Urban water supply system water plant joint scheduling method and system

Abstract

The invention belongs to the technical field of urban water supply, and provides an urban water supply system water plant joint scheduling method and system, which accurately controls the water supply amount and water supply pressure of each water plant through a primary optimization scheduling model, ensures the quality of water supply service, can enable a pipe network to operate at a small and gently changing pressure, and improves the water supply efficiency. The resource waste is effectively reduced, and the pipe explosion and leakage risks caused by overlarge water pressure fluctuation are obviously reduced; meanwhile, based on the fact that a current urban water supply system widely adopts a variable-frequency speed regulation pump, and multiple pump stations are used for combined water supply to adapt to the dynamically-changing water use requirement, the optimal rotating speed and the water supply amount of the water pumps in different time periods and the optimal combination of the water pumps are determined through a two-stage optimization scheduling model according to the water use curve rule of a user. The high-efficiency operation potential of the variable-frequency speed regulation pump is fully utilized, so that the consumption of water supply resources and energy is greatly reduced, the water supply cost is saved, and the pump stations are matched more harmoniously through dispatching among the pump stations.

Description

Technical Field

[0001] The present invention belongs to the technical field of urban water supply, and in particular relates to a method and system for joint dispatching of water plants in an urban water supply system. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the rapid development of economy and society, people's quality of life has gradually improved, and the level of urbanization has continued to rise. As a result, people's demand for water resources has also increased. As an important part of water resource allocation, the urban water supply system plays a vital role in energy conservation and consumption reduction, and has received widespread attention. Optimizing the scheduling of water supply pipe networks is an important measure to reduce the waste of water supply system resources.

[0004] The inventor found that although the pipeline facilities used in the current urban water supply system followed strict specifications during design and construction, due to long-term operation, some pipelines have entered the aging stage, and due to the imbalance of water pressure distribution and large water pressure fluctuations in the water supply system, the stability and safety of the pipeline may be affected. In modern urban water supply systems, multi-pump station joint water supply has become a common water supply mode. Pump stations widely use variable frequency speed regulation technology to adapt to the dynamic changes in water supply demand. However, at present, some pump stations have failed to fully utilize the efficient operation potential of variable frequency speed regulation pumps, and there are deficiencies in coordination and cooperation between pump stations, which to a certain extent affects the overall efficiency and energy efficiency of the water supply system. At present, many urban water supply systems still rely on traditional scheduling methods based on manual experience. Although this method meets the water supply demand to a certain extent, due to the lack of refined management and intelligent regulation, the start and stop operations of the pump station water pump are relatively frequent, which not only increases the degree of wear between the pump machinery, but also increases the cost of regular maintenance of the pump. Summary of the invention

[0005] To solve the above problems, the present invention proposes a method and system for joint scheduling of water plants in an urban water supply system. By predicting the water supply of the water plants and using the prediction results to jointly schedule urban water plants, the purpose of reducing energy consumption and saving economy in the water plants is achieved, while increasing the stability of the water supply system.

[0006] According to some embodiments, a first solution of the present invention provides a method for joint scheduling of water plants in a city water supply system, which adopts the following technical solution:

[0007] A method for joint dispatching of water plants in a city water supply system, comprising:

[0008] Obtain basic data of urban pipe networks, as well as water supply data, pressure data and meteorological data;

[0009] Based on the basic data, a hydraulic model of the water supply network is established, and pressure monitoring points are determined based on the hydraulic model of the water supply network; and a water volume prediction model is established based on historical water supply volume data and historical meteorological data; and a water volume prediction result is obtained based on the obtained water volume prediction model and predicted meteorological data;

[0010] According to the determined pressure monitoring points, the water volume prediction results obtained, and the preset first-level optimization scheduling model, the water supply volume and water supply pressure of the water plant that meet the constraint conditions are obtained; wherein the decision variables of the first-level optimization scheduling model are the water supply volume and water supply pressure of each water plant, and the first-level optimization scheduling model aims to minimize the water plant cost of the water supply network;

[0011] According to the water supply volume and water supply pressure determined by the first-level optimization scheduling model and the preset second-level optimization scheduling model, the switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump that meet the constraints are obtained; the decision variables of the second-level optimization scheduling model are the switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump, and the second-level optimization scheduling model aims to minimize the energy consumption of the water plant at the corresponding time.

[0012] As a further technical limitation, the basic data includes pipeline length, material, roughness coefficient and diameter, pump type and characteristic curve, valve type, node elevation, pool elevation and diameter, and geographical location of each hydraulic element.

[0013] As a further technical limitation, branches with nominal diameters below a preset value, pipes with diameters below a preset diameter and some nodes in the hydraulic model of the water supply network are deleted; the booster pump station and all pipes after the booster pump station are deleted; and the water demand of the deleted nodes and pipes is added to the nodes corresponding to the main pipe.

[0014] As a further technical limitation, in the hydraulic model of the water supply network, the locations of the pressure monitoring points are first preliminarily determined based on experience, including low-pressure areas of the network that meet preset conditions, points with the most faults, terminal control points of the network, water supply demarcation lines, areas where the frequency of changes in the network scheduling pressure is higher than a preset frequency, and user areas where the flow rate is higher than a preset flow rate;

[0015] According to the hydraulic model of the water supply network, the pressure difference between any two nodes is solved and the pressure difference matrix is ​​constructed; the shortest distance between any two nodes is solved by the Dijkstra algorithm and the shortest distance matrix is ​​constructed; the fuzzy similarity matrix of water volume influence is solved by the Euclidean distance method; the constraint conditions are determined, including the pressure difference, the shortest distance and the threshold of the fuzzy similarity matrix, as well as the frequent start-stop constraint and the long-term operation constraint; the fuzzy cluster analysis clustering algorithm is used to cluster the network nodes and pre-select the candidate pressure monitoring points in each subclass;

[0016] The pressure monitoring points preliminarily determined by experience and the overlapping points of the candidate pressure monitoring points selected by the fuzzy cluster analysis clustering algorithm are used as the final pressure monitoring point layout plan.

[0017] As a further technical limitation, feature value selection is performed on the historical meteorological data, specifically, each influencing feature is normalized; the importance of the feature is evaluated by calculating the impact of the feature on the model accuracy in each decision tree; based on the result of the feature importance evaluation, the feature that contributes the most to the model prediction is selected as the input of the water volume prediction model; the pre-trained water volume prediction model is used to predict the water demand in a preset time period in the future, specifically, the original time series data is decomposed into an approximate sequence and multiple detail sequences by wavelet decomposition; the approximate sequence is fitted and predicted by a long short-term memory network; the detail sequence is fitted and predicted by an XGBoost model; the predicted values ​​obtained by predicting the approximate sequence and the detail sequence are added and summed to obtain the final prediction result.

[0018] As a further technical limitation, the optimization scheduling process of the first-level optimization scheduling model includes: predicting the future hourly water supply of the city based on the water volume prediction model; taking the hourly water supply and water supply pressure of each water plant as decision variables, using a genetic algorithm improved by simulated annealing to search for optimization, and obtaining a feasible solution based on a preset objective function; obtaining the pressure value at the corresponding moment based on the feasible solution, and judging whether the constraint conditions are met, if not, re-iterating until the constraint requirements are met; the optimization scheduling process of the second-level optimization scheduling model includes: obtaining the hourly optimal water supply and water supply pressure of the water plant based on the first-level optimization scheduling model; taking the switch combination of the pump unit of the pump station and the speed ratio of the speed regulating pump as decision variables, using a genetic algorithm improved by simulated annealing to search for optimization, and obtaining a feasible solution based on a preset objective function expression; the obtained feasible solution is combined with relevant constraint conditions to judge whether the requirements are met, if not, returning to re-solve until the constraint requirements are met.

[0019] According to some embodiments, the second solution of the present invention provides a water plant joint dispatching system for a city water supply system, which adopts the following technical solution:

[0020] A water plant joint dispatching system for an urban water supply system, comprising:

[0021] A data acquisition module configured to obtain basic data of the urban pipe network, as well as water supply data, pressure data and meteorological data;

[0022] A pipe network modeling module, which is configured to establish a hydraulic model of the water supply pipe network according to the basic data, and determine the pressure monitoring point according to the hydraulic model of the water supply pipe network;

[0023] A water volume prediction module is configured to establish a water volume prediction model based on historical water supply data and historical meteorological data; and obtain a water volume prediction result based on the obtained water volume prediction model and predicted meteorological data;

[0024] A first optimization module is configured to obtain the water supply volume and water supply pressure of the water plant that meet the constraint conditions according to the water volume prediction results obtained from the determined pressure monitoring points and the preset first-level optimization scheduling model; wherein the decision variables of the first-level optimization scheduling model are the water supply volume and water supply pressure of each water plant, and the first-level optimization scheduling model aims to minimize the water plant cost of the water supply network;

[0025] The second optimization module is configured to obtain the switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump that meet the constraints according to the water supply volume and water supply pressure determined by the first-level optimization scheduling model and the preset second-level optimization scheduling model; the decision variables of the second-level optimization scheduling model are the switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump, and the second-level optimization scheduling model aims to minimize the energy consumption of the water plant at the corresponding time.

[0026] According to some embodiments, a third solution of the present invention provides a computer-readable storage medium, which adopts the following technical solution:

[0027] A computer-readable storage medium stores a program, which, when executed by a processor, implements the steps of the water plant joint scheduling method for a city water supply system as described in the first solution of the present invention.

[0028] According to some embodiments, a fourth solution of the present invention provides an electronic device, which adopts the following technical solution:

[0029] An electronic device comprises a memory, a processor and a program stored in the memory and running on the processor. When the processor executes the program, the steps in the joint dispatching method of water plants in a city water supply system as described in the first solution of the present invention are implemented.

[0030] According to some embodiments, a fifth solution of the present invention provides a computer program product, which adopts the following technical solution:

[0031] A computer program product includes software codes, wherein the program in the software codes executes the steps in the method for joint scheduling of water plants in a city water supply system as described in the first solution of the present invention.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] The present invention considers that pipe burst and leakage are key factors affecting urban water supply safety and water quality. Through the first-level optimization scheduling model, the water supply volume and water supply pressure of each water plant are accurately controlled to ensure the quality of water supply services. At the same time, the pipe network can be operated at a relatively small and smoothly changing pressure, which effectively reduces resource waste and significantly reduces the risk of pipe burst and leakage caused by excessive water pressure fluctuations. At the same time, based on the current widespread use of variable frequency speed regulating pumps in urban water supply systems, and the joint water supply through multiple pumping stations to adapt to the dynamically changing water demand, the present invention uses a second-level optimization scheduling model to determine the optimal speed, water supply volume and optimal combination of water pumps in different time periods according to the user water use curve. The high-efficiency operation potential of the variable frequency speed regulating pump is fully utilized, thereby greatly reducing the consumption of water supply resources and energy, saving water supply costs, and making the coordination between pumping stations more coordinated through the scheduling between pumping stations.

[0034] The present invention scientifically dispatches pump stations and pipe networks by optimizing the dispatching model, which can significantly reduce the number of water pump starts and stops based on experience in the past, thereby reducing the degree of wear and maintenance costs between water pump machines. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings in the specification that constitute a part of this embodiment are used to provide a further understanding of this embodiment. The schematic embodiments of this embodiment and their descriptions are used to explain this embodiment and do not constitute improper limitations on this embodiment.

[0036] Figure 1 This is the overall technical roadmap in the first embodiment of the present invention;

[0037] Figure 2 A flow chart for constructing a water volume prediction model based on wavelet decomposition and combination in Embodiment 1 of the present invention;

[0038] Figure 3 This is a flow chart of microscopic model building in Embodiment 1 of the present invention;

[0039] Figure 4 This is the QH curve of the water pump in Example 1 of the present invention. DETAILED DESCRIPTION

[0040] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0041] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0042] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0043] In the present invention, terms such as "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "side", "bottom", etc. indicate directions or positional relationships based on the directions or positional relationships shown in the accompanying drawings. They are relational words determined only for the convenience of describing the structural relationships of the various parts or elements of the present invention, and do not specifically refer to any part or element in the present invention and should not be understood as limitations on the present invention.

[0044] In the present invention, terms such as "fixed connection", "connected", "connection", etc. should be understood in a broad sense, indicating that it can be fixedly connected, integrally connected or detachably connected; it can be directly connected or indirectly connected through an intermediate medium. For relevant scientific research or technical personnel in this field, the specific meanings of the above terms in the present invention can be determined according to specific circumstances, and they cannot be understood as limitations on the present invention.

[0045] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0046] Embodiment 1

[0047] In view of the problem that most urban water supply systems currently still rely on traditional manual experience for scheduling and cannot determine the reasonable operating conditions of pumps based on actual flow demand, resulting in low working efficiency and high energy consumption of water plants, Example 1 of the present invention introduces a joint scheduling method for water plants in an urban water supply system. First, a microscopic modeling of the urban water supply network is performed, and then the urban water demand is predicted hour by hour. Finally, the urban water plants are jointly scheduled based on the predicted results.

[0048] A method for joint dispatching of water plants in a city water supply system, comprising:

[0049] S1. Establishment and verification of hydraulic model of water supply network:

[0050] S1.1. Acquisition of basic data of pipeline network and processing of outliers.

[0051] Optionally, on a permitted and legal basis, obtain the static attributes of the water network from the urban water department's water supply network geographic information system (GIS), including pipeline length, material, roughness coefficient and diameter, pump type and characteristic curve, valve type, node elevation, pool elevation and diameter, and the geographical location of each hydraulic component.

[0052] Since the data obtained from the GIS system may contain outliers that need to be processed, the outliers are identified and marked through the ArcGIS raster calculator and ArcPy tools, and then these values ​​are repaired or replaced using interpolation technology to ensure the accuracy of the data.

[0053] S1.2. Data import and pipeline network simplification.

[0054] After outlier processing, the basic data is converted into an .inp file and imported into conventional software to establish a water supply network hydraulic model, which is a microscopic model. There are a large number of pipes and nodes in the preliminary water supply network hydraulic model. The excessive number of these pipes and nodes will lead to slow hydraulic calculations and reduce the efficiency of the network model. Therefore, the preliminary water supply network hydraulic model is simplified. The simplification steps include: deleting branches below DN200, small-diameter pipes and unnecessary nodes; deleting the booster pump station and all pipes after the booster pump station; and accumulating the water demand of the deleted nodes and pipes to the corresponding nodes of the main pipeline.

[0055] S1.3. Selection of pressure monitoring points.

[0056] Optionally, use fuzzy cluster analysis (FCM) combined with empirical methods to determine the appropriate pressure monitoring point layout plan, and select the most representative points and the most unfavorable points in the pipeline network as pressure monitoring points. The specific process is as follows:

[0057] S1.3.1. First, based on the mature operation and management experience accumulated by the urban water supply company and management department for many years, the location of the pressure monitoring point is preliminarily determined. These locations usually include key areas such as low-pressure areas of the pipeline network, the most unfavorable points, the terminal control points of the pipeline network, the water supply demarcation line, sensitive areas of pipeline network dispatching pressure changes, large-flow users, and important government agencies; for example, low-pressure areas of the pipeline network that meet the preset conditions, points with the most faults, terminal control points of the pipeline network, water supply demarcation lines, areas where the frequency of changes in pipeline network dispatching pressure is higher than the preset frequency, and user areas where the flow rate is higher than the preset flow rate, etc.

[0058] S1.3.2. According to the hydraulic model of the water supply network, solve the pressure difference between any two nodes and construct a pressure difference matrix; use the Dijkstra algorithm to solve the shortest distance between any two nodes and construct a shortest distance matrix.

[0059] S1.3.3. Use the Euclidean distance method to solve the water volume impact fuzzy similarity matrix and provide input for the FCM clustering algorithm.

[0060] S1.3.4. Determine the constraints of the optimization layout model, including the thresholds of pressure difference, shortest distance and fuzzy similarity matrix, as well as frequent start-stop constraints and long-time operation constraints.

[0061] S1.3.5. Use the FCM clustering algorithm to cluster the pipe network nodes and pre-select candidate pressure monitoring points in each sub-class. The objective function of the FCM algorithm is m Defined as:

[0062]

[0063] Among them, N is the number of samples (number of network nodes), K is the number of clusters (number of subclasses), and U ij is the sample point x i With cluster center c j The membership degree, m is the fuzzy index (m>1), d ij is the sample point x i With cluster center c j The square of the Euclidean distance, the membership update formula is:

[0064]

[0065] The cluster center update formula is:

[0066]

[0067] S1.3.6. After selecting the candidate pressure monitoring points, combine them with the points selected based on the empirical method in step S1.3.1 to finally determine the optimal layout plan for the pressure monitoring points.

[0068] S1.4. Model accuracy verification.

[0069] Based on the selected pressure detection points, the pressure collection values ​​​​obtained by the micro-model are compared with those obtained by the pipeline SCADA system to determine whether the accuracy of the micro-model meets the requirements. The specific accuracy requirements are that the error between the calculated pressure values ​​and the measured values ​​of all verification points should be less than 4m, the calculation error of 4 / 5 of the data should be less than 2m, and the calculation error of 1 / 2 of the data should be less than 1m.

[0070] S1.5. Model modification.

[0071] In order to solve the accuracy problem caused by the static properties of the pipeline network, the pipe segment data in the conventional software is compared with the actual pipeline network data to identify whether there are any differences. Since the expansion or renovation of the pipeline network may cause changes in information such as the location, material and diameter of the pipeline, it is necessary to update the key data such as the diameter and material of the pipeline network until the model meets the error requirements between the predicted pressure and the actual pressure. The loss of accuracy caused by model simplification is unavoidable to a certain extent. For areas with significant errors, the pipeline network model before simplification can be appropriately restored to improve the accuracy of the simulation.

[0072] S2. Establishment of water volume prediction model:

[0073] S2.1. Acquisition of water volume data and meteorological data.

[0074] Optionally, obtain the water plant's historical water supply data from the water department; obtain the city's historical meteorological data and forecast meteorological data from the meteorological platform.

[0075] S2.2. Outlier identification and data filling. First, use the Z-score method based on statistical principles to filter out outliers in the data. The specific formula is:

[0076]

[0077] Here, x represents a single observation, μ represents the mean of the sample in which the observation is located, and σ represents the standard deviation of the sample.

[0078] After filtering out the outliers, use linear interpolation to fill in the removed outliers and missing values. Use the data values ​​of the two days before and two days after the missing point to calculate the missing value. The specific calculation formula is:

[0079]

[0080] Among them, the missing point is t, the known points of the first two days are t-2 and t-1, and the known points of the last two days are t+1 and t+2.

[0081] S2.3. Eigenvalue selection.

[0082] Optionally, after data processing is completed, you need to select the input variables of the model. The specific process is as follows:

[0083] S2.3.1. Construct a random forest model consisting of multiple decision trees, where each tree is trained based on a different random subsample of the original data and a subset of features.

[0084] S2.3.2. Normalize each influencing feature to compare the relative importance of different features.

[0085] S2.3.3. Evaluate the importance of features by calculating their impact on model accuracy in each decision tree.

[0086] S2.3.4. Based on the results of feature importance assessment, select the features that contribute most to model prediction as the input of the water volume prediction model.

[0087] S2.4. Water volume forecast.

[0088] Based on the processed data and the selected feature variables, the WT-XGBoost-LSTM model is used to predict the water demand in the next 24 hours. The specific process is as follows:

[0089] S2.4.1. Use wavelet decomposition to decompose the original time series data into an approximate sequence and multiple detail sequences.

[0090] S2.4.2. Use LSTM network to fit and predict the approximate sequence.

[0091] S2.4.3. Use the XGBoost model to fit and predict the detail sequence.

[0092] S2.4.4. The predicted values ​​obtained by the approximate sequence and the detailed sequence prediction are added together to obtain the final prediction result.

[0093] S3. Establishment and solution of optimization scheduling model:

[0094] Optionally, this embodiment provides a water plant joint scheduling method, including the establishment and solution of a primary optimization scheduling model and a secondary optimization scheduling model. The establishment of the primary optimization scheduling model: taking the water supply and water supply pressure of each water plant in the water supply system as decision variables, taking inequality functions such as the water supply of the water plant, outlet pressure, and pressure at the pressure measuring point as constraints, and taking minimizing the water supply cost of the water plant as the objective function, a primary optimization scheduling model is established. Solution of the primary optimization scheduling model: After the primary optimization scheduling model is built, the primary scheduling model is solved using a genetic algorithm improved by simulated annealing to obtain the optimal water supply and water supply pressure of the water plant. Fitting the characteristic curve of the water pump: Use the quadratic curve method to fit the characteristic curve of the water pump. First, use a quadratic equation to describe the characteristic curve relationship of the water pump and determine the unknown coefficients; then use the least squares method to determine the coefficients in the quadratic equation. The establishment of the secondary optimization scheduling model: based on the water supply and water supply pressure of the water plant reallocated by the first-level optimization scheduling, the switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump are used as decision variables, and the relevant inequality constraint functions such as the water plant outlet pressure, water plant water supply, speed ratio, and frequent start and stop constraints are used as constraints, with the goal of minimizing the total power consumption during the scheduling time period, to establish a secondary optimization scheduling model. Solution of the secondary optimization scheduling model: After the secondary optimization scheduling model is built, the genetic algorithm improved by simulated annealing is used to solve the secondary scheduling model to obtain the optimal switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump. Specifically:

[0095] S3.1. Establishment of the first-level optimization scheduling model.

[0096] S3.1.1. Determine the decision variables.

[0097] The decision variables are the independent variables in the optimization scheduling model. Changes in the decision variables will affect the output results of the model. The decision variables of the first-level optimization scheduling model are the water supply and water supply pressure of each water plant.

[0098] S3.1.2. Establish the objective function.

[0099] The objective function is a mathematical expression that reflects the change of a certain indicator in the pipe network through decision variables. Usually, in the decision-making of pipe network optimization scheduling, the lower the value, the better. The first-level optimization scheduling usually takes the lowest water plant cost of the water supply pipe network as the objective function. The goal is to minimize the water plant cost. The specific function expression is shown in the following formula:

[0100] mincost=min(cost1+cost2)

[0101] Among them, cost1 represents the water production cost, cost2 represents the energy consumption cost of the water plant, and the water production cost function expression and the network energy consumption cost function expression are shown as follows:

[0102]

[0103] Among them, n represents different water supply periods, m represents the number of water plants, Q ji represents the water supply of water plant i in period j, C ji It represents the unit water production cost of water plant i in time period j.

[0104]

[0105] Among them, n represents different water supply periods, m represents the number of water plants, e represents the electricity cost per unit of electricity, a represents the conversion coefficient, Q ji represents the water supply of water plant i in period j, P ji Represents the water supply pressure of water plant i in period j.

[0106] The final objective function of the first-level optimization scheduling model is shown as follows:

[0107]

[0108] S3.1.3. Determine the constraints.

[0109] In the optimal scheduling of water supply networks, constraints are the restrictions on decision variables required to meet the daily water use of the city, such as the upper and lower limits of water supply volume and water supply pressure of each water plant. The specific constraints are as follows:

[0110] Water supply constraint. The sum of the hourly water supply of each water plant should be equal to the total hourly water supply of the city in the water supply forecast, and the hourly water supply of each water plant should be less than the maximum hourly water supply and greater than the minimum hourly water supply.

[0111]

[0112] Among them, Q i represents the hourly water supply of the ith water plant, Q represents the total hourly water supply of the city, and They represent the minimum and maximum water supply of the ith water plant respectively.

[0113] Pressure constraints. Including water plant outlet pressure constraints and pressure measuring point pressure constraints. The pressure value is obtained by the constructed micro-hydraulic model. The pressure of each water plant outlet (pressure measuring point) should be less than the maximum outlet (pressure measuring point) pressure and greater than the minimum outlet (pressure measuring point) pressure.

[0114]

[0115] in, is the minimum pressure at the outlet (pressure measuring point) of the i-th water plant in the j-th time period, is the maximum pressure at the outlet (pressure measuring point) of the i-th water plant in the j-th time period, P ij is the pressure at the outlet (pressure measuring point) of the i-th water plant in the j-th time period.

[0116] S3.2. Solution of the first-level optimization scheduling model.

[0117] Optionally, predict the future hourly water supply of the city based on the water quantity prediction model; take the hourly water supply and water supply pressure of each water plant as decision variables, use the genetic algorithm improved by simulated annealing to find the optimal solution, and obtain the feasible solution of the expression according to the established objective function expression; input the obtained solution into the established microscopic model to obtain the pressure value at the corresponding moment, and judge whether the relevant constraints are met; if not, return to iterate again until the constraints are met.

[0118] S3.3. Fitting of water pump characteristic curve.

[0119] In describing the performance parameters of a water pump, flow rate (Q) is usually selected as the independent variable, and head (H), shaft power (N) and efficiency (η) are selected as the dependent variables to fit the water pump characteristic curve. The quadratic curve method is used, which is simple to operate and has high accuracy, to fit the characteristic curve.

[0120] S3.3.1. Fitting of the characteristic curve of the constant speed pump.

[0121] QH curve:

[0122]

[0123] In the formula, H N is the head of the pump at rated speed, H0 is the virtual head of the pump, Q N is the flow rate at the rated speed of the pump, and S0 is the pipe resistance coefficient.

[0124] QN curve:

[0125]

[0126] Where N N is the shaft power of the pump at rated speed, a0, a1, a2 are the coefficients to be determined in the equation.

[0127] Q-η curve:

[0128]

[0129] Where η N is the efficiency of the pump at rated speed, b0, b1, b2 are the coefficients to be determined in the equation.

[0130] S3.3.2. Fitting of the speed regulating pump characteristic curve.

[0131] According to the similarity law, the characteristic curve of the water pump at any speed can be obtained.

[0132] Pump similarity curve:

[0133]

[0134] Where Q, H, and N are the flow rate, head, and shaft power of the pump at the speed ratio S, respectively.

[0135] By combining the above equation with the equation at the rated speed of the water pump, the characteristic curve of the water pump at the speed ratio S can be obtained.

[0136] QH curve:

[0137] H=H0S 2 +S0Q 2

[0138] QN curve:

[0139] N=a0S 3 +a1S 2 Q+a2S 2

[0140] Q-η curve:

[0141] η=b0+b1S -1 Q+b2S -2 Q 2

[0142] The performance data of the water pump under different working conditions, including Q, H, N and η, are collected, and the coefficients in the quadratic equation are determined using the least squares method to obtain the characteristic curve of the water pump.

[0143] S3.4. Establishment of the secondary optimization scheduling model.

[0144] S3.4.1. Determine the decision variables.

[0145] The decision variables of the two-level optimization scheduling model are the switch combination of the pump units in the pump station and the speed ratio of the speed regulating pump.

[0146] S3.4.2. Establish the objective function.

[0147] The secondary optimization scheduling aims to minimize the energy consumption of the water plant at the corresponding time. The specific function expression is as follows:

[0148]

[0149] Where n is the total number of fixed speed pumps in the water plant, m is the total number of speed regulating pumps in the water plant, and c is i 、c j Indicates the decision of the pump, 1 and 0 represent opening and closing respectively, N i 、N j The distribution column shows the power of the fixed speed pump and the power of the variable speed pump.

[0150] The power function expression of the constant speed pump is shown as follows:

[0151]

[0152] Among them, a i0 、a i1 、a i2 represents the coefficient of the ith constant speed pump, Q i Indicates the flow rate of the pump at rated speed.

[0153] The power function expression of the speed regulating pump is as follows:

[0154]

[0155] Among them, b j0 , b j1 , b j2 is the coefficient of the speed regulating pump, S j is the speed ratio, Q is the flow rate of the water pump at the corresponding speed.

[0156] The final objective function of the two-level optimization scheduling model is as follows:

[0157]

[0158] S3.4.3. Determine the constraints.

[0159] Water supply constraint: The sum of the water supply of each parallel pump in the water plant should be equal to the target flow rate of the water plant at this moment.

[0160]

[0161] Among them, Q ij represents the water supply of the i-th water pump at time j, Qj Represents the target flow rate of the water plant in period j.

[0162] Pressure constraint: The pressure of the parallel pumps in the water plant should be less than the maximum outlet pressure and greater than the minimum outlet pressure.

[0163]

[0164] in, is the minimum pressure at the water outlet of the water plant in the jth time period, is the maximum pressure at the water plant outlet in the jth time period, P j is the pressure at the water plant outlet in the jth time period.

[0165] S3.4.4, speed ratio constraint of speed regulating pump.

[0166] The speed of the speed regulating pump in the water plant should not be set too high or too low. Its speed ratio should be greater than or equal to the lower limit of the speed regulating ratio of the speed regulating pump, and less than or equal to the upper limit of the speed regulating ratio of the speed regulating pump.

[0167] S min ≤S i ≤S max

[0168] Among them, S min Indicates the lower limit of the speed ratio of the speed regulating pump (generally 70%), S max Indicates the upper limit of the speed ratio of the speed regulating pump (generally taken as 1), S i Represents the speed ratio of the i-th speed regulating pump.

[0169] Frequent start and stop constraints. Frequent start and stop of the pump not only affects energy consumption, but also affects its life. It is set that the number of times the pump is turned on within 24 hours in a scheduling cycle should not exceed 4 times.

[0170] Efficient operation area constraints. Figure 4 As shown, curves CA and DB are parabolas of similar working conditions, curve AB is the QH curve of the water pump at rated power, curve CD is the QH curve of the water pump at minimum speed, and the area enclosed by ABCD is the efficient operation area of ​​the water pump.

[0171] The efficient operation area constraint of the fixed speed pump is:

[0172] Q A ≤Q i ≤Q B

[0173] The efficient operation area constraint of the speed regulating pump is:

[0174] Q jmin ≤Q j ≤Q jmax

[0175]

[0176] Among them, S x and H x represent the head H of the speed-regulating pump at the rotational speed of S x . x

[0177] S3.5. Solution of the secondary optimal scheduling model.

[0178] Based on the primary optimal scheduling model, obtain the optimal water supply volume and water supply pressure of the water plant in real time; take the switch combination of the pump units in the pumping station and the speed regulation ratio of the speed-regulating pump as decision variables, use the genetic algorithm improved by simulated annealing for optimization, and obtain the feasible solutions of the established objective function expression according to the obtained solutions; combine the relevant constraint conditions to judge whether the requirements are met; if not, return to re-solve until the constraint requirements are met.

[0179] The basic process of the genetic algorithm improved by simulated annealing is as follows:

[0180] Parameter determination: Determine the population mutation probability P m , the population crossover probability P c , the number of cooling iterations, the maximum number of iterations N, and the initial temperature T0 and the cooling temperature T f .

[0181] Optimal individual selection: Initialize the population and screen out the optimal fitness value F = f min and the corresponding optimal individual.

[0182] Judge the convergence of the algorithm: If the algorithm converges and the optimal value and the optimal individual meet the conditions, then end. Otherwise, continue to operate until convergence.

[0183] Isothermal: Each individual will undergo the isothermal operation in simulated annealing, aiming to obtain the minimum fitness value f m ' in and the optimal individual in the new population; if f m ' in < f min , then f m ' in will update the fitness value F.

[0184] When k < N, perform the cooling operation, and the steps will return to 3; otherwise, end the calculation to obtain the optimal value.

[0185] ​This embodiment considers that pipe burst and leakage are key factors affecting urban water supply safety and water quality. Through the first-level optimization scheduling model, the water supply volume and water supply pressure of each water plant are accurately controlled to ensure the quality of water supply services. At the same time, the pipe network can be operated at a relatively small and smoothly changing pressure, which effectively reduces resource waste and significantly reduces the risk of pipe burst and leakage caused by excessive water pressure fluctuations. At the same time, based on the fact that variable frequency speed regulating pumps are widely used in the current urban water supply system, and water is supplied by multiple pumping stations to adapt to the dynamically changing water demand, the present invention determines the optimal speed, water supply volume and optimal combination of water pumps in different time periods according to the user water use curve through the second-level optimization scheduling model. The efficient operation potential of the variable frequency speed regulating pump is fully utilized, thereby greatly reducing the consumption of water supply resources and energy, saving water supply costs, and making the coordination between pumping stations more coordinated through the scheduling between pumping stations. This embodiment uses the optimization scheduling model to scientifically schedule pumping stations and pipe networks, which can significantly reduce the number of pump starts and stops based on experience in the past, thereby reducing the wear and maintenance costs between pump machinery.

[0186] Embodiment 2

[0187] The second embodiment of the present invention introduces a water plant joint dispatching system for a city water supply system.

[0188] A water plant joint dispatching system for an urban water supply system, comprising:

[0189] A data acquisition module configured to obtain basic data of the urban pipe network, as well as water supply data, pressure data and meteorological data;

[0190] A pipe network modeling module, which is configured to establish a hydraulic model of the water supply pipe network according to the basic data, and determine the pressure monitoring point according to the hydraulic model of the water supply pipe network;

[0191] A water volume prediction module is configured to establish a water volume prediction model based on historical water supply data and historical meteorological data; and obtain a water volume prediction result based on the obtained water volume prediction model and predicted meteorological data;

[0192] A first optimization module is configured to obtain the water supply volume and water supply pressure of the water plant that meet the constraint conditions according to the water volume prediction results obtained from the determined pressure monitoring points and the preset first-level optimization scheduling model; wherein the decision variables of the first-level optimization scheduling model are the water supply volume and water supply pressure of each water plant, and the first-level optimization scheduling model aims to minimize the water plant cost of the water supply network;

[0193] The second optimization module is configured to obtain the switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump that meet the constraints according to the water supply volume and water supply pressure determined by the first-level optimization scheduling model and the preset second-level optimization scheduling model; the decision variables of the second-level optimization scheduling model are the switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump, and the second-level optimization scheduling model aims to minimize the energy consumption of the water plant at the corresponding time.

[0194] The detailed steps are the same as the joint dispatching method of water plants in the urban water supply system provided in Example 1, and will not be repeated here.

[0195] Embodiment 3

[0196] Embodiment 3 of the present invention provides a computer-readable storage medium.

[0197] A computer-readable storage medium stores a program, which, when executed by a processor, implements the steps of the water plant joint scheduling method for a city water supply system as described in the first embodiment of the present invention.

[0198] The detailed steps are the same as the joint dispatching method of water plants in the urban water supply system provided in Example 1, and will not be repeated here.

[0199] Embodiment 4

[0200] A fourth embodiment of the present invention provides an electronic device.

[0201] An electronic device comprises a memory, a processor and a program stored in the memory and running on the processor, wherein when the processor executes the program, the steps in the method for joint scheduling of water plants in a city water supply system as described in the first embodiment of the present invention are implemented.

[0202] The detailed steps are the same as the joint dispatching method of water plants in the urban water supply system provided in Example 1, and will not be repeated here.

[0203] Embodiment 5

[0204] Embodiment 5 of the present invention provides a computer program product.

[0205] A computer program product includes software codes, wherein the program in the software codes executes the steps in the method for joint scheduling of water plants in a city water supply system as described in the first embodiment of the present invention.

[0206] The detailed steps are the same as the joint dispatching method of water plants in the urban water supply system provided in Example 1, and will not be repeated here.

[0207] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0208] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0209] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0210] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0211] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0212] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0213] The above description is only a preferred embodiment of the present embodiment and is not intended to limit the present embodiment. For those skilled in the art, the present embodiment may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present embodiment shall be included in the protection scope of the present embodiment.

Claims

1. A method for joint dispatching of water plants in an urban water supply system, characterized in that: include: Obtain basic data of urban pipe networks, as well as water supply data, pressure data and meteorological data; Based on the basic data, a hydraulic model of the water supply network is established, and pressure monitoring points are determined based on the hydraulic model of the water supply network; and a water volume prediction model is established based on historical water supply volume data and historical meteorological data; and a water volume prediction result is obtained based on the obtained water volume prediction model and predicted meteorological data; According to the determined pressure monitoring points, the water volume prediction results obtained, and the preset first-level optimization scheduling model, the water supply volume and water supply pressure of the water plant that meet the constraint conditions are obtained; wherein the decision variables of the first-level optimization scheduling model are the water supply volume and water supply pressure of each water plant, and the first-level optimization scheduling model aims to minimize the water plant cost of the water supply network; According to the water supply volume and water supply pressure determined by the first-level optimization scheduling model and the preset second-level optimization scheduling model, the switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump that meet the constraints are obtained; the decision variables of the second-level optimization scheduling model are the switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump, and the second-level optimization scheduling model aims to minimize the energy consumption of the water plant at the corresponding time.

2. The method for joint dispatching of water plants in a city water supply system according to claim 1, characterized in that: The basic data include pipeline length, material, roughness coefficient and diameter, water pump type and characteristic curve, valve type, node elevation, water tank elevation and diameter, and geographical location of each hydraulic element.

3. The method for joint dispatching of water plants in a city water supply system according to claim 1, characterized in that: Delete branches with nominal diameters below a preset value, pipes with diameters below a preset diameter and some nodes in the hydraulic model of the water supply network; delete the booster pump station and all pipes after the booster pump station; and add the water demand of the deleted nodes and pipes to the nodes corresponding to the main pipe.

4. The method for joint dispatching of water plants in a city water supply system according to claim 1, characterized in that: In the water supply network hydraulic model, the locations of pressure monitoring points are first determined based on experience, including low-pressure areas of the network that meet preset conditions, points with the most faults, terminal control points of the network, water supply demarcation lines, areas where the frequency of changes in the network scheduling pressure is higher than the preset frequency, and user areas where the flow rate is higher than the preset flow rate; According to the hydraulic model of the water supply network, the pressure difference between any two nodes is solved and the pressure difference matrix is ​​constructed; the shortest distance between any two nodes is solved by the Dijkstra algorithm and the shortest distance matrix is ​​constructed; the fuzzy similarity matrix of water volume effect is solved by the Euclidean distance method; Determine the constraints, including the pressure difference, the shortest distance, and the threshold of the fuzzy similarity matrix, as well as the frequent start-stop constraints and the long-time operation constraints; cluster the pipe network nodes using the fuzzy cluster analysis clustering algorithm, and pre-select the candidate pressure monitoring points in each subclass; The pressure monitoring points preliminarily determined by experience and the overlapping points of the candidate pressure monitoring points selected by the fuzzy cluster analysis clustering algorithm are used as the final pressure monitoring point layout plan.

5. The method for joint dispatching of water plants in a city water supply system according to claim 1, characterized in that: Selecting feature values ​​for the historical meteorological data, specifically, normalizing each influencing feature; evaluating the importance of the feature by calculating the impact of the feature on the model accuracy in each decision tree; According to the results of feature importance evaluation, the feature that contributes most to model prediction is selected as the input of the water volume prediction model; the pre-trained water volume prediction model is used to predict the water demand in a preset time period in the future. Specifically, the original time series data is decomposed into an approximate sequence and multiple detail sequences using wavelet decomposition; the approximate sequence is fitted and predicted using a long short-term memory network; the detail sequence is fitted and predicted using an XGBoost model; the predicted values ​​obtained by predicting the approximate sequence and the detail sequence are added and summed to obtain the final prediction result.

6. The method for joint dispatching of water plants in a city water supply system according to claim 1, characterized in that: The optimization scheduling process of the first-level optimization scheduling model includes: predicting the future hourly water supply of the city based on the water volume prediction model; taking the hourly water supply and water supply pressure of each water plant as decision variables, using the genetic algorithm improved by simulated annealing to search for optimization, and obtaining a feasible solution based on the preset objective function; obtaining the pressure value at the corresponding time according to the feasible solution, and judging whether the constraint conditions are met. If not, re-iterate until the constraint requirements are met; the optimization scheduling process of the second-level optimization scheduling model includes: obtaining the hourly optimal water supply and water supply pressure of the water plant based on the first-level optimization scheduling model; taking the switch combination of the pump unit of the pump station and the speed ratio of the speed regulating pump as decision variables, using the genetic algorithm improved by simulated annealing to search for optimization, and obtaining a feasible solution based on the preset objective function expression; the obtained feasible solution is combined with relevant constraint conditions to judge whether the requirements are met. If not, return to re-solve until the constraint requirements are met.

7. A water plant joint dispatching system for an urban water supply system, characterized in that: include: A data acquisition module configured to obtain basic data of the urban pipe network, as well as water supply data, pressure data and meteorological data; A pipe network modeling module, which is configured to establish a hydraulic model of the water supply pipe network according to the basic data, and determine the pressure monitoring point according to the hydraulic model of the water supply pipe network; A water volume prediction module is configured to establish a water volume prediction model based on historical water supply data and historical meteorological data; and obtain a water volume prediction result based on the obtained water volume prediction model and predicted meteorological data; A first optimization module is configured to obtain the water supply volume and water supply pressure of the water plant that meet the constraint conditions according to the water volume prediction results obtained from the determined pressure monitoring points and the preset first-level optimization scheduling model; wherein the decision variables of the first-level optimization scheduling model are the water supply volume and water supply pressure of each water plant, and the first-level optimization scheduling model aims to minimize the water plant cost of the water supply network; The second optimization module is configured to obtain the switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump that meet the constraints according to the water supply volume and water supply pressure determined by the first-level optimization scheduling model and the preset second-level optimization scheduling model; the decision variables of the second-level optimization scheduling model are the switch combination of the pump station water pump unit and the speed ratio of the speed regulating pump, and the second-level optimization scheduling model aims to minimize the energy consumption of the water plant at the corresponding time.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the water plant joint scheduling method for a city water supply system as described in any one of claims 1 to 6 are implemented.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the steps of the urban water supply system water plant joint scheduling method as described in any one of claims 1-6 are implemented.

10. A computer program product comprising software code, characterized in that The program in the software code executes the steps of the urban water supply system water plant joint scheduling method as described in any one of claims 1-6.

Images