Real-time control method and apparatus for urban drainage system, device and medium

Abstract

The present disclosure relates to the field of urban pipeline network flood defense and drainage, and in particular to a real-time control method and apparatus for an urban drainage system, a device, and a medium. The method comprises: acquiring current measured rainfall data of a target city and forecast rainfall data thereof in multiple future time periods; on the basis of the current measured rainfall data, updating an initial pipeline network SWMM of the target city; and, on the basis of an initialized DDDP-TL optimization algorithm, using the current measured rainfall data and the forecast rainfall data in multiple future time periods to perform rolling optimization on the updated pipeline network SWMM, so as to obtain a final control trajectory.

Description

Real-time control methods, devices, equipment and media for urban drainage systems

[0001] Cross-reference to related applications

[0002] This disclosure claims priority to Chinese Patent Application No. 202510351189.7, filed on March 24, 2025, by Yangtze River Ecological and Environmental Protection Group Co., Ltd. and Wuhan University, entitled “Real-time Control Method, Device, Equipment and Medium for Urban Drainage System”. Technical Field

[0003] This disclosure relates to the field of urban pipe network flood control and drainage technology, and in particular to a real-time control method, device, equipment and medium for urban drainage systems based on discrete differential dynamic programming. Background Technology

[0004] With the accelerating pace of global urbanization and the intensifying effects of climate change, urban flooding risks are becoming increasingly severe, making water resource management a particularly prominent issue in large cities. The combined sewer systems and commonly used drainage control methods prevalent in many developed and developing countries are no longer sufficient to meet the ever-increasing drainage demands. For example, over 60% of China's 351 cities have experienced urban flooding, and approximately 140 cities experience at least one flood annually. Therefore, fully utilizing existing urban drainage facilities and establishing a real-time control method for urban drainage systems based on discrete differential dynamic programming is of great significance in addressing urban flooding under torrential rain conditions, ensuring public health and safety, and reducing economic losses.

[0005] In urban flooding and combined sewer overflow (CSO) management schemes, proactive control of existing drainage infrastructure not only effectively improves drainage system performance compared to constructing or expanding new drainage facilities, but also requires less capital investment. Existing proactive control methods largely rely on control rules, aiming to optimize the operational efficiency of storage tanks, pumping stations, and lakes with flood regulation capabilities. However, research on storage space within pipelines is insufficient, and the network's storage capacity is not fully utilized. Furthermore, when calculating the optimal scheduling plan for urban drainage networks, the complexity of optimization operations increases exponentially with the increase in control nodes (such as intercepting wells and pumping stations), easily leading to the "curse of dimensionality" problem, making the actual optimization process difficult to implement. Summary of the Invention

[0006] This disclosure provides a real-time control method, device, equipment, and medium for urban drainage systems to address the problems of existing urban flooding and combined sewer overflow control schemes relying heavily on control rules, the complexity of optimization operations increasing exponentially with the increase of control nodes, and the failure to fully utilize the storage capacity of the pipe network.

[0007] The first aspect of this disclosure provides a real-time control method for an urban drainage system, comprising the following steps:

[0008] The DDDP-TL optimization algorithm is initialized based on the pre-constructed initial pipeline network SWMM model of the target city to obtain the initialized DDDP-TL optimization algorithm.

[0009] Obtain the current measured rainfall data and the forecast rainfall data for multiple time periods in the target city;

[0010] The initial SWMM model of the pipeline network is updated based on the current measured rainfall data to obtain the updated SWMM model of the pipeline network.

[0011] Based on the initialized DDDP-TL optimization algorithm, the updated pipeline network SWMM model is continuously optimized using the current measured rainfall data and the forecasted rainfall data for multiple future periods to obtain the final control trajectory.

[0012] In some embodiments, the initialization of the DDDP-TL optimization algorithm based on the pre-constructed initial pipeline network SWMM model of the target city to obtain the initialized DDDP-TL optimization algorithm includes:

[0013] The number of discrete layers of the DDDP-TL optimization algorithm and the initial control trajectory of each control node of the pipeline network are determined based on the initial pipeline network SWMM model.

[0014] The DDDP-TL optimization algorithm is initialized using the number of discrete layers, the initial control trajectory of each control node in the pipeline network, the objective function, decision variables, state variables, and constraints of the DDDP-TL optimization algorithm to obtain the initialized DDDP-TL optimization algorithm.

[0015] In some embodiments, the expression for the objective function is:

[0016] Where F is the total overflow, N F N represents the number of nodes affected by flooding. C For the number of overflow nodes in a combined system, FL i,t CSO represents the flood overflow at node i during time period t. i,t Let be the combined overflow of node i during time period t, α and β be the weighting coefficients of the two overflow control methods, T be the total number of simulation time periods, and Δt be the time step.

[0017] In some embodiments, the decision variable is the set of opening degrees of all control nodes; the state variable is the sum of pipeline water storage and overflow within the control area of ​​the control node; and the constraints include initial conditions, boundary conditions, hydraulic constraints, facility operation condition constraints, and time constraints.

[0018] In some embodiments, the step of performing rolling optimization on the updated pipeline network SWMM model based on the initialized DDDP-TL optimization algorithm, using the current measured rainfall data and the forecasted rainfall data for multiple future time periods, to obtain the final control trajectory includes:

[0019] The forecasted rainfall data for time period t is input into the updated pipeline network SWMM model, and the state of the updated pipeline network SWMM model is updated using the initialized DDDP-TL optimization algorithm. The forecasted rainfall data for each future time period is input into the updated pipeline network SWMM model, and the state update process is iteratively executed until all control nodes are optimized and the number of iterations reaches a preset threshold, thus obtaining the final control trajectory, where t is the current time period.

[0020] In some embodiments, the step of inputting the forecasted rainfall data for time period t into the updated network SWMM model and using the initialized DDDP-TL optimization algorithm to update the state of the updated network SWMM model includes:

[0021] Input the forecasted rainfall data for time period t into the updated pipeline network SWMM model, and read the hot start file of the updated pipeline network SWMM model for time period t-1;

[0022] Based on the initialized DDDP-TL optimization algorithm, the updated pipeline network SWMM model is used to perform state transition calculations according to the forecast rainfall data for time period t and the hot start file for time period t-1 to obtain the current control trajectory for time period t, and the updated pipeline network SWMM model is then updated according to the current control trajectory for time period t.

[0023] A second aspect of this disclosure provides a real-time control device for an urban drainage system, comprising: an initialization module for initializing a DDDP-TL optimization algorithm based on a pre-constructed initial network SWMM model of a target city to obtain an initialized DDDP-TL optimization algorithm; an acquisition module for acquiring current measured rainfall data and forecasted rainfall data for multiple future time periods of the target city; an update module for updating the initial network SWMM model based on the current measured rainfall data to obtain an updated network SWMM model; and a rolling optimization module for performing rolling optimization on the updated network SWMM model based on the initialized DDDP-TL optimization algorithm, using the current measured rainfall data and the forecasted rainfall data for multiple future time periods to obtain a final control trajectory.

[0024] A third aspect of this disclosure provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the real-time control method for an urban drainage system as described in the above embodiments.

[0025] This disclosure provides a computer program product that, when executed by a processor, implements the real-time control method for an urban drainage system as described in the above embodiments.

[0026] A fifth aspect of this disclosure provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the real-time control method for an urban drainage system as described in the above embodiments.

[0027] The real-time control method, apparatus, equipment, and medium for urban drainage systems proposed in this disclosure take into account the current situation where the increase in control nodes in urban drainage systems easily leads to the curse of dimensionality, as well as the current situation where the storage space of existing urban pipe networks is not fully utilized. The method decomposes the multidimensional problem of flood control and drainage in pipe network systems into multiple one-dimensional sub-problems, thereby improving the calculation speed. Furthermore, it utilizes rolling optimization calculations to perform real-time control of urban drainage systems, meeting the scheduling needs of urban drainage systems. This real-time control method can adapt to most urban conditions and has strong adaptability and scalability.

[0028] Additional aspects and advantages of this disclosure will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this disclosure. Attached Figure Description

[0029] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0030] Figure 1 is a flowchart of a real-time control method for an urban drainage system provided in an embodiment of this disclosure;

[0031] Figure 2 is a technical roadmap of a real-time control method for an urban drainage system that considers the regulation and storage function of the drainage network according to an embodiment of this disclosure.

[0032] Figure 3 is a schematic diagram illustrating the specific execution of a real-time control method for an urban drainage system according to an embodiment of this disclosure.

[0033] Figure 4 is a map showing the location of a specific study area and the distribution of drainage facilities according to an embodiment of this disclosure.

[0034] Figure 5 is a schematic diagram of the main interface of a specific research area SWMM model according to an embodiment of this disclosure;

[0035] Figure 6 is a block diagram of a real-time control device for an urban drainage system provided in an embodiment of this disclosure;

[0036] Figure 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0037] Embodiments of this disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0038] Figure 1 is a flowchart of a real-time control method for an urban drainage system provided in an embodiment of this disclosure.

[0039] As shown in Figure 1, the real-time control method for the urban drainage system includes the following steps:

[0040] In step S101, the Discrete Differential Dynamic Programming (DDDP-TL) optimization algorithm is initialized based on the pre-constructed initial pipeline network SWMM model of the target city to obtain the initialized DDDP-TL optimization algorithm.

[0041] In embodiments of this disclosure, the DDDP-TL optimization algorithm is initialized based on a pre-constructed initial pipeline network SWMM model of the target city to obtain the initialized DDDP-TL optimization algorithm, including:

[0042] The number of discrete layers of the DDDP-TL optimization algorithm and the initial control trajectory of each control node in the pipeline network are determined based on the initial SWMM model of the pipeline network.

[0043] The DDDP-TL optimization algorithm is initialized using the discrete number of layers, the initial control trajectory of each control node in the pipeline network, the objective function, decision variables, state variables, and constraints of the DDDP-TL optimization algorithm to obtain the initialized DDDP-TL optimization algorithm.

[0044] In actual implementation, the discrete layer number of the Discrete Differential Dynamic Programming (DDDP-TL) optimization algorithm and the initial control trajectories (i.e., initial control strategies) of each control node (such as intercepting wells) in the pipeline network are determined using the pre-constructed EPA-SWMM5 model of the target city. The DDDP-TL optimization algorithm is then initialized based on the discrete layer number, the initial control trajectories of each control node in the pipeline network, the objective function, decision variables, state variables, constraints, and optimization corridors of the DDDP-TL optimization algorithm.

[0045] The objective function of the DDDP-TL optimization algorithm is to minimize the sum of urban sewer overflow and combined sewer overflow, expressed as:

[0046] Where F is the total overflow, N F N represents the number of nodes affected by flooding. C For the number of overflow nodes in a combined system, FL i,t CSO represents the flood overflow at node i during time period t. i,t Let be the combined overflow of node i during time period t, α and β be the weighting coefficients of the two overflow control methods, T be the total number of simulation time periods, and Δt be the time step.

[0047] In order to solve the dimensionality curse problem that is prone to occur under multiple control node conditions when optimizing the urban pipeline network model, this embodiment decomposes the multidimensional (M-dimensional) optimization control problem into M one-dimensional sub-problems through discrete differentiation, and then solves each sub-problem through dynamic programming, while keeping the control trajectory of other control nodes unchanged. In the DDDP-TL optimization algorithm, the decision variable is the set of opening degrees of all control nodes, and the state variable is the sum of pipeline water storage and overflow within the control area of ​​the control node.

[0048] The constraints include initial conditions, boundary conditions, hydraulic constraints, facility operation constraints, and time constraints. The initial conditions are the model state at the start and end of the optimization and the initial control trajectory. The boundary conditions consider the water level conditions of water bodies such as rivers, lakes, and oceans connected to the urban pipe network, as well as the elevation and coordinate limitations of each hydraulic facility in the pipe network model. The hydraulic constraints are that the sum of the inflow volume equals the sum of the outflow volume throughout the simulation process; the water body maintains a unidirectional flow from upstream to downstream (except at the outlet connected to the external water body, and backflow is not considered). The facility operation constraints are that the flow rate does not exceed the upper limit of the pipe and channel flow rate, the flow velocity does not exceed the upper limit of the pipe and channel flow velocity, the upper limit of the reservoir capacity and the water level-capacity curve are considered, and the flow rate and power limitations of the pumping station are considered. The time constraint is that the simulation optimization time must be less than the control time step.

[0049] In step S102, the current measured rainfall data and the forecast rainfall data for multiple time periods in the target city are obtained.

[0050] In step S103, the initial SWMM model of the pipeline network is updated based on the current measured rainfall data to obtain the updated SWMM model of the pipeline network.

[0051] In actual implementation, the current measured rainfall data and forecasted rainfall data for multiple time periods in the target city can be obtained through information such as rainfall amount and rainfall intensity released by the meteorological department. The initial SWMM model state of the pipeline network can be updated based on the current measured rainfall data, that is, the control nodes of the pipeline network are updated based on the current measured rainfall data to obtain the updated SWMM model of the pipeline network.

[0052] In step S104, based on the initialized DDDP-TL optimization algorithm, the updated pipeline network SWMM model is rolled and optimized using the current measured rainfall data and the forecast rainfall data for multiple future periods to obtain the final control trajectory.

[0053] In the embodiments of this disclosure, based on the initialized DDDP-TL optimization algorithm, the updated pipeline network SWMM model is subjected to rolling optimization using current measured rainfall data and forecasted rainfall data for multiple future periods to obtain the final control trajectory, including:

[0054] The forecasted rainfall data for time period t is input into the updated pipeline network SWMM model, and the state of the updated pipeline network SWMM model is updated using the initialized DDDP-TL optimization algorithm. The forecasted rainfall data for each future time period is input into the updated pipeline network SWMM model, and the state update process is iteratively executed until all control nodes are optimized and the number of iterations reaches a preset threshold, thus obtaining the final control trajectory, where t is the current time period.

[0055] In some embodiments, the forecasted rainfall data for time period t is input into the updated network SWMM model, and the state of the updated network SWMM model is updated using the initialized DDDP-TL optimization algorithm, including:

[0056] Input the forecasted rainfall data for time period t into the updated pipeline network SWMM model, and read the hot start file of the updated pipeline network SWMM model for time period t-1;

[0057] Based on the initialized DDDP-TL optimization algorithm, the updated pipeline network SWMM model is used to perform state transition calculations based on the forecast rainfall data and hot start file for time period t to obtain the current control trajectory for time period t, and the updated pipeline network SWMM model is then updated based on the current control trajectory for time period t.

[0058] In the actual execution process, as shown in Figures 2 and 3, rolling optimization calculations are performed based on the updated pipeline network SWMM model and the initialized DDDP-TL optimization algorithm. At this time, the current iteration number j = 1 and the current control node i = 1 are set.

[0059] The overflow rate under the current control strategy is evaluated based on the objective function of the updated SWMM model of the pipe network. If i > N, where N is the total number of control nodes, then j = j + 1 is run, and it is determined whether j and i satisfy j > M and i > N, where M is the total number of outer iterations. If they are satisfied, the final control trajectory is obtained. Otherwise, the forecast rainfall data for time period t is input into the updated SWMM model of the pipe network, and the hot start file for time period t-1 of the updated SWMM model of the pipe network is read. Based on the initialized DDDP-TL optimization algorithm, the state transition calculation of the updated SWMM model of the pipe network is performed according to the forecast rainfall data for time period t and the hot start file for time period t-1 to search for the current control strategy for time period t. At the same time, the hot start file for time period t is saved. After saving, it is determined whether the current time period is greater than the preset threshold T. If it is not greater, the state transition calculation is iteratively executed. Otherwise, the above process is iteratively executed for the next control node until all control nodes are updated, thereby obtaining the final control trajectory (i.e., the final control strategy) of the target city drainage system.

[0060] The recursive equation for the state transition calculation of the updated pipeline network SWMM model based on the forecast rainfall data for time period t and the hot start file for time period t-1 is as follows:

[0061] min CF i,t+1 (S i,t+1 ) = F i,t (S i,t O i,t )+CF i,t (S i,t )

[0062] In the formula, S i,t Let O be the water storage volume within the control area of ​​the i-th control node during time period t. i,t Let F be the control strategy for the i-th control node within time period t. i,t (S i,t O i,t ) represents the total overflow during time period t, Flooding i,t Let CSO be the flood overflow at node i during time period t. i,t Let L be the merging overflow of node i during time period t. i CF represents the time delay of the flow rate from the i-th control node to the system outlet. i,t (S i,t The system's cumulative overflow from the initial time period to the current time period (time period t) is the total overflow.

[0063] The following example, using a specific area in Yueyang, further illustrates the real-time control method for the urban drainage system proposed in this disclosure.

[0064] Step 1: Construct an SWMM model of the urban pipe network in a certain area of ​​Yueyang and determine the model parameters such as pipe size, roughness and coordinates. Determine the number of DDDP-TL discrete layers (set to 5 in this example) and the initial control trajectory of each control node of the pipe network (intercepting well in this example). Form an optimization corridor based on the number of discrete layers.

[0065] Step 2: Update the SWMM model state based on the latest measured rainfall data, denoted as t, and set the opening degree of the intercepting wells to 1 at the initial moment, that is, 100% open, so that the water can flow through completely;

[0066] Step 3, as shown in Figure 3, input the current measured rainfall data and the forecasted rainfall data for multiple future time periods into the updated SWMM model of the pipe network. Use the DDDP-TL optimization algorithm to calculate the optimal control trajectory for the time period t to t+n, i.e., the trajectory of the opening state of each intercepting well in the pipe network as time changes from t to t+n, where n represents the number of control time steps. The objective of the DDDP-TL optimization algorithm is to minimize the sum of the urban pipe network flood overflow and the combined sewer overflow. The objective function is:

[0067] In the formula, F is the total overflow, and N is the total overflow. F and N C FL represents the number of flood overflow nodes and the number of combined sewer overflow nodes, respectively. i,t and CSO i,tα and β represent the flood overflow and combined sewer overflow at node i during time period t, respectively. α and β represent the weighting coefficients of the two overflow control methods. In this example, α = 20 and β = 1 are set. T is the total number of simulation periods, which is 7 hours, and Δt is the time step, which is 20 minutes.

[0068] In the optimization algorithm of this embodiment, the decision variable is the opening degree of all intercepting wells, and the state variable is the sum of the pipeline water storage and overflow within the control area of ​​the intercepting well.

[0069] The constraints in this embodiment include initial condition constraints, pipeline model boundary constraints, lake water level constraints, hydraulic constraints, facility operation condition constraints, and time constraints.

[0070] The specific process of calculating the optimal control trajectory for the time period t to t+n using the DDDP-TL optimization algorithm is as follows:

[0071] (1) Rolling optimization calculation is performed based on the updated pipeline network SWMM model and the initial conditions of the initialized DDDP-TL optimization algorithm. Set j=1, i=1. In this embodiment, j is the current iteration number and i is the current control node (i.e., the interception well).

[0072] (2) Evaluate the overflow rate under the current control strategy based on the objective function. If i>N, then run j=j+1, where N is the total number of interception wells, which is set to 3 in the embodiment (i.e. C1~C3 in Figure 4).

[0073] (3) Determine whether j and i satisfy j>M and i>N. If not, proceed to (4). If they satisfy, proceed to (8). M is the total number of outer iterations, which is set to 20 in the example.

[0074] (4) Input the current measured rainfall data into the updated pipeline network SWMM model, and use the initialized DDDP-TL optimization algorithm to optimize the control strategy of intercepting well i (if i>N, then make i=1 and enter a new round of outer layer iteration), while the state of the other intercepting wells remains unchanged. At this time, t=1, and t is the time period;

[0075] (5) Update system state: Read the hot start file for time period t-1, perform state transition calculation based on the updated SWMM model, search for the optimal control strategy for time period t, and save the hot start file for time period t.

[0076] (6) Determine whether t and T satisfy t>T. If they satisfy, proceed to (7). If they do not satisfy, run t=t+1 and proceed to step 5.

[0077] (7) Update the control strategy of flow control node i, let i = i+1, and proceed to (2);

[0078] (8) Find the optimal control trajectory, the DDDP-TL optimization ends, and the optimal simulation result is output.

[0079] Step 4: While ensuring that the control time step is greater than the actual time required for each optimization step, execute the control strategy for the time period t to t+1 based on the calculation results of Step 3.

[0080] Step 5: Enter the next time period, use the optimal control trajectory calculated in Step 3 as the initial control trajectory of DDDP-TL, and repeat Steps 2 to 4 until the rolling optimization simulation ends.

[0081] In summary, the real-time control method for urban drainage systems proposed according to the embodiments of this disclosure has the following beneficial effects:

[0082] (1) The concept of dynamic planning and optimization control of urban drainage system was introduced, and the traditional "rule-controlled drainage" mode was transformed into a dual management mode of "dynamic regulation and storage + optimization control drainage", which provides new technical means for urban flood control and drainage management.

[0083] (2) Based on the Discrete Differential Dynamic Programming (DDDP-TL) algorithm, the problem of dimensionality curse under multiple control nodes is effectively alleviated and the optimization solution efficiency is significantly improved.

[0084] (3) Real-time control of the urban drainage system was achieved by using rolling optimization calculation, which better meets the scheduling needs of the urban drainage system;

[0085] (4) By making full use of the storage space in the drainage network, the control capability of flood overflow and combined sewer overflow has been optimized, and the response efficiency of the drainage system has been improved.

[0086] (5) It is applicable to the dynamic control scenarios of most urban drainage systems. Under the premise of maintaining the existing drainage network infrastructure, it can help improve the real-time scheduling capability and comprehensive flood control efficiency of urban drainage systems, achieve more efficient drainage management and flood risk control, and has strong adaptability and promotion.

[0087] Next, the real-time control device for an urban drainage system proposed according to an embodiment of the present disclosure is described with reference to the accompanying drawings.

[0088] Figure 6 is a block diagram of a real-time control device for an urban drainage system according to an embodiment of the present disclosure.

[0089] As shown in Figure 6, the real-time control device 60 for the urban drainage system includes: an initialization module 601, an acquisition module 602, an update module 603, and a rolling optimization module 604.

[0090] The initialization module 601 initializes the DDDP-TL optimization algorithm based on a pre-constructed initial pipeline network SWMM model of the target city, resulting in an initialized DDDP-TL optimization algorithm. The acquisition module 602 acquires current measured rainfall data and forecasted rainfall data for multiple future time periods for the target city. The update module 603 updates the initial pipeline network SWMM model based on the current measured rainfall data, resulting in an updated pipeline network SWMM model. The rolling optimization module 604 performs rolling optimization on the updated pipeline network SWMM model based on the initialized DDDP-TL optimization algorithm, using current measured rainfall data and forecasted rainfall data for multiple future time periods, to obtain the final control trajectory.

[0091] In one embodiment of this disclosure, the initialization module 601 includes:

[0092] The determination unit is used to determine the number of discrete layers of the DDDP-TL optimization algorithm and the initial control trajectory of each control node in the pipeline network based on the initial pipeline network SWMM model;

[0093] The initialization unit is used to initialize the DDDP-TL optimization algorithm using the discrete layer number and the initial control trajectory of each control node in the pipeline network, the objective function of the DDDP-TL optimization algorithm, decision variables, state variables and constraints, so as to obtain the initialized DDDP-TL optimization algorithm.

[0094] In one embodiment of this disclosure, the expression for the objective function is:

[0095] Where F is the total overflow, N F N represents the number of nodes affected by flooding. C For the number of overflow nodes in a combined system, FL i,t CSO represents the flood overflow at node i during time period t. i,t Let be the combined overflow of node i during time period t, α and β be the weighting coefficients of the two overflow control methods, T be the total number of simulation time periods, and Δt be the time step.

[0096] In one embodiment of this disclosure, the decision variable is the set of opening degrees of all control nodes; the state variable is the sum of the pipeline water storage and overflow within the control area of ​​the control node; and the constraints include initial conditions, boundary conditions, hydraulic constraints, facility operation condition constraints, and time constraints.

[0097] In one embodiment of this disclosure, the rolling optimization module 604 includes:

[0098] The state update unit inputs the forecasted rainfall data for time period t into the updated pipeline network SWMM model and uses the initialized DDDP-TL optimization algorithm to update the state of the updated pipeline network SWMM model.

[0099] The iterative update unit is used to input the forecast rainfall data for each future time period into the updated pipeline network SWMM model and iteratively execute the state update process until all control nodes are optimized and the number of iterations reaches a preset threshold to obtain the final control trajectory, where t is the current time period.

[0100] In one embodiment of this disclosure, the state update unit includes:

[0101] The input and acquisition sub-unit is used to input the forecasted rainfall data for time period t into the updated pipeline network SWMM model and read the hot start file of the updated pipeline network SWMM model for time period t.

[0102] The state update subunit is used to perform state transition calculations on the updated pipeline network SWMM model based on the initialized DDDP-TL optimization algorithm, according to the forecast rainfall data for time period t and the hot start file for time period t-1, so as to obtain the current control trajectory for time period t, and to update the state of the updated pipeline network SWMM model according to the current control trajectory for time period t-1.

[0103] It should be noted that the foregoing explanation of the embodiment of the real-time control method for urban drainage systems also applies to the real-time control device for urban drainage systems in this embodiment, and will not be repeated here.

[0104] The real-time control device for urban drainage systems proposed according to the embodiments of this disclosure has the following beneficial effects:

[0105] (1) The concept of dynamic planning and optimization control of urban drainage system was introduced, and the traditional "rule-controlled drainage" mode was transformed into a dual management mode of "dynamic regulation and storage + optimization control drainage", which provides new technical means for urban flood control and drainage management.

[0106] (2) Based on the Discrete Differential Dynamic Programming (DDDP-TL) algorithm, the problem of dimensionality curse under multiple control nodes is effectively alleviated and the optimization solution efficiency is significantly improved.

[0107] (3) Real-time control of the urban drainage system was achieved by using rolling optimization calculation, which better meets the scheduling needs of the urban drainage system;

[0108] (4) By making full use of the storage space in the drainage network, the control capability of flood overflow and combined sewer overflow has been optimized, and the response efficiency of the drainage system has been improved.

[0109] (5) It is applicable to the dynamic control scenarios of most urban drainage systems. Under the premise of maintaining the existing drainage network infrastructure, it can help improve the real-time scheduling capability and comprehensive flood control efficiency of urban drainage systems, achieve more efficient drainage management and flood risk control, and has strong adaptability and promotion.

[0110] Figure 7 is a schematic diagram of an electronic device according to an embodiment of the present disclosure. The electronic device may include:

[0111] The memory 701, the processor 702, and the computer program stored on the memory 701 and capable of running on the processor 702.

[0112] When the processor 702 executes the program, it implements the real-time control method for the urban drainage system provided in the above embodiments.

[0113] Furthermore, electronic devices also include:

[0114] Communication interface 703 is used for communication between memory 701 and processor 702.

[0115] The memory 701 is used to store computer programs that can run on the processor 702.

[0116] The memory 701 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0117] If the memory 701, processor 702, and communication interface 703 are implemented independently, they can be interconnected via a bus to communicate with each other. 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. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, only one thick line is used in Figure 7, but this does not indicate that there is only one bus or one type of bus.

[0118] Optionally, in a specific implementation, if the memory 701, processor 702, and communication interface 703 are integrated on a single chip, then the memory 701, processor 702, and communication interface 703 can communicate with each other through an internal interface.

[0119] The processor 702 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present disclosure.

[0120] This disclosure also provides a computer program product that, when executed by a processor, implements the above-described real-time control method for an urban drainage system.

[0121] This disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described real-time control method for an urban drainage system.

[0122] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0123] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0124] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.

[0125] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0126] It should be understood that the various parts of this disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0127] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0128] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0129] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.

Claims

1. A real-time control method for an urban drainage system, wherein, Includes the following steps: The DDDP-TL optimization algorithm is initialized based on the pre-constructed initial pipeline network SWMM model of the target city to obtain the initialized DDDP-TL optimization algorithm. Obtain the current measured rainfall data and the forecast rainfall data for multiple time periods in the target city; The initial SWMM model of the pipeline network is updated based on the current measured rainfall data to obtain the updated SWMM model of the pipeline network. Based on the initialized DDDP-TL optimization algorithm, the updated pipeline network SWMM model is continuously optimized using the current measured rainfall data and the forecasted rainfall data for multiple future periods to obtain the final control trajectory.

2. The real-time control method for urban drainage systems according to claim 1, wherein, The initialization of the DDDP-TL optimization algorithm based on the pre-constructed initial pipeline network SWMM model of the target city to obtain the initialized DDDP-TL optimization algorithm includes: The number of discrete layers of the DDDP-TL optimization algorithm and the initial control trajectory of each control node of the pipeline network are determined based on the initial pipeline network SWMM model. The DDDP-TL optimization algorithm is initialized using the number of discrete layers, the initial control trajectory of each control node in the pipeline network, the objective function, decision variables, state variables, and constraints of the DDDP-TL optimization algorithm to obtain the initialized DDDP-TL optimization algorithm.

3. The real-time control method for urban drainage systems according to claim 2, wherein, The expression for the objective function is: Where F is the total overflow, N F N represents the number of nodes affected by flooding. C For the number of overflow nodes in a combined system, FL i,t CSO represents the flood overflow at node i during time period t. i,t Let be the combined overflow of node i during time period t, α and β be the weighting coefficients of the two overflow control methods, T be the total number of simulation time periods, and Δt be the time step.

4. The real-time control method for urban drainage systems according to claim 2, wherein, The decision variable is the set of opening degrees of all control nodes; The state variable is the sum of the pipeline water storage and overflow within the control area of ​​the control node; The constraints include initial conditions, boundary conditions, hydraulic constraints, facility operation condition constraints, and time constraints.

5. The real-time control method for urban drainage systems according to claim 1, wherein, The optimization algorithm based on the initialized DDDP-TL uses the current measured rainfall data and the forecasted rainfall data for multiple future periods to perform rolling optimization on the updated pipeline network SWMM model to obtain the final control trajectory, including: The forecasted rainfall data for time period t is input into the updated pipeline network SWMM model, and the state of the updated pipeline network SWMM model is updated using the initialized DDDP-TL optimization algorithm; The forecasted rainfall data for each future time period is input into the updated pipeline network SWMM model, and the state update process is iteratively executed until all control nodes are optimized and the number of iterations reaches a preset threshold, thus obtaining the final control trajectory, where t is the current time period.

6. The real-time control method for urban drainage systems according to claim 5, wherein, The step of inputting the forecasted rainfall data for time period t into the updated pipeline network SWMM model and using the initialized DDDP-TL optimization algorithm to update the state of the updated pipeline network SWMM model includes: Input the forecasted rainfall data for time period t into the updated pipeline network SWMM model, and read the hot start file of the updated pipeline network SWMM model for time period t-1; Based on the initialized DDDP-TL optimization algorithm, the updated pipeline network SWMM model is used to perform state transition calculations according to the forecast rainfall data for time period t and the hot start file for time period t-1 to obtain the current control trajectory for time period t, and the updated pipeline network SWMM model is then updated according to the current control trajectory for time period t.

7. A real-time control device for an urban drainage system, wherein, include: The initialization module is used to initialize the DDDP-TL optimization algorithm based on the pre-built initial pipeline network SWMM model of the target city, so as to obtain the initialized DDDP-TL optimization algorithm. The acquisition module is used to acquire the current measured rainfall data and the forecast rainfall data for multiple time periods in the target city; The update module is used to update the initial network SWMM model based on the current measured rainfall data to obtain the updated network SWMM model. The rolling optimization module is used to perform rolling optimization on the updated pipeline network SWMM model based on the initialized DDDP-TL optimization algorithm, using the current measured rainfall data and the forecast rainfall data for multiple future periods, in order to obtain the final control trajectory.

8. An electronic device, wherein, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the real-time control method for an urban drainage system as described in any one of claims 1-6.

9. A computer program product, wherein, When the computer program / instruction is executed by the processor, it implements the real-time control method for the urban drainage system as described in any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, wherein, The program is executed by the processor to implement the real-time control method for urban drainage systems as described in any one of claims 1-6.

Images