Drainage system real-time optimization control method, device, equipment and medium

Abstract

The embodiments of the present application provide a method, device, equipment and medium for real-time optimization control of a drainage system, and relate to the technical field of drainage systems. The method includes: obtaining historical data of the drainage system, the historical data including: historical status data of the drainage system, historical rainfall data of the area where the drainage system is located, and historical control data of multiple control devices in the drainage system; based on the historical control data, historical status data, historical rainfall data and multiple future random scenarios, determining the overflow volume of the drainage system in multiple scenarios; based on the overflow volume of multiple scenarios and the corresponding probability of occurrence of each scenario, determining the candidate control strategies of multiple control facilities of the drainage system; optimizing the candidate control strategies to obtain the optimized target control strategy. The method improves the robustness of the real-time control strategy, effectively alleviates the phenomenon of urban waterlogging and a sharp increase in the overflow volume of the outlet when the drainage facilities suddenly fail, and achieves better comprehensive benefits.

Description

Technical Field

[0001] The present application relates to the technical field of drainage systems, and in particular to a method, device, equipment and medium for real-time optimization control of drainage systems. Background Art

[0002] Under the background of climate change and urbanization, extreme weather events occur frequently, and the impact of overflow in urban drainage systems has increased significantly. Real-time control can enhance the resilience of urban drainage systems and help cities better cope with the challenges of environmental changes.

[0003] At present, real-time control of drainage systems often develops an operation plan library for drainage facilities under different scenarios based on historical meteorological, hydrological and operation data, and then determines the control strategy of the drainage facilities in combination with real-time monitoring information; when a certain amount of operation data is accumulated or after a certain period of time, the operation plan library is optimized and adjusted.

[0004] However, due to various influencing factors such as high-intensity use of drainage systems and large-scale wastewater discharge, urban drainage systems face the problem of frequent failures of control facilities. This problem will lead to differences between drainage system behavior and model predictions, affecting the effectiveness of real-time control strategies. Therefore, it is urgent to study real-time control strategies and related equipment for emergency scenarios of urban drainage systems. Summary of the invention

[0005] The embodiments of the present application provide a drainage system real-time optimization control method, device, equipment and medium, which are used to improve the robustness of the real-time control strategy, effectively alleviate the phenomenon of urban waterlogging and sudden increase in outlet overflow when drainage facilities suddenly fail, and achieve better comprehensive benefits.

[0006] In a first aspect, an embodiment of the present application provides a real-time optimization control method for a drainage system, comprising:

[0007] Acquire historical data of the drainage system, the historical data including: historical status data of the drainage system, historical rainfall data of the area where the drainage system is located, and historical control data of multiple control devices in the drainage system, the historical status data and historical control data are used to indicate the risk of facility failure of the drainage system;

[0008] Determine the overflow volume of the drainage system under multiple scenarios based on the historical control data, the historical status data, the historical rainfall data and multiple random scenarios, wherein each scenario is generated by at least one random scenario;

[0009] Determining candidate control strategies for a plurality of control facilities of the drainage system based on the overflow volumes of the plurality of scenarios and the corresponding probability of occurrence of each scenario;

[0010] The candidate control strategy is optimized to obtain an optimized target control strategy.

[0011] In a possible implementation, the method further includes: determining the occurrence probabilities of the multiple random scenarios;

[0012] For any one of the multiple scenarios, determining at least one target scenario for generating the scenario, wherein each scenario is independent of each other;

[0013] When the number of the target scenarios is one, the occurrence probability of the target scenario is used as the occurrence probability of the scenario;

[0014] When there are multiple target scenarios, the sum of the occurrence probabilities of the multiple target scenarios is used as the occurrence probability of the scenario.

[0015] In a possible implementation manner, the above-mentioned obtaining of historical status data of the drainage system includes:

[0016] A physical process model is constructed based on the spatial distribution of the underlying surface of the drainage system and the properties of the drainage network; and model parameters of the physical process model are optimized based on the historical rainfall data and hydrological data.

[0017] Based on the real-time rainfall observation data of the area where the drainage system is located, the physical process model at the beginning of the optimization period is initialized to obtain the historical state data of the drainage system.

[0018] In a possible implementation, the above-mentioned method of determining the overflow volume of the drainage system in multiple scenarios based on the historical control data, the historical status data, the historical rainfall data and multiple random scenarios includes:

[0019] Constructing a drainage process simulation proxy model, wherein the drainage process simulation proxy model is used to replace the physical process model to simulate the overflow control effect;

[0020] The historical control data, historical status data, historical rainfall data and multiple random scenarios are input into the drainage process simulation agent model to obtain the overflow volume of the drainage system under various scenarios.

[0021] In a possible implementation, before determining the candidate control strategies for the multiple control devices in the drainage system based on the overflow volumes of the multiple scenarios and the corresponding probability of occurrence of each scenario, the method further includes: constructing an objective function under a random scenario, wherein the objective function is used to determine the average overflow volume under the multiple scenarios.

[0022] In a possible implementation manner, the candidate control strategies for the multiple control devices in the drainage system are determined based on the overflow volumes of the multiple scenarios and the corresponding probability of occurrence of each scenario, including:

[0023] Determine the average overflow volume under the multiple scenarios according to the overflow volume of the multiple scenarios, the occurrence probability corresponding to each scenario and the objective function;

[0024] Based on the average overflow rates under the multiple scenarios, candidate control strategies for multiple control facilities in the drainage system are determined.

[0025] In a possible implementation manner, the above-mentioned optimization process of the candidate control strategy to obtain the optimized target control strategy includes:

[0026] Based on a multi-objective decision-making method, the candidate control strategies are optimized, and the control strategy with the best overflow control effect is used as the target control strategy for the multiple control facilities.

[0027] In a second aspect, an embodiment of the present application provides a drainage system real-time optimization control device, comprising:

[0028] an acquisition module, used to acquire historical data of the drainage system, the historical data including: historical status data of the drainage system, historical rainfall data of the area where the drainage system is located, and historical control data of multiple control devices in the drainage system, the historical status data and historical control data are used to indicate the risk of facility failure of the drainage system;

[0029] A processing module, configured to determine the overflow volume of the drainage system under multiple scenarios based on the historical control data, the historical status data, the historical rainfall data and multiple random scenarios, wherein each scenario is generated by at least one random scenario;

[0030] The processing module is further used to determine candidate control strategies for multiple control devices in the drainage system based on the overflow volumes of the multiple scenarios and the corresponding probability of occurrence of each scenario;

[0031] The optimization module is used to optimize the candidate control strategy to obtain an optimized target control strategy.

[0032] In a possible implementation, the processing module is also used to determine the occurrence probabilities of the multiple random scenarios; for any one of the multiple scenarios, determine at least one target scenario for generating the scenario, and each scenario is independent of each other; when the number of the target scenarios is one, use the occurrence probability of the target scenario as the occurrence probability of the scenario; when the number of the target scenarios is multiple, use the sum of the occurrence probabilities of the multiple target scenarios as the occurrence probability of the scenario.

[0033] In a possible implementation, the acquisition module is further used to construct a drainage physical process model of the area where the drainage system is located based on the spatial distribution of the underlying surface of the drainage system and the drainage network attribute data, and optimize the model parameters of the physical process model based on the historical rainfall data and hydrological data;

[0034] Based on the real-time rainfall observation data of the area where the drainage system is located, the physical process model at the beginning of the optimization period is initialized to obtain the historical state data of the drainage system.

[0035] In a possible implementation, the processing module is also used to construct a drainage process simulation agent model, which is used to simulate the overflow control effect of the physical process model; the historical control data, historical status data, historical rainfall data and multiple random scenarios are input into the drainage process simulation agent model to obtain the overflow volume of the drainage system under various scenarios.

[0036] In a possible implementation, the processing module is further used to construct an objective function under a random scenario, and the objective function is used to determine an average overflow volume under the multiple scenarios.

[0037] In a possible implementation manner, the device further includes a determining device;

[0038] The determination device is used to determine the average overflow volume under the multiple scenarios according to the overflow volume of the multiple scenarios, the occurrence probability corresponding to each scenario and the objective function;

[0039] Based on the average overflow rates under the multiple scenarios, candidate control strategies for multiple control facilities in the drainage system are determined.

[0040] In a possible implementation, the optimization module is also used to optimize the candidate control strategies based on a multi-objective decision-making method, and use the control strategy with the best overflow control effect as the target control strategy for the multiple control facilities.

[0041] In a third aspect, an embodiment of the present application provides a drainage system real-time optimization control device, including: a memory, a processor;

[0042] Memory stores computer-executable instructions;

[0043] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and various possible implementations of the first aspect.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the above first aspect and various possible implementation methods of the first aspect.

[0045] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and various possible implementation methods of the first aspect.

[0046] The real-time optimization control method, device, equipment and medium of the drainage system provided in the embodiments of the present application realize real-time optimization of the control strategies of multiple control facilities by comprehensively considering the impact of rainfall forecast uncertainty, control device uncertainty and drainage pipe uncertainty on the drainage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0048] Figure 1 A flow chart of a real-time optimization control method for a drainage system provided in an embodiment of the present application Figure 1 ;

[0049] Figure 2 A histogram of drainage system overflow under an uncertain scenario provided in an embodiment of the present application;

[0050] Figure 3 A flow chart of a real-time optimization control method for a drainage system provided in an embodiment of the present application Figure 2 ;

[0051] Figure 4 A schematic diagram comparing deterministic optimization control based on a physical process model and an agent model in a single rainstorm provided in an embodiment of the present application;

[0052] Figure 5 A schematic diagram showing a comparison between a real-time optimization control method for a drainage system provided by the present invention and a traditional control method and a static control scenario;

[0053] Figure 6 A schematic diagram of the structure of a real-time optimization control device for a drainage system provided in an embodiment of the present application;

[0054] Figure 7 A schematic diagram of the structure of a real-time optimization control device for a drainage system provided in an embodiment of the present application.

[0055] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] "Multiple" means two or more, and other quantifiers are similar. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0058] In the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0059] With the frequent occurrence of extreme weather events caused by climate change, real-time control can enhance the resilience of urban drainage systems, help cities better cope with various climate challenges and reduce climate risks. However, due to various influencing factors such as high-intensity use of drainage systems and large-scale discharge of wastewater, urban drainage systems are facing the problem of frequent failure of control facilities.

[0060] At present, the real-time control of the drainage system is often based on real-time meteorological information, and corresponding rainwater storage facility operation plans are formulated under different meteorological warning levels or different real-time meteorological conditions; the content of the operation plan is then adjusted in combination with historical operation data.

[0061] However, the real-time control of the control strategy of the control facilities based on the single element of real-time meteorological information does not take into account the impact of frequent failures of the drainage system control facilities, and it is difficult to achieve the control strategy of the control facilities obtained by optimizing based on the system status prediction under normal operating conditions.

[0062] In response to the above problems, the present application provides a real-time optimization control method for a drainage system. This method comprehensively considers the uncertainty of precipitation forecasts, the uncertainty of the control device status and the uncertainty of the drainage pipe status, and performs real-time control of the control strategy of the control facility, thereby effectively improving the robustness of the real-time control strategy and achieving better overall benefits.

[0063] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0064] Figure 1 A flow chart of a real-time optimization control method for a drainage system provided in an embodiment of the present application Figure 1 .like Figure 1 As shown, the method includes:

[0065] S101. Acquire historical data of a drainage system, wherein the historical data includes: historical status data of the drainage system, historical rainfall data of an area where the drainage system is located, and historical control data of a plurality of control devices in the drainage system.

[0066] Among them, historical status data and historical control data are used to indicate the risk of facility failure of the drainage system.

[0067] Among them, historical data refers to parameters in a certain period of time in the past before the start time of the period to be optimized, and the certain period of time in the past can be, for example, 2 hours, 3 hours, etc.; historical status is used to indicate whether the drainage pipe has a fault, and the drainage pipe fault can be caused by factors such as pipe damage and silt blockage, resulting in a decrease in the drainage capacity of the drainage pipe; historical status data refers to the drainage capacity of the drainage pipe in a certain period of time in the past; historical rainfall data refers to the rainfall in the area where the drainage pipe is located in a certain period of time in the past; historical control data is used to indicate the opening of multiple control devices in the drainage pipe in a certain period of time in the past. The control device can be, for example, a valve, a gate, etc.

[0068] Obtain the drainage capacity of the drainage pipe, the rainfall in the area where the drainage system is located, and the opening degree of multiple control devices in the drainage pipe within a certain period of time in the past.

[0069] Exemplarily, historical data of the drainage system within 2 hours before time T is obtained, wherein historical status data: normal, normal; historical rainfall data: 11.6 mm, 8.6 mm; historical control data: control device A is normal, control device B is normal, control device A is normal, control device B is faulty.

[0070] S102. Determine the overflow volume of the drainage system in various scenarios based on the historical control data, historical status data, historical rainfall data and multiple random scenarios.

[0071] Among them, the random scenario is used to indicate the uncertainty of rainfall forecast, control device uncertainty and drainage pipe uncertainty of the drainage system in the period to be optimized. The scenario is an uncertainty scenario composed of any combination of random scenarios. For example, there may be errors in the rainfall forecast, normal control device and drainage pipe failure.

[0072] Based on the drainage capacity of the drainage pipe, the rainfall in the area where the drainage system is located, the opening degree of multiple control devices in the drainage pipe, the rainfall forecast error of the drainage system in the optimization period, whether the control device is faulty, and whether the drainage pipe is faulty, the overflow volume of the drainage system under various scenarios is determined.

[0073] For example, Figure 2 This is a histogram of the drainage system overflow under the uncertainty scenario provided by the embodiment of the present application. Figure 2 As shown, Figure 2 The vertical axis in (a) represents the combined sewer overflow volume; Figure 2 The horizontal axis in (b) represents the waterlogging overflow flow in the drainage system; Figure 2 (a) and Figure 2 The horizontal axis of (b) represents multiple uncertainty scenarios, where RU is the uncertainty of precipitation forecast; EF is the failure of various control devices; PF is the failure of drainage pipes; RU_EF is the uncertainty of precipitation forecast and the failure of various control devices; RU_PF is the uncertainty of precipitation forecast and the failure of drainage pipes. Figure 2 It can be seen that when there is a control device failure, the overflow of waterlogging increases significantly. Among the multi-dimensional uncertainties of precipitation forecast, control device failure, and drainage pipe failure, the control device failure has the greatest impact on the overflow of the drainage system. Therefore, when adjusting the real-time control strategy of the control facility, it is necessary not only to consider the rainfall forecast error, but also to comprehensively consider the state of the drainage pipe and the state of the control device. By comprehensively considering the uncertainty of rainfall forecast, the uncertainty of control device, and the uncertainty of drainage pipe, the real-time control strategy of the control facility is more robust.

[0074] S103: Determine candidate control strategies for the plurality of control facilities of the drainage system based on the overflow volumes of the plurality of scenarios and the corresponding probability of occurrence of each scenario.

[0075] The candidate control strategy is a sequence of alternative control strategies for multiple control devices in the drainage system during the control period.

[0076] Based on the overflow volumes corresponding to a variety of different scenarios and the probability of occurrence of each scenario, a sequence of alternative control strategies for multiple control devices in the drainage system is determined.

[0077] In a possible implementation, determining the occurrence probability corresponding to each scenario is described in detail, including:

[0078] Determine the probability of occurrence of multiple random scenarios;

[0079] Probabilistic statistical models of rainfall forecast uncertainty, control device uncertainty and drainage pipe uncertainty are constructed respectively. Based on the above probabilistic statistical models, the occurrence probabilities of multiple random scenarios are determined.

[0080] a. Construct a statistical model of rainfall forecast uncertainty.

[0081] For each precipitation forecast scenario, assume that its error compared to the actual scenario is The standard deviation of the precipitation forecast error is 0, which is a Gaussian distribution with a mean of 0. and the period to be optimized The length of the correlation, assuming the standard deviation of the error With forecast period It is a linear relationship, and the specific calculation expression is as follows:

[0082]

[0083]

[0084] Among them, CP represents the prediction accuracy, and its value range is 0~1; It represents the precipitation forecast from time t to time t+l.

[0085] b. Construct a statistical model of the control device and drainage pipe failure probability.

[0086] Drainage facility failures (specifically including control device and drainage pipe failures) are described using a probabilistic statistical model based on a uniform Poisson process. Its basic assumptions include: (1) Assuming that the urban drainage system is a repairable system, the interval between failures can be simulated using a probability distribution; (2) The time of occurrence of system failures is completely random, and the probability of failure is the same regardless of the system state and the system failure history. According to assumption (1), the failure probability of the drainage system is independent of the operating time, and the failure probability remains consistent during the life cycle, that is, it will not increase or decrease with the increase in operating years. Assumption (2) has a relatively strong premise that the drainage system is affected by component aging and environmental changes, and its failure probability may change with the change in operating years. For random events with changing probabilities, a non-uniform Poisson process based on a non-stationary assumption can be used to describe it. However, the probability simulation based on the non-stationary assumption requires a long series of observation data, and the failure probability of the drainage system does not always show non-stationarity. Therefore, the embodiment of the present application describes the failure interval of the drainage system based on a uniform Poisson process and determines the failure probability of the drainage system components in each control period.

[0087] Constructing a probabilistic statistical model of uncertainty in control devices:

[0088] The probability density of the equipment failure time interval is expressed by the gamma distribution for control device failure, and its formula is defined as follows:

[0089]

[0090] Among them, a and b are shape and scale parameters respectively; is the gamma function.

[0091] Constructing uncertainty probability statistical model of drainage pipeline:

[0092] The probability of drainage pipe failure adopts a single-parameter exponential distribution, and the expression is as follows:

[0093]

[0094] Where λ is the rate parameter, which represents the average number of fault events per unit time.

[0095] It is understandable that when the control device fails, the control device becomes uncontrollable and the valve opening always maintains the current state. Drainage pipe failure refers to the reduction of drainage capacity of the drainage pipe caused by factors such as pipe damage, collapse, and siltation. Pipeline failure is simulated by changing the Manning coefficient of the hydraulic calculation of the drainage pipe. The Manning coefficient of the faulty pipe is set to four times the initial value.

[0096] For any one of the multiple scenarios, at least one target scenario for generating the scenario is determined; when the number of target scenarios is one, the occurrence probability of the target scenario is used as the occurrence probability of the scenario; when the number of target scenarios is multiple, the product of the occurrence probabilities of multiple target scenarios is used as the occurrence probability of the scenario.

[0097] For example, if the probability of occurrence of random scenario 1 is a, the probability of occurrence of random scenario 2 is b, uncertainty scenario A is composed of random scenario 1, and uncertainty scenario B is composed of random scenario 1 and random scenario 2, then the probability of occurrence of uncertainty scenario A is a, and the probability of occurrence of uncertainty scenario 2 is a+b.

[0098] S104: Optimize the candidate control strategy to obtain an optimized target control strategy.

[0099] Among them, the target control strategy is the optimal control strategy for the control facilities under the corresponding uncertainty scenario.

[0100] The control period includes multiple control time periods. The candidate control strategies corresponding to each control time period are optimized one by one to obtain the optimal control strategies for multiple control facilities under the corresponding uncertainty scenarios until all the candidate control strategies corresponding to each control time period are optimized.

[0101] The embodiment of the present application provides a real-time optimization control method for a drainage system. By comprehensively considering the impact of rainfall forecast errors, control device state uncertainty, and drainage network state uncertainty on the overflow of the drainage system, the control strategy of the control facility is optimized, the robustness of the real-time control strategy is improved, and the phenomenon of a sharp increase in the overflow of internal waterlogging when the system faces emergencies is effectively alleviated, thereby achieving better comprehensive benefits.

[0102] Figure 3 A flow chart of a real-time optimization control method for a drainage system provided in an embodiment of the present application Figure 2 ,like Figure 3 As shown, in this embodiment Figure 1 Based on the embodiment, a possible implementation method of the real-time optimization control method of the drainage system is described in detail, and the method includes:

[0103] S301. Based on the spatial distribution of the underlying surface of the drainage system and the properties of the drainage network, a physical process model is constructed, and model parameters of the physical process model are optimized based on historical rainfall data and hydrological data.

[0104] S302: Based on the real-time rainfall observation data of the area where the drainage system is located, the physical process model at the start time of the optimization period is initialized to obtain the historical status data of the drainage system.

[0105] Based on the real-time rainfall observation data in the area where the drainage system is located, the corresponding drainage physical process model is initialized at the starting time of the optimization period, such as time t, that is, the state of the drainage physical process model at time t is updated to obtain the historical state data of the drainage system.

[0106] S303, constructing a drainage process simulation agent model.

[0107] A drainage process simulation agent model based on the long short-term memory model is established, and its input and output relationship expressions are as follows:

[0108]

[0109] in, represents the time period; P represents the number of time periods of past information required for predicting system overflow; L represents the number of time periods included in the time period to be optimized; It represents the rainfall in period t, in mm; represents the control strategy of control facility j during time period t; Indicates the status of drainage system component k (including control device and drainage pipe) in time period t, represented by 0 and 1, where 0 represents normal condition and 1 represents fault condition.

[0110] Figure 4 A schematic diagram comparing deterministic optimization control based on a drainage physical process model and a drainage process simulation agent model in a single rainstorm provided in an embodiment of the present application.

[0111] Exemplarily, the hyperparameters required for training the drainage process simulation agent model include the number of network layers, the number of hidden layer nodes, and the learning rate, and their values ​​can be, for example, 1, 96, and 0.003, respectively. Figure 4 As shown in the figure, SWMM is a drainage physical process model; MLSM is a drainage process simulation agent model; static control represents a drainage system without optimization control; Figure 4 In (a), the horizontal axis is time and the vertical axis is water depth, which is used to show the change of water depth over time; Figure 4 In (b), the horizontal axis is time and the vertical axis is node traffic, which is used to show the change of node traffic over time; Figure 4 In (c), the horizontal axis is time and the vertical axis is the combined sewer overflow volume, which is used to show the change of combined sewer overflow volume over time; Figure 4 In (d), the horizontal axis is the overflow volume, and the vertical axis is the waterlogging overflow and combined system overflow, which are used to represent the combined system overflow and waterlogging overflow under different models. In the same rainstorm, the water depth, node flow, combined system overflow volume, combined system overflow and waterlogging overflow of the drainage process simulation proxy model and the drainage physical process model are similar in time change. Therefore, the drainage process simulation proxy model can achieve overflow control effects similar to those of the physical process model in deterministic control.

[0112] S304, inputting the historical control data, historical status data, historical rainfall data and multiple random scenarios into the drainage process simulation agent model to obtain the overflow volume of the drainage system under multiple scenarios.

[0113] The historical control data, historical status data, historical rainfall data and multiple random scenarios of the period to be optimized are used as the input of the drainage process simulation agent model. The output results of the drainage process simulation agent model are the overflow volume of the drainage system under various scenarios under various uncertain scenarios.

[0114] S305: Determine an average overflow volume under the multiple scenarios according to the overflow volumes of the multiple scenarios, the occurrence probability corresponding to each scenario, and the objective function.

[0115] In a possible implementation, the process of determining the average overflow volume under various scenarios is described in detail, including: constructing an objective function under a random scenario, wherein the objective function is used to determine the average overflow volume under the various scenarios. The objective function expression is as follows:

[0116]

[0117]

[0118]

[0119] in, represents the average overflow under the influence of precipitation forecast uncertainty; represents the number of random scenario sets for precipitation forecast; represents the overflow volume corresponding to the nth precipitation forecast scenario in period t; represents the probability of occurrence of the nth precipitation forecast scenario in period t; It indicates the average overflow flow under the condition of control equipment failure; It represents the average overflow volume under the condition of sewer failure; and denote the number of random scenario sets for control equipment failure and drainage pipe failure, respectively; represents the overflow volume for time period t, precipitation forecast scenario n and control equipment failure scenario k; represents the joint probability of precipitation forecast scenario n and control equipment failure scenario k in time period t; represents the overflow volume in time period t, precipitation forecast scenario n and drainage pipe failure scenario g; represents the joint probability of precipitation forecast scenario n and drainage pipe failure scenario g in time period t.

[0120] S306: Determine candidate control strategies for multiple control facilities in the drainage system based on the average overflow volumes under the multiple scenarios.

[0121] A multi-objective optimization algorithm (Non-dominated Sorting Genetic Algorithm Ⅱ, NSGA-Ⅱ) is used to optimize the control strategy within the control period (t~t+m, m refers to the number of control period time periods), optimize the above objective function, determine the Pareto frontiers of multiple control objectives and the corresponding control strategies, so that the balance between multiple objectives is more effective and the corresponding control strategies are taken as candidate control strategies.

[0122] S307: Based on a multi-objective decision-making method, the candidate control strategies are optimized, and the control strategy with the best overflow control effect is used as the target control strategy for the multiple control facilities.

[0123] Based on the multi-objective decision-making method, i.e., the distance method between the best and worst solutions, the Euclidean distances between the candidate control strategies and the optimal solution and the worst solution for each control period are determined one by one, and the candidate control strategy with the shortest Euclidean distance to the optimal solution, i.e., the control strategy with the best overflow control effect, is used as the target control strategy for multiple control facilities. Compared with the existing single-objective random predictive control model, the multi-objective random predictive control model provided in the embodiment of the present application can significantly reduce the overflow of the drainage system under the condition of control equipment failure, and achieve better comprehensive benefits.

[0124] For example, Figure 5 This is a comparative diagram of a drainage system real-time optimization control provided by the present invention and a traditional control method and a static control scenario. Figure 5 As shown, SOSMPC is a traditional control method, and MOSMPC is a real-time optimization control method for a drainage system provided in an embodiment of the present application. Figure 5 (a) is a schematic diagram for comparing overflow levels; Figure 5 (b) is a schematic diagram of the comparison of overflow duration; Figure 5 (c) is a schematic diagram for comparing the overflow volume of combined sewer systems; Figure 5 (d) is a schematic diagram for comparing waterlogging overflow. Compared with static control and traditional control methods, the real-time optimization control method for the drainage system provided in the embodiment of the present application significantly reduces the overflow of the drainage system under the condition of control device failure, achieving better comprehensive benefits. Specifically, in the combined uncertainty scenario of precipitation forecast and control device failure, the real-time optimization control method for the drainage system provided in the embodiment of the present application reduces the combined overflow control benefit of the traditional control method by an average of 13.3%, reduces the increase in waterlogging overflow caused by control device failure by an average of 38.0%, and reduces the comprehensive benefit index R caused by control device failure. deficit (a resilience indicator reflecting the magnitude of system service loss) and Rduration The average losses of (resilience indicators reflecting the duration of system service loss) decreased by 46.8% and 50.1% respectively.

[0125] The embodiment of the present application provides a real-time optimization control method for a drainage system. By comprehensively considering the rainfall forecast error, the uncertainty of the control device state and the uncertainty of the drainage network state, the overflow volume corresponding to a variety of random scenarios is determined, and the average overflow volume under a variety of scenarios is determined, and then the candidate control strategy is determined. The candidate control strategy is optimized to obtain a target control strategy, which improves the robustness of the real-time control strategy, effectively alleviates the phenomenon of a sharp increase in the overflow volume of internal waterlogging when the system faces an emergency, and achieves better comprehensive benefits.

[0126] Figure 6 A structural diagram of a real-time optimization control device for a drainage system provided in this application is shown in FIG. Figure 6 As shown, a drainage system real-time optimization control device 60 provided in this embodiment includes:

[0127] An acquisition module 601 is used to acquire historical data of the drainage system, the historical data including: historical status data of the drainage system, historical rainfall data of the area where the drainage system is located, and historical control data of multiple control devices in the drainage system;

[0128] A processing module 602 is used to determine the overflow volume of the drainage system under multiple scenarios based on the historical control data, the historical state data, the historical rainfall data and multiple random scenarios, wherein each scenario is generated by at least one random scenario;

[0129] The processing module 602 is further used to determine candidate control strategies for multiple control devices in the drainage system based on the overflow volumes of the multiple scenarios and the corresponding probability of occurrence of each scenario;

[0130] The optimization module 603 is used to optimize the candidate control strategy to obtain an optimized target control strategy.

[0131] In a possible implementation, the processing module 602 is also used to determine the occurrence probabilities of the multiple random scenarios; for any one of the multiple scenarios, determine at least one target scenario for generating the scenario, and each scenario is independent of each other; when the number of the target scenario is one, the occurrence probability of the target scenario is used as the occurrence probability of the scenario; when the number of the target scenarios is multiple, the sum of the occurrence probabilities of the multiple target scenarios is used as the occurrence probability of the scenario.

[0132] In a possible implementation, the acquisition module 601 is further used to construct a physical process model based on the spatial distribution of the underlying surface of the drainage system and the drainage network properties, and optimize the model parameters of the physical process model based on the historical rainfall data and hydrological data;

[0133] Based on the real-time rainfall observation data of the area where the drainage system is located, the physical process model at the beginning of the optimization period is initialized to obtain the historical state data of the drainage system.

[0134] In one possible implementation, the processing module 602 is also used to construct a drainage process simulation agent model, which is used to simulate the overflow control effect of the physical process model; the historical control data, historical status data, historical rainfall data and multiple random scenarios are input into the drainage process simulation agent model to obtain the overflow volume of the drainage system under various scenarios.

[0135] In a possible implementation, the processing module 602 is further used to construct an objective function under the random scenario, and the objective function is used to determine an average overflow volume under the multiple scenarios.

[0136] In a possible implementation, the device further includes a determining device;

[0137] The determination device is used to determine the average overflow volume under the multiple scenarios according to the overflow volume of the multiple scenarios, the occurrence probability corresponding to each scenario and the objective function;

[0138] Based on the average overflow rates under the various scenarios, candidate control strategies for multiple control facilities in the drainage system are determined.

[0139] In a possible implementation, the optimization module 603 is also used to optimize the candidate control strategies based on a multi-objective decision-making method, and use the control strategy with the best overflow control effect as the target control strategy for the multiple control facilities.

[0140] The present embodiment provides a drainage system real-time optimization control device, which can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail in this embodiment.

[0141] Figure 7 This is a schematic diagram of the structure of a real-time optimization control device for a drainage system provided in an embodiment of the present application. Figure 7 As shown, the drainage system real-time optimization control device 70 provided in this embodiment includes: at least one processor 701 and a memory 702. Optionally, the device 70 also includes a communication component 703. The processor 701, the memory 702 and the communication component 703 are connected via a bus.

[0142] In a specific implementation process, at least one processor 701 executes the computer-executable instructions stored in the memory 702, so that at least one processor 701 executes the above method.

[0143] The specific implementation process of the processor 701 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0144] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0145] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0146] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0147] The present application also provides a computer program product, including a computer program, which implements the above-mentioned real-time optimization control method for the drainage system when executed by a processor.

[0148] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0149] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0150] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0151] The division of units is only a logical function division, and there may be other divisions in actual implementation, 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 an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0152] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0153] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0154] If the function 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 invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0155] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0156] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A real-time optimization control method for a drainage system, characterized in that: include: Acquire historical data of the drainage system, the historical data including: historical status data of the drainage system, historical rainfall data of the area where the drainage system is located, and historical control data of multiple control devices in the drainage system, the historical status data and historical control data are used to indicate the risk of facility failure of the drainage system; Determine the overflow volume of the drainage system under multiple scenarios based on the historical control data, the historical status data, the historical rainfall data and multiple random scenarios, wherein each scenario is generated by at least one random scenario; Constructing an objective function under a random scenario, wherein the objective function is used to determine an average overflow volume under the multiple scenarios; Determine the average overflow volume under the multiple scenarios according to the overflow volume of the multiple scenarios, the occurrence probability corresponding to each scenario and the objective function; Based on the average overflow volume under the multiple scenarios, candidate control strategies for multiple control facilities in the drainage system are determined, specifically: a multi-objective optimization algorithm is used to optimize the control strategy during the control period, the objective function is optimized, the Pareto fronts of multiple control objectives and corresponding control strategies are determined, and the control strategy corresponding to the balance between the multiple objectives is selected as the candidate control strategy; The candidate control strategy is optimized to obtain an optimized target control strategy.

2. The method according to claim 1, characterized in that The method further comprises: determining the probability of occurrence of the plurality of random scenarios; For any one of the multiple scenarios, determining at least one target scenario for generating the scenario, wherein each scenario is independent of each other; When the number of the target scenarios is one, the occurrence probability of the target scenario is used as the occurrence probability of the scenario; When there are multiple target scenarios, the sum of the occurrence probabilities of the multiple target scenarios is used as the occurrence probability of the scenario.

3. The method according to claim 1, characterized in that The obtaining of historical status data of the drainage system includes: Based on the spatial distribution of the underlying surface of the drainage system and the properties of the drainage network, a physical process model is constructed, and model parameters of the physical process model are optimized based on the historical rainfall data and hydrological data; Based on the real-time rainfall observation data of the area where the drainage system is located, the physical process model at the beginning of the optimization period is initialized to obtain the historical state data of the drainage system.

4. The method according to claim 3, characterized in that The method of determining the overflow volume of the drainage system in various scenarios based on the historical control data, the historical status data, the historical rainfall data and a plurality of random scenarios includes: Constructing a drainage process simulation proxy model, wherein the drainage process simulation proxy model is used to replace the physical process model to simulate the overflow control effect; The historical control data, historical status data, historical rainfall data and multiple random scenarios are input into the drainage process simulation agent model to obtain the overflow volume of the drainage system under various scenarios.

5. The method according to claim 1, characterized in that The step of optimizing the candidate control strategy to obtain an optimized target control strategy includes: Based on a multi-objective decision-making method, the candidate control strategies are optimized, and the control strategy with the best overflow control effect is used as the target control strategy for the multiple control facilities.

6. A real-time optimization control device for a drainage system, characterized in that: include: an acquisition module, used to acquire historical data of the drainage system, the historical data including: historical status data of the drainage system, historical rainfall data of the area where the drainage system is located, and historical control data of multiple control devices in the drainage system, the historical status data and historical control data are used to indicate the risk of facility failure of the drainage system; A processing module, configured to determine the overflow volume of the drainage system under multiple scenarios based on the historical control data, the historical status data, the historical rainfall data and multiple random scenarios, wherein each scenario is generated by at least one random scenario; The processing module is further used to determine the average overflow volume under the multiple scenarios according to the overflow volume under the multiple scenarios, the probability of occurrence corresponding to each scenario and the objective function; based on the average overflow volume under the multiple scenarios, determine the candidate control strategies for the multiple control facilities in the drainage system, specifically: use a multi-objective optimization algorithm to optimize the control strategy within the control period, optimize the objective function, determine the Pareto fronts of multiple control objectives and the corresponding control strategies, and select the control strategy corresponding to the balance between the multiple objectives as the candidate control strategy; An optimization module, used for optimizing the candidate control strategy to obtain an optimized target control strategy; The processing module is also used to construct an objective function under the random scenario, and the objective function is used to determine the average overflow volume under the multiple scenarios.

7. A real-time optimization control device for a drainage system, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the real-time optimization control method for the drainage system according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the real-time optimization control method for the drainage system as described in any one of claims 1 to 5.

Images