiments, historical flooded area, historical loss per unit area, historical water depth loss rate curve, historical super-safe discharge flow, historical downstream flow and historical river safety discharge are obtained; upstream flooding loss is calculated based on historical flooded area, historical loss per unit area and historical water depth loss rate curve; downstream flooding loss is calculated based on historical super-safe discharge flow, historical downstream flow and historical river safety discharge.

[0075] It should be noted that if the number of data points is less than 500, the Monte Carlo method can be used to generate several reservoir inflow floods based on historical flood characteristics, and the reservoir operation can be simulated according to the reservoir flood control operation rules.

[0076] In this embodiment, the upstream and downstream flooding losses are calculated to prepare for the subsequent training of the model based on the upstream and downstream flooding losses.

[0077] Step S102: determining an optimal Copula function based on the upstream and downstream flooding losses, and determining a joint probability density function of the upstream and downstream flooding losses based on the optimal Copula function.

[0078] Optionally, an optimal Copula function is determined based on uniformly distributed variables of upstream and downstream flooding losses, and then a joint probability density function of upstream and downstream flooding losses is calculated based on the optimal Copula function.

[0079] In some embodiments, probability distributions are fitted for upstream flooding losses and downstream flooding losses respectively to obtain marginal probability distributions of upstream and downstream flooding losses; the marginal probability distributions of upstream and downstream flooding losses are converted into uniformly distributed variables of upstream and downstream flooding losses through probability integral transformation; an optimal Copula function is determined based on the uniformly distributed variables of upstream and downstream flooding losses; parameters in the optimal Copula function are determined through maximum likelihood estimation, and an expression for the optimal Copula function is determined; the goodness of fit is verified based on the expression of the optimal Copula function to obtain a joint probability density function of upstream and downstream flooding losses.

[0080] In this embodiment, the optimal Copula function is determined based on the upstream and downstream flooding losses, and the joint probability density function of the upstream and downstream flooding losses is determined based on the optimal Copula function, which is conducive to capturing tail dependencies, improving joint risk measurement, and enhancing the modeling accuracy and risk prediction capabilities of multivariate loss correlation.

[0081] Step S103 : constructing an objective function based on the upstream and downstream flooding losses and the joint probability density function, defining constraints, and constructing a scheduling model based on the objective function and the constraints.

[0082] Specifically, the constraint conditions include at least one of a water balance constraint, a reservoir capacity upper and lower limit constraint, a flow rate upper and lower limit constraint, and a non-negative constraint.

[0083] Optionally, an objective function is constructed, constraints are defined, and a scheduling model is constructed based on the objective function and the constraints.

[0084] In some embodiments, a confidence level and a risk coordination coefficient are determined; a risk value threshold is determined based on the confidence level and the joint probability density function; an objective function is constructed based on upstream and downstream flooding losses, the joint probability density function, the risk value threshold and the risk coordination coefficient; constraints are defined; and a scheduling model is constructed based on the objective function and the constraints.

[0085] In this embodiment, an objective function is constructed based on the upstream and downstream flooding losses and the joint probability density function, constraints are defined, and a scheduling model is constructed based on the objective function and the constraints. The upstream and downstream losses are simultaneously incorporated into the objective function, which is conducive to improving the accuracy and applicability of the model.

[0086] Step S104: Optimize the scheduling model through a random dynamic programming method to obtain a target decision.

[0087] Optionally, the scheduling model is optimized by a dynamic programming method, and the target decision is obtained through the scheduling model.

[0088] In some embodiments, under the condition of uncertain inflow, the scheduling model is optimized by the stochastic dynamic programming (SDP) method to obtain the optimal flood discharge decision, thereby obtaining the conditional risk value that minimizes the combined upstream and downstream flooding losses.

[0089] Furthermore, the current inflow runoff is obtained; the current inflow runoff is input into the target decision to obtain the conditional risk value that minimizes the combined upstream and downstream flooding losses.

[0090] In this embodiment, the scheduling model is optimized by a stochastic dynamic programming method to obtain the target decision. Through joint distribution modeling, the upstream reservoir capacity control and the downstream flood discharge control are simultaneously optimized to improve the robustness of the full-cycle scheduling and enhance the scientificity, reliability and applicability of the scheduling decision.

[0091] Steps S101 to S104 shown in the embodiment of the present application calculate the upstream and downstream flooding losses; determine the optimal Copula function based on the upstream and downstream flooding losses, and determine the joint probability density function of the upstream and downstream flooding losses based on the optimal Copula function, which is conducive to capturing tail dependencies, improving joint risk measurement, and improving the modeling accuracy and risk prediction ability of multivariate loss correlation; construct an objective function based on the upstream and downstream flooding losses and the joint probability density function, define constraints, and construct a scheduling model based on the objective function and constraints, incorporating upstream and downstream losses into the objective function at the same time, which is conducive to improving the accuracy and applicability of the model; optimize the scheduling model through a stochastic dynamic programming method to obtain a target decision, simultaneously optimize upstream reservoir capacity control and downstream flood discharge control, improve the robustness of full-cycle scheduling, and improve the scientificity, reliability and applicability of scheduling decisions.

[0092] See also Figure 2 In some embodiments, step S102 may include but is not limited to steps S201 to S205:

[0093] Step S201 : fitting probability distributions for upstream flooding losses and downstream flooding losses respectively to obtain marginal probability distributions of upstream and downstream flooding losses.

[0094] In some embodiments, probability distributions (such as Gamma distribution and Weibull distribution) are fitted to the upstream and downstream flooding loss data respectively, and the rationality is verified using the KS test.

[0095] It is understandable that if the KS test fails to verify the rationality, the probability distribution is refitted.

[0096] Step S202 : converting the marginal probability distribution of upstream and downstream flooding losses into a uniform distribution variable of upstream and downstream flooding losses through probability integral transformation.

[0097] In some embodiments, the cumulative distribution function value of each variable is calculated through probability integral transformation, and the expression for converting the original data into a variable that strictly obeys the [0,1] uniform distribution is as follows:

[0098]

[0099] Among them, u i With v i A uniformly distributed variable representing upstream and downstream flooding losses, and Indicates upstream and downstream flooding losses.

[0100] Step S203: determining an optimal Copula function based on the uniformly distributed variables of upstream and downstream flooding losses.

[0101] In some embodiments, a rank correlation coefficient is calculated based on uniformly distributed variables of upstream and downstream flooding losses. Tail dependence is determined based on the rank correlation coefficient. An optimal copula function is selected based on the tail dependence using an information criterion or Euclidean distance.

[0102] Specifically, the Kendall rank correlation coefficient or Spearman rank correlation coefficient is calculated to determine tail dependence. Based on the tail dependence, the optimal copula function is selected using the AIC / BIC criterion or Euclidean distance.

[0103] Step S204: Determine the parameters of the optimal Copula function by maximum likelihood estimation, and determine the expression of the optimal Copula function.

[0104] In step S204 of some embodiments, the parameters in the Copula function are determined by maximum likelihood estimation to determine the expression of the optimal Copula function.

[0105] Step S205 : Verify the goodness of fit based on the expression of the optimal Copula function to obtain the joint probability density function of upstream and downstream flooding losses.

[0106] Optionally, the goodness of fit is verified (KS test) to obtain the joint probability density function of flooding losses upstream and downstream of the reservoir.

[0107] In step S205 of some embodiments, the KS test is used to verify the goodness of fit of the expression of the optimal Copula function; if the KS test fails, the process returns to the step of determining the parameters in the optimal Copula function by maximum likelihood estimation and determining the expression of the optimal Copula function until the goodness of fit of the expression of the optimal Copula function passes the KS test.

[0108] See also Figure 3 In some embodiments, step S103 may include but is not limited to steps S301 to S305:

[0109] Step S301: Determine the confidence level and risk coordination coefficient.

[0110] In step S301 of some embodiments, the present application does not specifically limit the method for determining the confidence level and the risk coordination coefficient, and can be flexibly selected in combination with actual scheduling needs. For example, the confidence level and the risk coordination coefficient can be determined manually or automatically by the system.

[0111] Step S302: Determine a value-at-risk threshold based on the confidence level and the joint probability density function.

[0112] In step S302 of some embodiments, a value-at-risk threshold of the joint probability density function under the confidence level 1-α is obtained.

[0113] Step S303: construct an objective function based on upstream and downstream flooding losses, a joint probability density function, a risk value threshold, and a risk coordination coefficient.

[0114] In step S303 of some embodiments, the upstream and downstream conditional value at risk (CVaR) is minimized, and the expected value of excess loss at a confidence level α is used as the core indicator to quantify the systemic risk of upstream and downstream flooding.

[0115] Specifically, the objective function is expressed as follows:

[0116] minCVaR α =E[L total ||L total >VaRα]

[0117] L total =wL up +(1-w)L down

[0118] VaRα=F L -1 (α)

[0119] Where minCVaRα represents the objective function (i.e., minimizing the upstream and downstream conditional value at risk), Lup and Ldown are the upstream and downstream flooding losses, VaRα is the value at risk threshold under the confidence level 1-α, FL-1(α) is the α quantile of the joint loss distribution Ltotal (α is usually taken as 0.95 or 0.99), and w is the risk coordination coefficient, 0≤w≤1.

[0120] Step S304: define constraints.

[0121] In step S304 of some embodiments, at least one of a water balance constraint, a storage capacity upper and lower limit constraint, a flow upper and lower limit constraint, and a non-negative constraint is defined.

[0122] Step S305: construct a scheduling model based on the objective function and the constraints.

[0123] In step S305 of some embodiments, the scheduling problem is converted into a scheduling model based on the objective function and the constraints.

[0124] Taking the reservoir flood control optimization dispatching system as an example, Figure 4 This is a specific implementation flow chart of the flood control scheduling method provided in the embodiment of the present application when it is applied to a reservoir flood control optimization scheduling system. Figure 4 The method may include, but is not limited to, the following steps:

[0125] Step 1: Calculate upstream and downstream flooding losses.

[0126] (1) Upstream flooding:

[0127]

[0128] Among them, A i Indicates the flooded area extracted by GIS, unit: km 2 , C i Indicates the loss per unit area (farmland / town), unit: yuan, f i (h) represents the water depth-loss rate curve.

[0129] (2) Downstream flooding

[0130]

[0131] Among them, Q excess (t) = Q(t) - Q safe represents the super-safe discharge flow; Q(t) is the flow of the reservoir outflow evolving to the downstream; Q safe is the safe discharge of the river, and V(Q) represents the flow-loss function (including population / facility sensitivity).

[0132] Exemplarily, the reservoir parameters are as follows:

[0133] Initial storage capacity: V0 = 500 million cubic meters

[0134] Storage capacity limit: Vmin = 200 Vmax = 600

[0135] Flood discharge capacity: St∈{200,250,300}m 3 / s

[0136] Scheduling period: 3 periods (Δt = 6 hours)

[0137] For example, the loss function is as follows:

[0138] Upstream loss: Lup(V)=0.5(600-V)2(100 million yuan)

[0139] Downstream loss: Ldown(S)=1.2max(S-250,0) (100 million yuan)

[0140] Total loss weight: w = 0.5, Ltotal = 0.5Lup + 0.5Ldown

[0141] Step 2: Copula joint distribution construction.

[0142] (1) Obtain or use the upstream and downstream flooding loss expression to calculate the flooding loss data L of the reservoir upstream and downstream in the past years after the reservoir was built. up , L down .

[0143] It should be noted that if the number of data points is less than 500, the Monte Carlo method can be used to generate several reservoir inflows based on historical flood characteristics. According to the reservoir flood control scheduling rules, the reservoir scheduling operation can be simulated, and the upstream and downstream flooding loss expressions can be used to deduce the upstream and downstream flooding loss values.

[0144] (2) Marginal distribution fitting and testing: For upstream and downstream flooding loss data L up , L down Fit probability distributions (such as Gamma and Weibull distributions) respectively, and use KS test to verify rationality.

[0145] (3) Through the probability integral transformation, the cumulative distribution function value of each variable is calculated, and the original data is converted into a variable that strictly obeys the uniform distribution of [0,1].

[0146]

[0147] (4) Copula function selection: calculate the Kendall rank correlation coefficient or Spearman rank correlation coefficient to determine tail dependence. Based on the tail dependence, the optimal copula function is selected using the AIC / BIC criterion or Euclidean distance.

[0148] (5) Parameter estimation: Determine the parameters in the Copula function through maximum likelihood estimation, determine the expression of the optimal Copula function, and verify the goodness of fit (KS test) to obtain the joint probability density function of flooding losses upstream and downstream of the reservoir.

[0149] Step 3: Scheduling model construction.

[0150] (1) Objective function: Minimize the upstream and downstream conditional value at risk (CVaR). The expected value of excess loss at the confidence level α is used as the core indicator to quantify the systemic risk of upstream and downstream flooding:

[0151] minCVaR α =E[L total |L total >VaRα]

[0152] L total =wL up +(1-w)L down

[0153] VaRα=F L -1 (α)

[0154] Among them, L up , L down are upstream and downstream flooding losses; VaR α F is the risk value threshold under the confidence level 1-α condition. L -1 (α) is the α quantile of the joint loss distribution Ltotal (α is usually taken as 0.95 or 0.99), w is the risk coordination coefficient, 0≤w≤1.

[0155] Exemplarily, the CVaR parameters are as follows:

[0156] Confidence level: α = 0.95;

[0157] Objective function: minCVaR α =E[L total ∣L total >VaR α ].

[0158] (2) Constraints

[0159] 1) Water balance constraints:

[0160] V i,t+1 =V i,t +(I i,t -q i,t )Δt

[0161] Where: V i,t 、V i,t+1 represents the water storage capacity of reservoir i at the end of time period t and t+1; I i,t is the average inflow to reservoir i during period t, q i,t is the average outflow of reservoir i during period t.

[0162] 2) Storage capacity upper and lower limit constraints:

[0163]

[0164] Where: V i,t is the water level of reservoir i at time t; V i,t UL 、V i,t LL are the upper and lower limits of the water level of reservoir i.

[0165] 3) Traffic upper and lower limit constraints:

[0166]

[0167] Where: q i,t UL ,q i,tLL are the upper and lower limits of the power generation flow of reservoir hydropower station i.

[0168] 4) Non-negativity constraints.

[0169] All the above variables are not less than 0.

[0170] Step 4: Optimization and solution of the model.

[0171] Under the condition of uncertain inflow, the scheduling model is optimized by stochastic dynamic programming (SDP) method to obtain the optimal flood discharge decision, thereby obtaining the conditional risk value that minimizes the combined upstream and downstream flooding losses.

[0172] For example, the uncertainty of inflow runoff is as follows:

[0173] Runoff state: Qt∈{200,300,400}m 3 / s

[0174] The schematic diagram of the transition probability matrix (Markov process) is as follows Figure 5 shown.

[0175] In some embodiments, the calculation steps are as follows:

[0176] 1. State space discretization

[0177] Storage capacity: 5 discrete points (200, 300, 400, 500, 600)

[0178] Inbound flow: 3 discrete states (200, 300, 400)

[0179] Flood discharge volume: 3 discrete decisions (200, 250, 300)

[0180] 2. Calculation of the terminal period (t=3)

[0181] For each (V3, Q3) combination, calculate the total loss Ltotal of all feasible S3 and record its distribution:

[0182]

[0183]

[0184] Select S3 corresponding to the minimum CVaR: If α = 0.95, take the mean above the 95% quantile of the loss distribution.

[0185] 3. Reverse recursion (t=2)

[0186] Step 1: Traverse all (V2, Q2) combinations

[0187] Step 2: For each feasible S2, calculate V3 and future CVaR:

[0188]

[0189] Step 3: Select S2 that minimizes the total CvaR and update the CVaR table for t=2

[0190] 4. Positive decision (t=1)

[0191] Initial state: V0 = 500, Q1 = 200

[0192] Select the optimal S1 based on the CVaR table at t=1 and recursively make decisions for subsequent periods

[0193] Furthermore, the optimal flood discharge sequence diagram is shown in the following figure: Figure 6 The total CVaR (0.95) = 4.2 + 7.5 + 3.8 = 1.55 billion yuan, compared to the uniform flood discharge strategy (250, 250, 250): total CVaR = 1.86 billion yuan, an improvement of 16.7%.

[0194] Optionally, a sensitivity analysis is performed on the scheduling decision. The weight w influences the diagram as shown in the following figure: Figure 7 As shown, the confidence level α affects the schematic diagram as shown Figure 8 shown.

[0195] In this embodiment, the CVaR-Copula-SDP triple technology coupling achieves a paradigm shift from "passive defense" to "active optimization" for flood risk. This embodiment has the following advantages:

[0196] 1. Core Advantages

[0197] 1. Accurately characterize tail risks

[0198] Through the conditional value at risk (CVaR) objective function, the model can directly optimize the expected value of losses under extreme flood scenarios. Compared with the traditional mean-variance model or deterministic optimization, it is more suitable for the prevention needs of "low probability-large loss" events in flood control scheduling.

[0199] 2. Multivariate Joint Risk Modeling

[0200] The Copula function is used to describe the joint distribution of upstream storage capacity and downstream flood discharge losses, effectively capturing the nonlinear correlation between the two (such as the risk of synchronous surge in upstream and downstream losses under extreme floods).

[0201] 2. Beneficial Effects

[0202] 1. Multi-objective collaborative management capabilities

[0203] Spatial dimension: Through joint distribution modeling, upstream reservoir capacity control and downstream flood discharge control are simultaneously optimized.

[0204] Time dimension: Under the dynamic programming framework, flood discharge decisions made in the previous period can reserve reservoir capacity to buffer the impact of subsequent flood peaks, thereby improving the robustness of full-cycle scheduling.

[0205] 2. Improved transparency in decision-making

[0206] Risk visualization: Joint probability density surface based on Copula ( Figure 1 ) can intuitively display the loss distribution characteristics under different scheduling strategies and support collaborative decision-making among multiple departments.

[0207] Sensitivity quantification: The model can output the impact gradient of confidence level α, Copula parameter θ, etc. on the total CVaR, providing a quantitative basis for risk preference adjustment.

[0208] See also Figure 9 The embodiment of the present application further provides a flood control scheduling device, which can implement the above-mentioned flood control scheduling method, and the device includes:

[0209] The loss calculation module 901 is used to calculate upstream and downstream flooding losses, which include upstream flooding losses and downstream flooding losses;

[0210] A function determination module 902 is configured to determine an optimal Copula function based on upstream and downstream flooding losses, and determine a joint probability density function of upstream and downstream flooding losses based on the optimal Copula function;

[0211] A model construction module 903 is configured to construct an objective function based on upstream and downstream flooding losses and a joint probability density function, define constraints, and construct a scheduling model based on the objective function and the constraints. The constraints include at least one of a water balance constraint, a reservoir capacity upper and lower limit constraint, a flow upper and lower limit constraint, and a non-negative constraint.

[0212] The model optimization module 904 is used to optimize the scheduling model through a stochastic dynamic programming method to obtain a target decision.

[0213] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0214] The present application also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the flood control scheduling method when executing the computer program. The electronic device can be any smart terminal, such as a tablet computer or an in-vehicle computer.

[0215] It can be understood that the contents of the above method embodiments are applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0216] See also Figure 10 , Figure 10 The hardware structure of an electronic device according to another embodiment is shown. The electronic device includes:

[0217] The processor 1001 can be implemented as a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0218] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1002 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1002 and is called by the processor 1001 to execute the flood control scheduling method of the embodiments of this application.

[0219] Input / output interface 1003, used to implement information input and output;

[0220] Communication interface 1004, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0221] Bus 1005 , which transmits information between various components of the device (e.g., processor 1001 , memory 1002 , input / output interface 1003 , and communication interface 1004 );

[0222] The processor 1001 , the memory 1002 , the input / output interface 1003 and the communication interface 1004 are connected to each other in communication within the device via the bus 1005 .

[0223] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned flood control scheduling method is implemented.

[0224] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiment, the functions specifically implemented by the present storage medium embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0225] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0226] The flood control scheduling method, flood control scheduling device, electronic device and storage medium provided in the embodiments of the present application calculate upstream and downstream flooding losses; determine the optimal Copula function based on the upstream and downstream flooding losses, and determine the joint probability density function of the upstream and downstream flooding losses based on the optimal Copula function, which is conducive to capturing tail dependencies, improving joint risk measurement, and improving the modeling accuracy and risk prediction ability of multivariate loss correlation; construct an objective function based on the upstream and downstream flooding losses and the joint probability density function, define constraints, and construct a scheduling model based on the objective function and constraints, and incorporate upstream and downstream losses into the objective function at the same time, which is conducive to improving the accuracy and applicability of the model; optimize the scheduling model through a random dynamic programming method to obtain a target decision, simultaneously optimize upstream reservoir capacity control and downstream flood discharge control, improve the robustness of full-cycle scheduling, and improve the scientificity, reliability and applicability of scheduling decisions.

[0227] The embodiments described in the embodiments of this application are intended to more clearly illustrate the technical solutions of the embodiments of this application and do not constitute a limitation on the technical solutions provided by the embodiments of this application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0228] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0229] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0230] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0231] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0232] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0233] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0234] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0235] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0236] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0237] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but are not intended to limit the scope of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and essence of the present invention should be within the scope of the present invention.

Claims

1. A flood control scheduling method, characterized in that: The method comprises the following steps: Calculating upstream and downstream flooding losses, wherein the upstream and downstream flooding losses include upstream flooding losses and downstream flooding losses; Determine an optimal Copula function based on the upstream and downstream flooding losses, and determine a joint probability density function of the upstream and downstream flooding losses based on the optimal Copula function; constructing an objective function based on the upstream and downstream flooding losses and the joint probability density function, defining constraints, and constructing a scheduling model based on the objective function and the constraints, wherein the constraints include at least one of a water balance constraint, a reservoir capacity upper and lower limit constraint, a flow upper and lower limit constraint, and a non-negative constraint; The scheduling model is optimized by a stochastic dynamic programming method to obtain a target decision.

2. The method according to claim 1, characterized in that The method further comprises: Get the current inflow runoff; The current inflow runoff is input into the target decision to obtain the conditional risk value of minimizing the combined upstream and downstream flooding losses.

3. The method according to claim 1, characterized in that The calculation of upstream and downstream flooding losses includes: Obtain historical flooded area, historical unit area loss, historical water depth loss rate curve, historical excess safety discharge flow, historical downstream discharge and historical river channel safety discharge; Calculate upstream flooding losses based on historical flooded area, historical unit area loss, and historical water depth loss rate curves; The downstream flooding losses are calculated based on the historical super-safe discharge flow, historical downstream discharge flow and historical river safety discharge.

4. The method according to claim 1, wherein Determining the optimal Copula function according to the upstream and downstream flooding losses, and determining the joint probability density function of the upstream and downstream flooding losses according to the optimal Copula function, includes: Fitting probability distributions for the upstream flooding loss and the downstream flooding loss respectively to obtain marginal probability distributions of the upstream and downstream flooding losses; Converting the marginal probability distribution of the upstream and downstream flooding losses into a uniform distribution variable of the upstream and downstream flooding losses by probability integral transformation; Determining the optimal Copula function based on the uniformly distributed variables of the upstream and downstream flooding losses; Determine the parameters of the optimal Copula function by maximum likelihood estimation, and determine the expression of the optimal Copula function; The goodness of fit is verified based on the expression of the optimal Copula function, and the joint probability density function of the upstream and downstream flooding losses is obtained.

5. The method according to claim 4, characterized in that The determining of the optimal Copula function based on the uniformly distributed variables of the upstream and downstream flooding losses includes: Calculating a rank correlation coefficient based on the uniformly distributed variables of the upstream and downstream flooding losses; determining tail dependence based on the rank correlation coefficient; The optimal Copula function is selected according to the tail dependency by using an information criterion or Euclidean distance.

6. The method according to claim 4, characterized in that The expression based on the optimal Copula function verifies the goodness of fit and obtains the joint probability density function of the upstream and downstream flooding losses, including: The KS test is used to verify the goodness of fit of the expression of the optimal Copula function; If the KS test fails, the process returns to the step of determining the parameters in the optimal Copula function by maximum likelihood estimation and determining the expression of the optimal Copula function until the goodness of fit of the expression of the optimal Copula function passes the KS test.

7. The method according to claim 1, characterized in that The step of constructing an objective function based on the upstream and downstream flooding losses and the joint probability density function, defining constraints, and constructing a scheduling model based on the objective function and the constraints includes: Determine the confidence level and risk coordination coefficient; determining a value-at-risk threshold based on the confidence level and the joint probability density function; Constructing an objective function based on the upstream and downstream flooding losses, the joint probability density function, the risk value threshold and the risk coordination coefficient; Define constraints; A scheduling model is constructed according to the objective function and the constraint conditions.

8. A flood control dispatching device, characterized in that: The device comprises: A loss calculation module, used to calculate upstream and downstream flooding losses, wherein the upstream and downstream flooding losses include upstream flooding losses and downstream flooding losses; a function determination module, configured to determine an optimal Copula function according to the upstream and downstream flooding losses, and determine a joint probability density function of the upstream and downstream flooding losses according to the optimal Copula function; a model construction module, configured to construct an objective function based on the upstream and downstream flooding losses and the joint probability density function, define constraints, and construct a scheduling model based on the objective function and the constraints, wherein the constraints include at least one of a water balance constraint, a reservoir capacity upper and lower limit constraint, a flow upper and lower limit constraint, and a non-negative constraint; The model optimization module is used to optimize the scheduling model through a stochastic dynamic programming method to obtain a target decision.

9. An electronic device, characterized in that: The electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images