Real-time prediction control and dynamic optimization method and system for split-flow rainwater storage tank

Abstract

The present application provides a method and system for real-time prediction control and dynamic optimization of a diversion rainwater storage tank, the method comprising the following steps: setting a rainy day algorithm decision; setting a dry day algorithm decision; obtaining a dynamic database; judging and obtaining real-time weather conditions based on the obtained rainfall monitoring data of the storage tank and the flow of the rainwater well upstream of the storage tank; using the obtained water quality, flow, water level and rainfall monitoring data as a training set, dynamically optimizing the parameters of the set rainy day algorithm decision and the dry day algorithm decision, and obtaining the rainy day algorithm decision and the dry day algorithm decision after the dynamic optimization of the parameters; according to the obtained real-time weather conditions and based on the basic information of the storage tank system, controlling the storage tank system to execute the rainy day algorithm decision or the dry day algorithm decision after the dynamic optimization of the parameters of the corresponding weather. The present application can utilize the continuously updated online monitoring data and weather forecast data of the storage tank system to significantly improve the water quantity, water quality and economy multiple control performance of the rainwater storage tank.

Description

Technical Field

[0001] The present application relates to the field of urban stormwater management and real-time control technology, and specifically to a real-time prediction control and dynamic optimization method and system for a diversion-type stormwater storage tank. Background Art

[0002] Affected by global climate change and the rapid development of urbanization, the urban water cycle and storm flood characteristics have undergone tremendous changes, and urban flood problems have become increasingly prominent. Facing the urgent need for urban flood control, domestic and foreign scholars have carried out a lot of research on the layout and optimization of storm flood management measures.

[0003] Among them, the diversion-type urban rainwater storage tank is an important engineering measure for rainwater retention. It takes in water from the rainwater main pipe to adjust the peak flow in the drainage network, which has the function of increasing the storage capacity of the rainwater system. With the proposal and practice of the sponge city concept in my country, the rainwater storage tank, as an important part of the gray infrastructure in the construction of sponge cities, complements the green facilities at the source, plays a key role in improving the control of runoff in heavy rain weather, and can provide additional economic benefits such as rainwater reuse.

[0004] However, most of the current rainwater storage pond practices only focus on the optimization of spatial layout, lacking a dynamic control strategy for optimizing the "water storage-drainage" schedule. When dealing with changeable and complex weather conditions, the disadvantages of this type of static management model are mainly reflected in the fact that it greatly restricts the dynamic storage capacity of the storage pond system, resulting in the diversion rainwater storage pond often being unable to play a significant peak-cutting role in rainstorm weather when the runoff volume far exceeds the system storage volume, and it is difficult to cope with multiple control targets under different weather conditions. Therefore, further research is needed on the dynamic control technology of diversion rainwater storage ponds under changing weather conditions.

[0005] With the development of urban hydrological information and monitoring technology, dynamic real-time control mode has been applied to the operation of urban combined sewer systems and gradually extended to the field of stormwater management. In recent years, many studies on real-time control algorithms for rainwater storage tanks, collection tanks, and water storage basins have emerged at home and abroad, mainly including reactive control and predictive control.

[0006] Among them, reactive control only gives feedback based on the current state information of the reservoir system (such as rainfall, upstream flow, water level of the reservoir, etc.). The decision-making cost is low and easy to execute. Typical algorithms include simple rule control method and fuzzy logic control method. Predictive control integrates future prediction information (such as rainfall prediction, flow prediction, water level prediction) into the decision-making process of the current state. Typical algorithms include predictive rule control method and model predictive control method. The former uses prediction information to improve the conditional discriminant of the control rule, and the latter requires the use of hydrological and hydrodynamic prediction models and advanced parameter dynamic optimization methods. Compared with reactive control, whose benefits are limited by historical experience and lack of portability, predictive control has the flexibility to adapt to changing environmental conditions and has shown high efficiency in urban flood control, water quality improvement, base flow control and other aspects.

[0007] However, some predictive control algorithms have high requirements for the prediction of rainfall and flow processes, and face many challenges of uncertain factors in practice. In terms of the development of real-time control tools, foreign scholars have achieved some results, such as swmm_mpc, Pystorm and other software based on the secondary development of the SWMM model, which can be used for real-time control simulation of specified storage tank cases; domestic rain and flood real-time control started late, and existing research mainly uses mature software tools to carry out reactive control simulation of storage tanks, and there is little research on the development of real-time control theoretical methods and tools. In addition, most of the current real-time control strategies are only aimed at a specific rainfall period, such as during or before the rainfall begins, and cannot meet the decision makers' needs for continuous control under changing weather conditions.

[0008] Although many scholars have conducted a certain amount of methodological research on real-time control of urban rainwater storage tanks and developed some software tools suitable for case analysis, the existing research results are usually based on ideal data and the online monitoring and forecasting information that can be actually obtained. It is difficult to take into account the practicality and efficiency of the control algorithm, and it faces challenges in real-world practice. It is necessary to further combine the easy execution of reactive control and the dynamic optimization of parameters of predictive control to develop a real-time control tool for diversion rainwater storage tanks for practical applications, improve the water volume control performance of the storage tank to reduce flood peaks and control runoff under different weather conditions, and achieve rainwater purification, reuse and other control benefits. Further research on real-time control methods for urban rainwater storage tanks will provide important scientific basis and technical support for the adaptive management of urban rain and floods in rainstorm weather. Summary of the invention

[0009] The present application provides a real-time prediction control and dynamic optimization method and system for a diversion-type rainwater storage tank, which can solve the technical problems that the real-time control method of urban rainwater storage tanks in the prior art is only for specific rainfall periods, and cannot fully utilize the available online monitoring data and forecast information, and it is difficult to take into account the practicality and efficiency of the control algorithm.

[0010] In a first aspect, the present application provides a real-time prediction control and dynamic optimization method for a diversion type rainwater storage tank, comprising the following steps:

[0011] Set the rainy day algorithm decision;

[0012] Set drought algorithm decisions;

[0013] Acquire a dynamic database, wherein the dynamic database includes water quality, flow, water level and rainfall monitoring data of the regulating reservoir, weather forecast data and basic information of the regulating reservoir system;

[0014] According to the acquired rainfall monitoring data of the regulating reservoir and the flow of the rainwater well upstream of the regulating reservoir, the real-time weather conditions are determined;

[0015] Using the acquired water quality, flow, water level and rainfall monitoring data as training sets, dynamically optimizing the parameters of the set rainy day algorithm decision and drought day algorithm decision, and obtaining the rainy day algorithm decision and drought day algorithm decision after the dynamic optimization of the parameters;

[0016] According to the real-time weather conditions obtained and based on the basic information of the regulating reservoir system, the regulating reservoir system is controlled to execute the rainy day algorithm decision or the dry day algorithm decision after the parameters of the corresponding weather are dynamically optimized.

[0017] In combination with the first aspect, in one implementation, the setting of the rainy day algorithm decision specifically includes the following steps:

[0018] Construct a fuzzy set of three elements: total rainfall, storage capacity of the reservoir and target flow.

[0019] According to the principle that the greater the rainfall, the greater the target flow, and the smaller the water storage capacity, the smaller the target flow, a fuzzy rule is established with the total rainfall and the water storage capacity of the regulating reservoir as input variables and the target flow as output.

[0020] Based on the established fuzzy rules, the fuzzy set of target flow is obtained through fuzzy reasoning under the condition of known total rainfall and water storage capacity;

[0021] The maximum membership method is used to perform defuzzification calculation on the fuzzy set of the target flow to obtain the calculated value of the target flow;

[0022] Based on the calculated value of the target flow, solve the opening of the water inlet gate of the storage tank.

[0023] In combination with the first aspect, in one implementation, the setting of the drought algorithm decision specifically includes the following steps:

[0024] Prioritize the implementation of pre-drainage rules that take into account dynamic reserve water levels;

[0025] Simultaneous implementation of rainwater reuse rules;

[0026] If the current water level is lower than the reserve water level, the reservoir is controlled according to the retention and emptying rules to execute the retention and emptying strategies in sequence.

[0027] In combination with the first aspect, in one implementation, if the current water level is lower than the reserve water level, the water reservoir is controlled to sequentially execute the retention and emptying strategies according to the retention and emptying rules, specifically including the following steps:

[0028] If the current water level is lower than the reserve water level and the suspended solids concentration in the pool is greater than the standard suspended solids concentration required by the local recycled water quality standard, the water outlet gate is controlled to close;

[0029] If the current water level is lower than the reserve water level, and the suspended solids concentration in the pool is lower than the standard suspended solids concentration required by the local recycled water quality standard, the outlet gate is controlled to open for rainwater reuse;

[0030] If the current water level is lower than the reserve water level and the accumulated retention time exceeds the maximum allowable retention time, the outlet gate is controlled to open to drain the rainwater in the pool.

[0031] In combination with the first aspect, in one implementation, judging and obtaining real-time weather conditions based on the acquired rainfall monitoring data and weather forecast data specifically includes the following steps:

[0032] If the current rainfall or the flow rate of the rainwater well upstream of the storage tank is greater than 0, it is considered to be a rainy day;

[0033] If the current rainfall and the flow rate of the rainwater well upstream of the storage tank are both less than 0, it is judged to be a drought day.

[0034] In combination with the first aspect, in one implementation, the acquired water quality, flow, water level and rainfall monitoring data are used as a training set, parameters of the set rainy day algorithm decision and the dry day algorithm decision are dynamically optimized, and the rainy day algorithm decision and the dry day algorithm decision after the dynamic optimization of the parameters are obtained, specifically including the following steps:

[0035] Setting initial values ​​for parameter groups in the rainy day algorithm decision and the dry day algorithm decision;

[0036] Using the dynamic database as a training set, the first parameter group in the rainy day algorithm decision is optimized based on the genetic algorithm, and the second parameter group in the dry day algorithm decision is optimized based on the genetic algorithm to obtain the dry day algorithm decision after parameter optimization;

[0037] The dynamic database is updated, and the updated dynamic database is used as a training set to dynamically optimize the parameters of the rainy day algorithm decision and the drought algorithm decision after the parameter optimization, so as to obtain the rainy day algorithm decision and the drought algorithm decision after the parameter optimization;

[0038] According to the real-time weather conditions obtained and based on the basic information of the regulating reservoir system, the regulating reservoir system is controlled to execute the rainy day algorithm decision or the dry day algorithm decision after the parameters of the corresponding weather are dynamically optimized.

[0039] In combination with the first aspect, in one implementation, the method uses the dynamic database as a training set, optimizes the first parameter group in the rainy day algorithm decision based on a genetic algorithm, optimizes the second parameter group in the dry day algorithm decision based on a genetic algorithm, and obtains the dry day algorithm decision after parameter optimization, specifically comprising the following steps:

[0040] Extract rainfall monitoring and weather forecast data, rainwater well flow monitoring data upstream of the storage tank, and water level monitoring data of the storage tank to generate training events;

[0041] For the training of the rainy day algorithm decision, the 24-hour total rainfall depth forecast value at the beginning of each event is used as the total rainfall input, and the empty volume of the regulating reservoir at the beginning of the rainfall is used as the water storage capacity input. By analyzing the flow process, the expected value of the target flow output that can maximize the peak reduction rate is obtained. These training data are input into the fuzzy set calculation formula of the target flow and the first parameter group is adjusted to obtain the first parameter group that minimizes the error between the fuzzy logic calculation value and the expected value of the target flow.

[0042] For the training of drought algorithm decision, the 24-hour total rainfall depth forecast value at the beginning of each event is used as input, and the rainfall-runoff coefficient calculated by the predicted total rainfall and flow is used as the output expected value. These training data are input into the pre-drainage rule expression and the second parameter group is adjusted to obtain the second parameter group that minimizes the error between the calculated value and the expected value of the rainfall-runoff coefficient, and obtain the drought algorithm decision containing the second parameter group.

[0043] In a second aspect, the present application provides a real-time prediction control and dynamic optimization system for a diversion type rainwater storage tank, comprising:

[0044] Rainy day algorithm decision module, used to set the rainy day algorithm decision;

[0045] A drought algorithm decision module, used to set drought algorithm decisions;

[0046] A dynamic database acquisition module is used to acquire a dynamic database, which includes water quality, flow, water level and rainfall monitoring data of the storage tank, weather forecast data and basic information of the storage tank system;

[0047] A weather condition acquisition module is connected to the dynamic database acquisition module for determining and acquiring real-time weather conditions based on the acquired rainfall monitoring data of the storage tank and the flow rate of the rainwater well upstream of the storage tank;

[0048] A parameter dynamic optimization module is communicatively connected with the rainy day algorithm decision module, the drought algorithm decision module and the dynamic database acquisition module, and is used to dynamically optimize the parameters of the set rainy day algorithm decision and drought algorithm decision using the acquired water quality, flow, water level and rainfall monitoring data as a training set, and obtain the rainy day algorithm decision and drought algorithm decision after the dynamic optimization of the parameters;

[0049] The water volume control module, the weather condition acquisition module and the parameter dynamic optimization module are used to control the regulating reservoir system to execute the rainy day algorithm decision or the dry day algorithm decision after the dynamic optimization of the parameters of the corresponding weather according to the acquired real-time weather conditions and the basic information of the regulating reservoir system.

[0050] In conjunction with the second aspect, in one implementation, the rainy day algorithm decision module includes:

[0051] The fuzzy set construction unit is used to construct the fuzzy set of the total rainfall in a session, the water storage capacity of the regulating reservoir and the target flow;

[0052] A fuzzy rule building unit is used to build a fuzzy rule with the total rainfall and the storage capacity of the regulating reservoir as input variables and the target flow rate as output, based on the principle that the larger the rainfall, the larger the target flow rate, and the smaller the storage capacity, the smaller the target flow rate;

[0053] a target flow fuzzy set calculation unit, which is in communication connection with the fuzzy set construction unit and the fuzzy rule establishment unit, and is used to obtain the fuzzy set of the target flow through fuzzy reasoning based on the established fuzzy rules;

[0054] a target flow calculation value acquisition unit, which is in communication connection with the target flow fuzzy set calculation unit and is used to perform defuzzification calculation on the fuzzy set of the target flow by using the maximum membership method to obtain the calculated value of the target flow;

[0055] The water inlet gate opening acquisition unit is communicatively connected with the target flow calculation value acquisition unit, and is used to solve the water inlet gate opening of the regulating reservoir based on the calculated value of the target flow.

[0056] In the third aspect, the present application provides a computer-readable storage medium, on which is stored a real-time prediction control and dynamic optimization program for a diversion type rainwater storage tank. When the real-time prediction control and dynamic optimization program for a diversion type rainwater storage tank is executed by a processor, the steps of the real-time prediction control and dynamic optimization method for a diversion type rainwater storage tank as described above are implemented.

[0057] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0058] The real-time prediction control and dynamic optimization method of the diversion rainwater storage tank provided in the present application can utilize the continuously updated online monitoring and forecast data of the storage tank system, and dynamically optimize the real-time prediction control strategy of rainy days and dry days, which can significantly improve the water quantity, water quality and economic multiple control performance of the rainwater storage tank. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A method flow chart of the real-time prediction control and dynamic optimization method of the diversion type rainwater storage tank in this application;

[0060] Figure 2 A conceptual diagram of the real-time prediction control and dynamic optimization system of the diversion rainwater storage tank in this application;

[0061] Figure 3 A flow chart of real-time prediction control and dynamic optimization of the diversion-type urban rainwater storage tank in this application;

[0062] Figure 4 (a) is an example of the fuzzy logic system control rules of the rainy day algorithm decision module in this application; Figure 4 (b) is an example of the target flow membership function of the fuzzy logic system of the rainy day algorithm decision module in this application; Figure 4 (c) is an example of the total rainfall membership function of the fuzzy logic system of the rainy day algorithm decision module in this application; Figure 4 (d) is an example of the membership function of the water storage capacity of the fuzzy logic system of the rainy day algorithm decision module in this application;

[0063] Figure 5 This is a flow chart of the parameter dynamic optimization module in this application. DETAILED DESCRIPTION

[0064] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0065] The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices. The terms "first", "second" and "third" are used to distinguish different objects, etc., and do not represent a sequence, nor do they limit "first", "second" and "third" to different types.

[0066] In the description of the embodiments of the present application, "exemplary", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary", "for example" 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", "for example" or "for example" is intended to present related concepts in a specific way.

[0067] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; the “and / or” in the text is merely a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, “multiple” refers to two or more than two.

[0068] In some processes described in the embodiments of the present application, multiple operations or steps that appear in a specific order are included, but it should be understood that these operations or steps may not be executed in the order in which they appear in the embodiments of the present application or in parallel, and the sequence number of the operation is only used to distinguish the different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed in sequence or in parallel, and these operations or steps may be combined.

[0069] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0070] First, please refer to Figure 1-Figure 3 The real-time prediction control and dynamic optimization method of the diversion type rainwater storage tank provided in the present application comprises the following steps:

[0071] Step S1: setting a rainy day algorithm decision for regulating the water volume of the storage tank system under rainy conditions;

[0072] Step S2: setting a dry weather algorithm decision for water volume control of the storage tank system under sunny weather conditions;

[0073] Step S3: Acquire a dynamic database, which includes water quality, flow, water level and rainfall monitoring data of the regulating reservoir, weather forecast data and basic information of the regulating reservoir system;

[0074] Step S4: according to the acquired rainfall monitoring data of the regulating reservoir and the flow rate of the rainwater well upstream of the regulating reservoir, determine and obtain the real-time weather conditions;

[0075] Step S5: using the acquired water quality, flow, water level and rainfall monitoring data as a training set, dynamically optimizing the parameters of the set rainy day algorithm decision and the dry day algorithm decision, and obtaining the rainy day algorithm decision and the dry day algorithm decision after the dynamic optimization of the parameters;

[0076] Step S6: Based on the acquired real-time weather conditions and the basic information of the regulating reservoir system, the regulating reservoir system is controlled to execute the rainy day algorithm decision or the dry day algorithm decision after the parameters of the corresponding weather are dynamically optimized.

[0077] The real-time prediction control and dynamic optimization method of the diversion rainwater storage tank provided in the present application can utilize the continuously updated online monitoring data and weather forecast data of the storage tank system, and dynamically optimize the parameters of the real-time prediction control strategy for rainy days and dry days. It can significantly improve the water quantity-water quality-economy multiple control performance of the rainwater storage tank, which is of great significance for urban waterlogging prevention and control and intelligent management of urban rain and floods.

[0078] Figure 3 The middle dashed box (a) is the real-time prediction control process of the diversion urban rainwater storage tank; Figure 3 The dashed box (b) in the middle is the information interaction of the rainy day algorithm decision module; Figure 3 The middle dashed box (c) is the information interaction of the drought algorithm decision module; Figure 3 The dashed box (d) in the middle is the information interaction of the parameter dynamic optimization module;

[0079] Figure 4 (a) is an example of the fuzzy logic system control rules of the rainy day algorithm decision module in this application; Figure 4 (b) is an example of the target flow membership function of the fuzzy logic system of the rainy day algorithm decision module in this application; Figure 4 (c) is an example of the total rainfall membership function of the fuzzy logic system of the rainy day algorithm decision module in this application; Figure 4 (d) is an example of the water storage capacity membership function of the fuzzy logic system of the rainy day algorithm decision module in this application.

[0080] In one embodiment, if Figure 4As shown, the rainy day algorithm decision in step S1 takes the opening degree of the water inlet hole of the regulating reservoir as the control object, takes weakening the outflow peak and the total amount of runoff as the goal, and is set based on the fuzzy logic control system established based on the language rules in the form of "IF-THEN". It is used to describe the fuzzy relationship between the total amount of rainfall and the target flow rate in the specified regulating volume, and dynamically calculate the target flow rate in different rainfall events; Specifically, step S1: setting the rainy day algorithm decision setting is as follows:

[0081] Step S11: construct a fuzzy set of three elements: total rainfall p, storage capacity v of the regulating reservoir, and target flow q, as shown in formula (1):

[0082] Formula (1)

[0083] Among them, Ω p ,Ω v ,Ω q are the domains of total rainfall, water storage capacity of the regulating reservoir, and target flow, respectively; μ(p), μ(v), ​​and μ(q) represent the possibility that the three elements of total rainfall, water storage capacity of the regulating reservoir, and target flow belong to a fuzzy concept, i.e., the degree of membership;

[0084] Among them, for Ω p For {p i |i=1,2,…,n}, set the total rainfall from large to small {P j |j=1,2,…,m j Total m j A vague concept of class;

[0085] Similarly, for Ω v For {v i |i=1,2,…,n} water storage capacity, set from large to small {V k |k=1,2,…,m k Total m k A vague concept of class;

[0086] Similarly, for Ω q For {q i |i=1,2,…,n}, set the target flow from large to small {Q l |l=1,2,…,m l Total m l A vague concept of level.

[0087] According to the actual situation of the storage tank system, the fuzzy concept level quantitative formulas of the three elements are determined respectively (m j 、m k 、m l). Each fuzzy concept corresponds to a membership function, whose shape and distribution are determined by the first parameter group E1={Eμ P , Eμ V , Eμ Q}, it can be triangular, trapezoidal, S-shaped, or Z-shaped, forming a set of function curve clusters distributed on the domain interval. For example, for the total rainfall fuzzy set, its membership function is {μ Pj (p i )| i=1,2,…,n, j=1,2,…, m j}, where the fuzzy set corresponding to the fuzzy concept Pj is {(p1, μ Pj (p1)), (p2, μ Pj (p2)), … , (p n , μ Pj (p n ))}.

[0088] Step S12: According to the principle that the larger the rainfall, the larger the target flow, and the smaller the water storage capacity, the smaller the target flow, a fuzzy rule is established with the total rainfall and the water storage capacity of the regulating reservoir as input variables and the target flow as output, which is used to describe the logical relationship between the fuzzy concepts of the three elements, as shown in formula (2):

[0089] Formula (2)

[0090] in, is the membership function of the total rainfall at the jth level, is the membership function of the k-th level water storage capacity, is the membership function of the l-th level target flow.

[0091] For the control rule "If the total rainfall is , the water storage capacity is , then the target flow is ", according to the membership functions corresponding to these three fuzzy concepts, the fuzzy relationship R is derived, as shown in formula (3) and formula (4):

[0092] Formula (3)

[0093] Formula (4)

[0094] In the formula, R is the fuzzy relationship, For the fuzzy relationship integration of input variables, The fuzzy concept of total rainfall is The membership function of The fuzzy concept of water storage capacity is The membership function of The fuzzy concept of target flow is The membership function of , , are the values ​​of the total rainfall element, water storage capacity element, and target flow element (i=1,2,…,n).

[0095] Step S13: Based on the established fuzzy rules, under the condition of known total rainfall and water storage capacity, the fuzzy set of target flow is obtained through fuzzy reasoning. The fuzzy set calculation formula of target flow is as follows:

[0096] Formula (5)

[0097] In the formula, is the fuzzy set of target traffic, is the fuzzy set of total rainfall, is the fuzzy set of the water storage capacity of the regulating reservoir, A fuzzy relationship.

[0098] Step S14: using the maximum membership method to perform defuzzification calculation on the fuzzy set of the target flow, and obtaining the calculated value of the target flow;

[0099] Step S15: Based on the calculated value of the target flow rate, the opening of the water inlet gate of the regulating reservoir is solved; specifically, the measured monitoring data of the upstream water flow rate is read, and the gate is opened to intercept the part that exceeds the calculated value of the target flow rate to ensure that the outflow of the regulating reservoir system downstream is less than the calculated value of the target flow rate. The Torricelli formula and the well flow formula are used to calculate the gate flow rate of the water inlet gate, and the interpolation method is used to inversely calculate the gate opening of the specified gate flow rate, as shown in Formula (6)-Formula (8):

[0100] Formula (6)

[0101] Formula (7)

[0102] Formula (8)

[0103] in, , , They are the water flow rate at the water inlet gate of the regulating reservoir at time t, the total water flow rate from upstream, and the target flow rate downstream of the regulating reservoir, in L / s; is the gate opening, 0~1; is the calibration factor; is the area of ​​the gate opening at time t, in m2; is the effective head at the front end of the gate hole, in m; d is the orifice diameter, in m.

[0104] Step S1 utilizes the limited storage space to minimize the peak of upstream water inflow. For diversion rainwater storage tanks that are constrained by urban land use planning and have limited water storage capacity, adjusting the working state of the water inlet gate through a dynamic target flow control algorithm can significantly improve the flood peak reduction performance on rainy days.

[0105] In one embodiment, the dry weather algorithm decision in step S2 takes the on / off state of the water pump of the regulating reservoir as the control object, aims to reduce rainy day runoff, reduce the concentration of suspended solids, and increase the rainwater reuse rate, establishes a discriminant based on rainfall forecast and real-time water quantity and water quality status monitoring, and triggers a pre-set "IF-THEN" form mathematical rule, which specifically includes the following steps:

[0106] Step S21: Prioritize the pre-drainage rule considering the dynamic reserve water level, and adjust the water level of the storage tank system in real time in combination with the forecast information of future rainfall; specifically, the time T required to drain the storage tank is p As the standard, when the future T p When there is rainfall, the storage space required to store the rainfall runoff in the next 24 hours is calculated, and the dynamic reserve water level is calculated based on the current water level. If the real-time water level exceeds the reserve water level, the outlet gate of the storage tank is opened to drain water. The pre-drainage rule expression is shown in Equation (9)-Equation (11):

[0107] Formula (9)

[0108] Formula (10)

[0109] Formula (11)

[0110] Among them, H max and H min They are the maximum and minimum water level limits of the storage tank, in m; PP 24,t is the forecast rainfall depth for the next 24 hours at time t, in mm; A S , A T are the upstream catchment area and the average bottom area of ​​the storage tank, respectively, in m 2 ; R is the rainfall-runoff coefficient, which establishes a nonlinear exponential empirical relationship with the forecast rainfall and is determined by the second parameter group E2={α, β}; l t The on / off status of the water pump, 1 is on and 0 is off.

[0111] Step S22: Synchronously execute rainwater reuse rules; specifically, if the suspended solids concentration SS in the pool at the current time t is lower than the standard suspended solids concentration SS required by the local reuse water quality standard ’ , and the water demand at the current moment is ηt When it is greater than 0, the water gate is opened for rainwater reuse;

[0112] Step S23: If the current water level is lower than the reserve water level, the water storage tank is controlled to execute the retention and emptying strategies in sequence according to the retention and emptying rules; specifically, when the solid suspended matter concentration SS in the pool is greater than the solid suspended matter standard concentration SS required by the local reuse water quality standard ’ When SS is less than SS, the water gate is closed and the rainwater is retained in the pool to promote the sedimentation of suspended solids. At the same time, the cumulative retention time is calculated. ’ When there is water demand at the current moment, the water gate is opened for rainwater reuse; when the accumulated retention time exceeds the maximum allowable retention time, the water gate is opened to reduce the water level to the minimum water level limit.

[0113] In one embodiment, the step S3: obtaining a dynamic database is specifically implemented as follows:

[0114] Step S31: installing and arranging monitoring equipment around the regulating reservoir; specifically, connecting the water quantity and quality monitoring equipment such as rain gauge, flow meter, water level meter, SS meter, and the control point sensors of the water inlet gate and water outlet pump in the diversion regulating reservoir system to a programmable logic controller (PLC) to realize the storage and real-time automatic control of online monitoring data;

[0115] Step S32: Monitor and obtain relevant data of the water reservoir system; specifically, the relevant data of the water reservoir system include water quality, flow, water level and rainfall monitoring data of the regulating reservoir, continuously updated weather forecast data and basic information of the regulating reservoir system; more specifically, the water quality, flow, water level and rainfall monitoring data include suspended solid concentration (SS) monitoring data of the regulating reservoir, flow monitoring data of rainwater pipes upstream and downstream of the regulating reservoir, water level and rainfall monitoring data inside the regulating reservoir, and the weather forecast data is hourly rainfall forecast data for the next 24 hours or 72 hours; the basic information of the regulating reservoir system includes basic information such as the size of the regulating reservoir, the aperture of the water inlet gate, and the working capacity of the outlet water pump.

[0116] In one embodiment, the step S4: determining and obtaining real-time weather conditions based on the acquired rainfall monitoring data of the regulating reservoir and the flow rate of the rainwater well upstream of the regulating reservoir, specifically includes the following steps:

[0117] If the current rainfall or the flow rate of the rainwater well upstream of the storage tank is greater than 0, it is considered to be a rainy day;

[0118] On the contrary, if the current rainfall and the flow rate of the rainwater well upstream of the storage tank are both less than 0, it is judged to be a drought day.

[0119] In one embodiment, please refer to Figure 5The step S5: using the acquired water quality, flow, water level and rainfall monitoring data as a training set, dynamically optimizing the parameters of the set rainy day algorithm decision and the drought algorithm decision, and obtaining the rainy day algorithm decision and the drought algorithm decision after the dynamic optimization of the parameters, specifically includes the following steps:

[0120] Step S51: initial value setting: initial value setting of the first parameter group and the dry weather parameter group in the rainy day algorithm decision;

[0121] Step S52, initial parameter optimization: using the dynamic database as a training set, optimizing the first parameter group in the rainy day algorithm decision based on a genetic algorithm, optimizing the second parameter group in the dry day algorithm decision based on a genetic algorithm, and obtaining the dry day algorithm decision after parameter optimization;

[0122] Step S53: Dynamic parameter optimization: updating the dynamic database, taking the updated dynamic database as a training set, dynamically optimizing the parameters of the rainy day algorithm decision and the drought algorithm decision after the parameter optimization, and obtaining the rainy day algorithm decision and the drought algorithm decision after the parameter optimization;

[0123] Step S54: Water flow control in the regulating reservoir: Based on the real-time weather conditions obtained and the basic information of the regulating reservoir system, the water flow control strategy after the parameters of the corresponding weather are dynamically optimized is controlled to be executed; specifically, when the real-time weather obtained is sunny, the sunny day control strategy after the parameters are dynamically optimized is controlled to be executed; when the real-time weather obtained is rainy, the decision of the rainy day algorithm after the dynamic optimization is executed is controlled to be executed.

[0124] Based on step S5, the water volume of the regulating reservoir system is predicted and controlled to achieve the effect of rain and flood control. In addition, a dynamic optimization link of control parameters is added to the prediction and control process, which can continuously absorb new rainfall event information to update the control strategy of the regulating reservoir and obtain more efficient and stable control performance in a changing environment.

[0125] In one embodiment, the step S52: using the dynamic database as a training set, optimizing the first parameter group in the rainy day algorithm decision based on a genetic algorithm, optimizing the second parameter group in the dry day algorithm decision based on a genetic algorithm, and obtaining the dry day algorithm decision after parameter optimization, is specifically implemented as follows:

[0126] Extract rainfall monitoring and weather forecast data, rainwater well flow monitoring data upstream of the storage tank, and water level monitoring data of the storage tank to generate training events;

[0127] For the training of the algorithm decision on rainy days, the 24-hour total rainfall depth forecast value at the beginning of each event is used as the total rainfall input, and the empty volume of the regulating reservoir at the beginning of rainfall is used as the water storage capacity input. By analyzing the flow process, the expected value of the target flow output that can maximize the peak reduction rate is obtained. These training data are input into the target flow back calculation formula and the first parameter group is adjusted to obtain the first parameter group that minimizes the error between the fuzzy logic calculated value and the expected value of the target flow.

[0128] For the training of drought algorithm decision-making, the 24-hour total rainfall depth forecast at the beginning of each event is used as input, and the rainfall-runoff coefficient calculated from the predicted total rainfall and flow is used as the output expected value. These training data are input into the pre-drainage rule expression and the second parameter group is adjusted to obtain the second parameter group that minimizes the error between the calculated value and the expected value of the rainfall-runoff coefficient.

[0129] The above training process is implemented by genetic algorithm. A group of populations representing the first parameter group E1 and the second parameter group E2 are initialized and continuously evolved in each generation through crossover and mutation to generate new parameter groups. When the number of population generations generated reaches its maximum set value or reaches the ideal fitness, the evolution stops. The optimization process finally obtains the best first parameter group E1' and the best second parameter group E2' for adjusting the fuzzy control system and prediction rules. The fitness expression is shown in Equation (12)-Equation (13):

[0130] Formula (12)

[0131] Formula (13)

[0132] Among them, F E1 is the fitness of the first parameter group E1, calculated as the average relative error between the calculated value and the expected value of the target flow rate of N rainfall events; F E2 is the fitness of the second parameter group E2, calculated as the average relative error between the calculated value and the expected value of the rainfall-runoff coefficient in N fields.

[0133] In one embodiment, the step S53: dynamic parameter optimization: updating the dynamic database, taking the updated dynamic database as the training set, dynamically optimizing the parameters of the rainy day algorithm decision and the drought algorithm decision after the parameter optimization, and obtaining the rainy day algorithm decision and the drought algorithm decision after the parameter dynamic optimization, is specifically implemented as follows:

[0134] Use the parameter group obtained from the fitness expression to adjust the real-time control algorithm in the rainy day algorithm decision and the dry day algorithm decision, and record the online monitoring data;

[0135] When a complete rainfall event data is obtained, the dynamic database is updated and new training data is formed, and the optimization steps in the fitness expression are repeated to obtain a gradually optimized first parameter group E1', a gradually optimized second parameter group E2', a rainy day algorithm decision containing E1', and a dry day algorithm decision containing E2', that is, a rainy day algorithm decision and a dry day algorithm decision after dynamic parameter optimization.

[0136] The predictive control process in step S53 is repeated in each control period. The control step size is determined based on the equipment conditions and the catchment area upstream of the regulating reservoir. By combining real-time monitoring and forecast data with control algorithms under different weather conditions, it can be used for continuous control under changing weather conditions.

[0137] In a second aspect, the present application provides a real-time prediction control and dynamic optimization system for a diversion type rainwater storage tank, comprising:

[0138] Rainy day algorithm decision module, used to set the rainy day algorithm decision;

[0139] A drought algorithm decision module, used to set drought algorithm decisions;

[0140] A dynamic database acquisition module is used to acquire a dynamic database, which includes water quality, flow, water level and rainfall monitoring data of the storage tank, weather forecast data and basic information of the storage tank system;

[0141] A weather condition acquisition module is connected to the dynamic database acquisition module for determining and acquiring real-time weather conditions based on the acquired rainfall monitoring data of the storage tank and the flow rate of the rainwater well upstream of the storage tank;

[0142] A parameter dynamic optimization module is communicatively connected with the rainy day algorithm decision module, the drought algorithm decision module and the dynamic database acquisition module, and is used to dynamically optimize the parameters of the set rainy day algorithm decision and drought algorithm decision using the acquired water quality, flow, water level and rainfall monitoring data as a training set, and obtain the rainy day algorithm decision and drought algorithm decision after the dynamic optimization of the parameters;

[0143] The water volume control module, the weather condition acquisition module and the parameter dynamic optimization module are used to control the regulating reservoir system to execute the rainy day algorithm decision or the dry day algorithm decision after the dynamic optimization of the parameters of the corresponding weather according to the acquired real-time weather conditions and the basic information of the regulating reservoir system.

[0144] Among them, the functional implementation of each module in the real-time prediction control and dynamic optimization system of the above-mentioned diversion type rainwater storage tank corresponds to the steps in the embodiment of the real-time prediction control and dynamic optimization method of the above-mentioned diversion type rainwater storage tank, and its functions and implementation process will not be repeated here one by one.

[0145] In one embodiment, the rainy day algorithm decision module includes:

[0146] The fuzzy set construction unit is used to construct the fuzzy set of the total rainfall in a session, the water storage capacity of the regulating reservoir and the target flow;

[0147] A fuzzy rule building unit is used to build a fuzzy rule with the total rainfall and the storage capacity of the regulating reservoir as input variables and the target flow rate as output, based on the principle that the larger the rainfall, the larger the target flow rate, and the smaller the storage capacity, the smaller the target flow rate;

[0148] A target flow fuzzy set calculation unit is communicatively connected with the fuzzy set construction unit and the fuzzy rule establishment unit, and is used for back-calculating and obtaining the fuzzy set of the target flow based on the established fuzzy rules;

[0149] a target flow calculation value acquisition unit, which is in communication connection with the target flow fuzzy set calculation unit and is used to perform defuzzification calculation on the fuzzy set of the target flow by using the maximum membership method to obtain the calculated value of the target flow;

[0150] The water inlet gate opening acquisition unit is communicatively connected with the target flow calculation value acquisition unit, and is used to solve the water inlet gate opening of the regulating reservoir based on the calculated value of the target flow.

[0151] On the third aspect, an embodiment of the present application provides a real-time prediction control and dynamic optimization device for a diversion type rainwater storage tank. The real-time prediction control and dynamic optimization device for a diversion type rainwater storage tank can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0152] The communication interface includes input / output (I / O) interface, physical interface and logical interface, etc., which are used to realize the interconnection of devices inside the real-time prediction control and dynamic optimization device of the diversion type rainwater storage tank, and the interface used to realize the interconnection of the real-time prediction control and dynamic optimization device of the diversion type rainwater storage tank with other devices (such as other computing devices or user devices). The physical interface can be an Ethernet interface, a fiber optic interface, an ATM interface, etc.; the user device can be a display screen (Display), a keyboard (Keyboard), etc.

[0153] The memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0154] The processor may be a general-purpose processor, which may call the real-time prediction control and dynamic optimization program of the diversion type rainwater storage tank stored in the memory, and execute the real-time prediction control and dynamic optimization method of the diversion type rainwater storage tank provided in the embodiment of the present application. For example, the general-purpose processor may be a central processing unit (CPU). The method executed when the real-time prediction control and dynamic optimization program of the diversion type rainwater storage tank is called may refer to the various embodiments of the real-time prediction control and dynamic optimization method of the diversion type rainwater storage tank of the present application, which will not be repeated here.

[0155] In a fourth aspect, an embodiment of the present application also provides a readable storage medium.

[0156] The readable storage medium of the present application stores a real-time prediction control and dynamic optimization program for a diversion type rainwater storage tank, wherein when the real-time prediction control and dynamic optimization program for a diversion type rainwater storage tank is executed by a processor, the steps of the real-time prediction control and dynamic optimization method for a diversion type rainwater storage tank as described above are implemented.

[0157] Among them, the method implemented when the real-time prediction control and dynamic optimization program of the diversion type rainwater storage tank is executed can refer to the various embodiments of the real-time prediction control and dynamic optimization method of the diversion type rainwater storage tank of the present application, and will not be repeated here.

[0158] It should be noted that the serial numbers of the above-mentioned embodiments of the present application are only for description and do not represent the advantages or disadvantages of the embodiments.

[0159] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present application.

[0160] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A real-time prediction control and dynamic optimization method for a diversion rainwater storage tank, characterized in that: The following steps are involved: Set the rainy day algorithm decision; The setting of the rainy day algorithm decision specifically includes the following steps: Construct a fuzzy set of three elements: total rainfall, storage capacity of the reservoir and target flow. According to the principle that the greater the rainfall, the greater the target flow, and the smaller the water storage capacity, the smaller the target flow, a fuzzy rule is established with the total rainfall and the water storage capacity of the regulating reservoir as input variables and the target flow as output. Based on the established fuzzy rules, the fuzzy set of target flow is obtained through fuzzy reasoning under the condition of known total rainfall and water storage capacity; The maximum membership method is used to perform defuzzification calculation on the fuzzy set of the target flow to obtain the calculated value of the target flow; Based on the calculated value of the target flow, solve the opening of the water inlet gate of the storage tank; Set drought algorithm decisions; The setting of the drought algorithm decision specifically includes the following steps: Prioritize the implementation of pre-drainage rules that take into account dynamic reserve water levels; Simultaneous implementation of rainwater reuse rules; If the current water level is lower than the reserve water level, the reservoir is controlled to execute the retention and emptying strategies in sequence according to the retention and emptying rules; Acquire a dynamic database, wherein the dynamic database includes water quality, flow, water level and rainfall monitoring data of the regulating reservoir, weather forecast data and basic information of the regulating reservoir system; According to the acquired rainfall monitoring data of the regulating reservoir and the flow of the rainwater well upstream of the regulating reservoir, the real-time weather conditions are determined; Using the acquired water quality, flow, water level and rainfall monitoring data as training sets, dynamically optimizing the parameters of the set rainy day algorithm decision and drought day algorithm decision, and obtaining the rainy day algorithm decision and drought day algorithm decision after the dynamic optimization of the parameters; The water quality, flow, water level and rainfall monitoring data obtained are used as training sets, and parameters of the set rainy day algorithm decision and drought day algorithm decision are dynamically optimized to obtain the rainy day algorithm decision and drought day algorithm decision after the dynamic optimization of parameters, which specifically includes the following steps: Setting initial values ​​for parameter groups in the rainy day algorithm decision and the dry day algorithm decision; Using the dynamic database as a training set, the first parameter group in the rainy day algorithm decision is optimized based on the genetic algorithm, and the second parameter group in the dry day algorithm decision is optimized based on the genetic algorithm to obtain the dry day algorithm decision after parameter optimization; The dynamic database is updated, and the updated dynamic database is used as a training set to dynamically optimize the parameters of the rainy day algorithm decision and the drought algorithm decision after the parameter optimization, so as to obtain the rainy day algorithm decision and the drought algorithm decision after the parameter optimization; According to the real-time weather conditions obtained and the basic information of the regulating and storage system, the regulating and storage system is controlled to execute the rainy day algorithm decision or the dry day algorithm decision after the parameters of the corresponding weather are dynamically optimized; According to the real-time weather conditions obtained and based on the basic information of the regulating reservoir system, the regulating reservoir system is controlled to execute the rainy day algorithm decision or the dry day algorithm decision after the parameters of the corresponding weather are dynamically optimized.

2. The real-time prediction control and dynamic optimization method of the diversion type rainwater storage tank according to claim 1 is characterized in that: If the current water level is lower than the reserve water level, the water storage tank is controlled to sequentially execute the retention and emptying strategies according to the retention and emptying rules, which specifically includes the following steps: If the current water level is lower than the reserve water level and the suspended solids concentration in the pool is greater than the standard suspended solids concentration required by the local recycled water quality standard, the water outlet gate is controlled to close; If the current water level is lower than the reserve water level, and the suspended solids concentration in the pool is lower than the standard suspended solids concentration required by the local recycled water quality standard, the outlet gate is controlled to open for rainwater reuse; If the current water level is lower than the reserve water level and the accumulated retention time exceeds the maximum allowable retention time, the outlet gate is controlled to open to drain the rainwater in the pool.

3. The real-time prediction control and dynamic optimization method of the diversion type rainwater storage tank according to claim 1 is characterized in that: According to the acquired rainfall monitoring data of the regulating reservoir and the flow of the rainwater well upstream of the regulating reservoir, the real-time weather conditions are determined and obtained, which specifically includes the following steps: If the current rainfall or the flow rate of the rainwater well upstream of the storage tank is greater than 0, it is considered to be a rainy day; If the current rainfall and the flow rate of the rainwater well upstream of the storage tank are both less than 0, it is judged to be a drought day.

4. The real-time prediction control and dynamic optimization method of the diversion type rainwater storage tank according to claim 1 is characterized in that: The method uses the dynamic database as a training set, optimizes the first parameter group in the rainy day algorithm decision based on a genetic algorithm, optimizes the second parameter group in the dry day algorithm decision based on a genetic algorithm, and obtains the dry day algorithm decision after parameter optimization, specifically including the following steps: Extract rainfall monitoring and weather forecast data from the dynamic database, flow monitoring data of rainwater wells upstream of the storage tank, and water level monitoring data of the storage tank to generate training events; For the training of the rainy day algorithm decision, the total rainfall depth forecast value at the beginning of each event is used as the total rainfall input, the empty volume of the regulating reservoir at the beginning of the rainfall is used as the water storage capacity input, and the expected value of the target flow output that can maximize the peak shaving rate is obtained by analyzing the flow process. These training data are input into the fuzzy set calculation formula of the target flow and the first parameter group is adjusted to obtain the first parameter group that minimizes the error between the fuzzy logic calculation value and the expected value of the target flow, and obtain the rainy day algorithm decision containing the first parameter group; For the training of drought algorithm decision, the total rainfall depth forecast value at the beginning of each event is taken as input, and the rainfall-runoff coefficient calculated by the predicted total rainfall and flow is taken as the output expected value. These training data are input into the pre-drainage rule expression and the second parameter group is adjusted to obtain the second parameter group that minimizes the error between the calculated value and the expected value of the rainfall-runoff coefficient, and obtain the drought algorithm decision containing the second parameter group.

5. A system using the real-time prediction control and dynamic optimization method of a diversion type rainwater storage tank as described in any one of claims 1 to 4, characterized in that: include: Rainy day algorithm decision module, used to set the rainy day algorithm decision; A drought algorithm decision module, used to set drought algorithm decisions; A dynamic database acquisition module is used to acquire a dynamic database, which includes water quality, flow, water level and rainfall monitoring data of the storage tank, weather forecast data and basic information of the storage tank system; A weather condition acquisition module is connected to the dynamic database acquisition module for determining and acquiring real-time weather conditions based on the acquired rainfall monitoring data of the storage tank and the flow rate of the rainwater well upstream of the storage tank; A parameter dynamic optimization module is communicatively connected with the rainy day algorithm decision module, the drought algorithm decision module and the dynamic database acquisition module, and is used to dynamically optimize the parameters of the set rainy day algorithm decision and drought algorithm decision using the acquired water quality, flow, water level and rainfall monitoring data as a training set, and obtain the rainy day algorithm decision and drought algorithm decision after the dynamic optimization of the parameters; The water volume control module, the weather condition acquisition module and the parameter dynamic optimization module are used to control the regulating reservoir system to execute the rainy day algorithm decision or the dry day algorithm decision after the dynamic optimization of the parameters of the corresponding weather according to the acquired real-time weather conditions and the basic information of the regulating reservoir system.

6. The system according to claim 5, characterized in that The rainy day algorithm decision module includes: The fuzzy set construction unit is used to construct the fuzzy set of the total rainfall in a session, the water storage capacity of the regulating reservoir and the target flow; A fuzzy rule building unit is used to build a fuzzy rule with the total rainfall and the storage capacity of the regulating reservoir as input variables and the target flow rate as output, based on the principle that the larger the rainfall, the larger the target flow rate, and the smaller the storage capacity, the smaller the target flow rate; A target flow fuzzy set calculation unit is communicatively connected with the fuzzy set construction unit and the fuzzy rule establishment unit, and is used for back-calculating and obtaining the fuzzy set of the target flow based on the established fuzzy rules; a target flow calculation value acquisition unit, which is in communication connection with the target flow fuzzy set calculation unit and is used to perform defuzzification calculation on the fuzzy set of the target flow by using the maximum membership method to obtain the calculated value of the target flow; The water inlet gate opening acquisition unit is communicatively connected with the target flow calculation value acquisition unit, and is used to solve the water inlet gate opening of the regulating reservoir based on the calculated value of the target flow.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a real-time prediction control and dynamic optimization program for a diversion type rainwater storage tank, wherein when the real-time prediction control and dynamic optimization program for a diversion type rainwater storage tank is executed by a processor, the steps of the real-time prediction control and dynamic optimization method for a diversion type rainwater storage tank as described in any one of claims 1 to 4 are implemented.

Images