Urban intelligent drainage management system based on cloud-side cooperation

Through cloud-edge collaboration technology, real-time monitoring and prediction of urban drainage system status has been solved, and the problem of lagging response of traditional urban drainage management systems has been achieved, efficient and accurate drainage management has been achieved, and flood disaster risks have been reduced.

CN119048307APending Publication Date: 2024-11-29CHINASOFT INTERNATIONAL SOFTWARE (SUZHOU) CO LTD
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202411107476.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-13
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

Traditional urban drainage management systems rely on manual monitoring and fault response, with lagging reactions and low efficiency, unable to monitor and adjust in real time, making it difficult to cope with the increased demand for extreme weather events.

Method used

Adopt a smart urban drainage management system based on cloud edge collaboration, and monitor and predict drainage systems in real time through the cloud control center and coordinated work with edge computing nodes, data acquisition modules, data analysis modules, data prediction modules, data interaction modules and data execution modules. state, realizes rapid data processing and precise execution of decision-making.

Benefits of technology

It improves the efficiency and accuracy of urban drainage management, warning of drainage problems in advance, reduces the occurrence of floods and floods, reduces data transmission delays, and improves the real-time and stability of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119048307A_ABST
    Figure CN119048307A_ABST
Patent Text Reader

Abstract

The invention discloses an urban intelligent drainage management system based on cloud-side cooperation. The system is designed to integrate advanced sensing technology, edge computing, cloud computing and artificial intelligence algorithms. The system core comprises a data acquisition module, an edge computing node, a cloud server and a user interaction interface, the data acquisition module is responsible for collecting key operation data of a drainage network in real time, and the edge computing node performs primary processing and real-time analysis on the data to quickly respond to abnormal conditions; the cloud server undertakes complex data analysis tasks and provides long-term trend prediction and optimization strategies; a user interaction interface adopts a visual design, supports multi-platform access, and provides real-time data visualization and operation control; the system also introduces a block chain technology and a community participation mechanism. The invention relates to the technical field of Internet of Things and cloud computing. The efficiency and response speed of urban drainage management can be better improved, and the urban waterlogging problem caused by rainstorm natural disasters is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of Internet of Things and cloud computing technology, and specifically to an urban smart drainage management system based on cloud-edge collaboration. Background Art

[0002] Urban drainage management system refers to the system used in cities to collect, transport, treat and discharge urban rainwater and sewage, also known as urban rainwater and sewage treatment system. Urban drainage management system plays an important role in ensuring the quality of life of urban residents, environmental protection and disaster prevention and mitigation. In order to achieve urban drainage management, it is usually necessary to establish a complete set of management strategies and technical mechanisms, including the following aspects: collection module, edge computing node, cloud server and user interaction interface.

[0003] In the existing technology, traditional urban drainage management systems usually rely on manual monitoring and fault response, and there are problems of delayed response and low efficiency. With the acceleration of urbanization, extreme weather events occur frequently, and the demand for drainage systems is increasing. There is an urgent need for an intelligent solution that can monitor, predict and automatically adjust in real time. In view of the shortcomings of the existing technology, the present invention provides an urban smart drainage management system based on cloud-edge collaboration technology. Cloud-edge collaboration technology combines the big data processing of cloud computing and the real-time response capabilities of edge computing to achieve rapid data processing and accurate decision-making. This system not only improves the efficiency and accuracy of drainage management, but also provides strong support for the sustainable development of cities. Summary of the invention

[0004] The purpose of the present invention is to provide an urban smart drainage management system based on cloud-edge collaboration, aiming to improve urban drainage efficiency, timely warn and deal with drainage problems. In order to achieve the above purpose, the present invention is implemented through the following technical solutions:

[0005] An urban smart drainage management system based on cloud-edge collaboration includes a cloud control center, wherein the cloud control center is communicatively connected with a data acquisition module, an edge computing node, a data analysis module, a data prediction module, a data interaction module and a data execution module;

[0006] The cloud control center is the core of the system, responsible for coordinating and managing the operation of each module. It connects the data acquisition module, edge data computing node, data analysis module, data prediction module, data interaction module and data execution module through the communication network to realize the centralized processing of data and the unified issuance of control instructions.

[0007] The data acquisition module is used to collect rainfall, water level and water quality data in various areas of the city. The specific operation steps include: installing a variety of sensors at key locations in the city, including liquid level sensors, flow meters, water quality detectors and rainfall sensors.

[0008] Liquid level sensor: used to measure the water level in drainage pipes and storage tanks. Common types include ultrasonic liquid level sensors and float liquid level sensors.

[0009] Flow meter: used to measure water flow, common types include electromagnetic flow meter and ultrasonic flow meter.

[0010] Water quality detector: used to monitor water quality parameters such as pH, turbidity, and dissolved oxygen content.

[0011] Rainfall sensor: used to measure rainfall amount and rainfall intensity. Common types include tipping bucket rain gauge and photoelectric rain gauge. The sensor can monitor the data of key nodes such as drainage pipes and water storage tanks in real time.

[0012] The sensor connects to the nearby wireless network via wireless connection (WiFi) using the built-in WiFi module, transmitting the collected data to the edge computing node via WiFi and wired connection (Ethernet and Wi-Fi) via network cable to the network switch or router, transmitting the collected data to the edge computing node via Ethernet.

[0013] Edge data computing nodes are small computing units located near data sources, equipped with high-performance processors and storage devices, which can pre-process and perform preliminary analysis on data close to the data source. Edge computing nodes upload pre-processed data to the cloud control center through API interfaces.

[0014] Data Analysis Module:

[0015] The data analysis module analyzes the collected data in real time to identify the operating status of the drainage system. Its operation process includes:

[0016] Receive and process data (null values, duplicate values) that have been initially cleaned and formatted by the data acquisition module.

[0017] Select appropriate machine learning algorithm models and use different models according to different real-time and complexity requirements (such as LSTM, GRU time series models, deep learning models such as CNN, Autoencoders, and integrated learning models such as XGBoost, TinyML, and random forests).

[0018] The machine learning model is trained until its accuracy and stability reach preset targets.

[0019] The data prediction module predicts future rainfall and drainage demand based on historical data and real-time data. The prediction process includes:

[0020] Get the latest weather forecast data through the API interface, including rainfall, rainfall intensity and rainfall duration.

[0021] Weather forecast data is combined with preprocessed drainage data to predict future rainfall using machine learning models.

[0022] Generate waterlogging risk maps, analyze waterlogging risks in different areas, and dynamically adjust the operation strategy of the drainage system.

[0023] Establish a feedback mechanism for prediction results and debug the prediction model.

[0024] The data interaction module is used to conduct two-way communication with urban drainage facilities, receive equipment status information and send control instructions. The communication process includes:

[0025] Establish a two-way communication mechanism through standard communication protocols (such as TCP / IP, HTTP, MQTT).

[0026] Realize real-time communication between drainage facilities and data interaction modules, and monitor the operating status of pump stations, valves and water level sensors.

[0027] Various drainage facilities are connected to the network through Internet of Things technology to achieve real-time data transmission and equipment status monitoring.

[0028] The data execution module is responsible for executing the control instructions sent by the cloud control center to remotely operate urban drainage facilities. Its execution process includes:

[0029] Receive and parse the instructions from the cloud control center and extract the specific content.

[0030] Send specific instructions to the device through the interface to start and stop the pump station and change the valve opening degree.

[0031] The execution results are fed back to the cloud control center to achieve closed-loop control.

[0032] The public feedback platform is used to collect and manage the public's questions and opinions about the urban drainage system. The public can submit the drainage problems they encounter through mobile applications, websites and social media, and the system will incorporate this information into the management and processing process.

[0033] The user interaction interface includes a data display unit and a control unit:

[0034] The data display unit displays the operation status, historical data and trend prediction results of the drainage system in real time through charts and graphs.

[0035] The control unit allows users to operate and control the drainage system through the interface, such as adjusting drainage strategies and activating emergency plans. Users can view and operate at any time through PC and mobile terminals.

[0036] Through the above technical solution, the urban smart drainage management system based on cloud-edge collaboration constructed by the present invention can achieve accurate management and timely response of urban drainage, and improve the urban flood control and drainage capabilities. Compared with the prior art, the advantages of the present invention are:

[0037] 1. Through cloud-edge collaboration, efficient data processing and decision-making response are achieved, improving the intelligence level of the urban drainage system;

[0038] 2. Using the intelligent prediction module, drainage problems can be warned in advance to reduce the occurrence of flood disasters;

[0039] 3. The introduction of edge computing nodes reduces data transmission delay and improves the real-time performance and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic diagram of the present invention. DETAILED DESCRIPTION

[0041] The following specific implementation method describes in detail a method for implementing an urban smart drainage management system based on cloud-edge collaboration. The system realizes real-time monitoring, analysis, prediction and control of the urban drainage system through the collaborative work of the cloud control center and the edge computing nodes, improves the efficiency of drainage management and reduces the risk of waterlogging.

[0042] Embodiment 1, a smart urban drainage management system based on cloud-edge collaboration, comprising:

[0043] The cloud control center is connected to the data collection module, the data analysis module, the edge data computing node, the data prediction module, the data interaction module and the data execution module;

[0044] Data collection module, used to collect rainfall, water level and water quality data in various areas of the city;

[0045] Edge data nodes are small computing units located near data sources, equipped with high-performance processors, storage devices, and necessary software, which can process data close to the data source;

[0046] Data analysis module, which performs real-time analysis on the collected data and identifies the operating status of the drainage system;

[0047] Data prediction module, which predicts future rainfall and drainage demand based on uploaded data and real-time data;

[0048] Data interaction module, used for two-way communication with urban drainage facilities, receiving equipment status information and sending control instructions;

[0049] The data execution module is responsible for executing the control instructions sent by the cloud control center and remotely operating the urban drainage facilities.

[0050] The data collection process of the data acquisition module includes:

[0051] The data collection module collects rainfall, water level and water quality data in real time through a network of sensors distributed at key locations in the city. The specific steps include:

[0052] First, we need to select liquid level sensors, flow meters, water quality detectors and rainfall sensors at different locations according to monitoring needs, install the sensors at key nodes of drainage pipes and water storage tanks, send the collected rainfall, water level and water quality data to the data acquisition module via WiFi, and transmit the data to the edge computing node via wired and wireless connections. The specific operation steps are as follows:

[0053] First, we need to clean the data to remove invalid data, write a data cleaning script, and write code to detect and remove invalid data;

[0054] Secondly, the collected rainfall, water level and water quality data are divided into several groups at the same time intervals, according to the calculation formula Z = \frac{X-\mu}{\sigma};

[0055] (Z) is the Z score of the data point (X),

[0056] (X) is the specific data point value,

[0057] (\mu) is the mean of the data set,

[0058] (\sigma) is the standard deviation of the data set, which calculates the relative position of each value in a set of data.

[0059] If the calculated result is greater than 3, it means that the difference between it and the mean exceeds the range of normal data points and is considered an outlier. Find and eliminate outliers greater than 3.

[0060] Finally, the pre-processed data is customized to output date and time format by writing code to ensure that the time format of all sensor data is consistent. Then, the same type of data is expressed in one unit through unit conversion. Finally, data with the same time interval is selected for data aggregation, and the data within the set time range is aggregated and merged. At the same time, the same type of sensor data in the same geographical area is merged, added and averaged to calculate the regional average and total.

[0061] The edge computing node preprocesses the data as above and uploads the preprocessed data to the cloud control center via a wireless connection through an API interface, a tool that allows different software systems to communicate with each other.

[0062] The operation process of the data analysis module includes:

[0063] After the collected data is initially cleaned and formatted by the data acquisition module, it is also transmitted to the data analysis module through the interface. Different machine learning algorithm models are selected according to the needs. For high real-time requirements, LSTM and GRU time series models are used; for tasks with high data complexity, deep learning models and integrated learning models are used. For resource-constrained tasks: When deployed on edge devices, TinyML and random forests are selected;

[0064] After selecting the learning algorithm, upload the previously transmitted pre-processed rainfall, water level and water quality data to train the machine learning algorithm model until its accuracy and stability reach the preset goals.

[0065] The prediction process of the data prediction module includes:

[0066] First, select an API through the interface to send a request to obtain the latest weather forecast data, including rainfall, rainfall intensity, and rainfall duration. Then combine the weather forecast data with the previously preprocessed drainage data to let the machine learning model predict future rainfall conditions and generate results.

[0067] At the same time, based on previously input data and weather forecast data, the time series data is analyzed and meaningful statistical features and patterns are extracted from it to predict possible waterlogging points in the future. The waterlogging risks in different areas are analyzed through spatial aggregation to generate waterlogging risk maps. According to real-time weather data and forecast results, the operation strategy of the drainage system is dynamically adjusted. At the same time, a feedback mechanism for the forecast results is established, that is, the forecast model is debugged by comparing the forecast results with the actual situation.

[0068] The communication process of the data interaction module includes:

[0069] The interaction between data cannot avoid the establishment of a two-way communication mechanism. Specifically, it is necessary to use standard communication protocols such as TCP / IP protocol, HTTP protocol, MQTT protocol, and use specific communication rules and parameters. After the two-way communication mechanism is established, the data interaction module can receive data from the drainage facilities and send control instructions to the drainage facilities, thereby realizing remote monitoring and control of the drainage facilities.

[0070] Then, through the Internet of Things technology, real-time communication between the drainage facilities and the data interaction module is realized. The Internet of Things technology can connect various drainage facilities such as pump stations, valves and water level sensors to the network. Through various sensors and equipment deployed on the drainage facilities, the system can monitor the operating status of the drainage facilities in real time, and transmit the data collected by the sensors to the data interaction module through the wireless network. The operating status information of the pump station, the start and stop status of the pump, and the operating power fault alarm will be collected in real time through the sensors installed in the pump station, and the collected operating status information of the pump station will be sent to the data interaction module through wireless transmission. Similarly, the opening and closing status information of the valve is collected through the valve position sensor, which can detect the specific position and opening and closing angle of the valve, and transmit the opening and closing status information of the valve to the data interaction module in real time. The real-time collected water level data can help the system determine the load of the drainage network and take timely measures to prevent internal, realize real-time communication between the drainage facilities and the data interaction module, and receive and process the operating status of the pump station, the opening and closing status of the valve and the water level sensor data in real time.

[0071] The execution process of the data execution module includes:

[0072] After receiving instructions from the cloud control center through wireless transmission and wired connection, Python's built-in library json is used to parse the instructions and extract the specific content of the instructions from the parsed content. The edge computing node sends specific instructions to the device through the interface to start and stop the pump station, change the degree of valve opening, and then feed back the execution results to the cloud control center to achieve closed-loop control.

[0073] The public feedback platform is a platform used to collect, process and manage public issues and opinions regarding the urban drainage system. The public can submit drainage problems such as drainage blockage, overflow and improper sewage treatment encountered in their daily lives through mobile applications, websites and social media.

[0074] The user interface includes:

[0075] The data display unit displays the operation status, historical data and trend prediction results of the drainage system in real time through charts and graphs; the control unit allows users to operate and control the drainage system through the interface, such as adjusting drainage strategies and enabling emergency plans. It supports multi-platform access and users can view and operate at any time through PC and mobile terminals.

[0076] The environment and equipment required for this implementation include:

[0077] Hardware equipment:

[0078] Liquid level sensor, flow meter, water quality detector, rainfall sensor, etc.

[0079] Edge computing nodes (equipped with high-performance processors and storage devices)

[0080] Cloud server (with big data processing and storage capabilities)

[0081] Network equipment (routers, switches)

[0082] Software Configuration:

[0083] Sensor Data Acquisition Software

[0084] Edge computing platforms (such as EdgeXFoundry, KubeEdge)

[0085] Cloud-based big data processing platforms (such as Apache Hadoop, Apache Spark)

[0086] Data visualization tools (such as D3.js, Tableau)

[0087] Security management software (such as SSL / TLS encryption tools)

[0088] How to use, the specific implementation steps of the data acquisition module are as follows:

[0089] Install level sensors, flow meters, water quality detectors and rainfall sensors in different areas of the city.

[0090] Liquid level sensors are installed at key locations of water bodies such as rivers, lakes, and drainage channels, and are connected to the nearest network switch via network cables.

[0091] Flow meters are installed in water pipes, sewage pipes, major rivers and drains, etc., and are connected to the nearest network switch via network cables.

[0092] Water quality detectors are installed at drinking water sources, sewage treatment plants, industrial outfalls and natural water bodies and are connected to the nearest network switch via network cables.

[0093] Rainfall sensors are installed in various areas of the city and connect to nearby wireless networks via built-in WiFi modules.

[0094] Sensors monitor data such as water level, flow, water quality, and rainfall in real time and transmit the data to edge computing nodes.

[0095] The liquid level sensor and flow meter are connected to the network switch via a network cable, and the data is transmitted to the edge computing node via Ethernet.

[0096] The rain sensor connects to a nearby wireless network via a built-in WiFi module and transmits data to the edge computing node.

[0097] Specific operation steps of edge computing nodes:

[0098] The edge computing node receives the data transmitted by the sensor in real time and connects through wired and wireless networks to ensure the timeliness and stability of data transmission. The data of the liquid level sensor, flow meter and water quality detector are connected to the edge computing node via network cables, while the data of the rainfall sensor is connected to the edge computing node via WiFi.

[0099] Data cleaning

[0100] Data cleaning is the first step in data processing, which aims to eliminate invalid data and improve data quality. It mainly includes the following steps:

[0101] Null value handling: Write code to detect and remove null values ​​in the data to avoid errors in subsequent analysis.

[0102] Duplicate value processing: Write a program to detect and remove duplicate data to ensure data uniqueness and accuracy.

[0103] Formatting: Unify the timestamp format and unit of data to ensure data consistency and comparability.

[0104] Data aggregation is to aggregate different sensor data within the same time period to generate time series data. The aggregated data can better reflect the changes in water level, flow, water quality and rainfall within a specific time period, providing support for subsequent analysis and decision-making.

[0105] After the edge computing node performs preliminary processing on the data, it uploads the pre-processed data to the cloud control center through the API interface. The cloud control center centrally stores and processes the data, supports big data analysis and machine learning applications, and provides in-depth data analysis and decision support.

[0106] Specific implementation methods of data analysis:

[0107] Choose the appropriate machine learning algorithm model,

[0108] Long Short-Term Memory (LSTM)

[0109] Used for time series forecasting and processing data with long-term dependencies, such as predicting water level trends.

[0110] Hyperparameter Optimization:

[0111] Find the best hyperparameter combination through grid search, random search, or Bayesian optimization.

[0112] Through the above methods, using machine learning models and real-time data monitoring systems, the operating status of urban drainage systems can be effectively predicted and analyzed, potential problems can be identified and countermeasures can be taken in a timely manner.

[0113] The specific implementation of the data prediction module is as follows:

[0114] Get the latest weather forecast data through the API interface, including rainfall amount, rainfall intensity and rainfall duration.

[0115] Combine weather forecast data with historical drainage data and use the trained machine learning model to predict future rainfall and drainage needs.

[0116] Feature extraction and time series analysis:

[0117] Extract statistical features such as average rainfall, maximum rainfall, cumulative rainfall, etc.

[0118] Analyze the changing trend and periodic characteristics of rainfall, and use the model to make time series forecasts;

[0119] Generate a waterlogging risk map and analyze the waterlogging risks in different areas. Based on the prediction results, evaluate the waterlogging risks in different areas, classify the risks, and dynamically adjust the operation strategy of the drainage system.

[0120] Specific implementation methods of data interaction:

[0121] Establish a two-way communication mechanism using standard communication protocols;

[0122] Select the communication protocol:

[0123] TCP / IP: used for high-reliability communication scenarios, such as device control command transmission.

[0124] HTTP: used for data requests and responses, such as sensor data acquisition.

[0125] MQTT: used for low-latency, lightweight message transmission, such as real-time status monitoring and control command sending.

[0126] To establish two-way communication:

[0127] Configure the device and server to support the selected protocol to achieve two-way communication between the device and the cloud.

[0128] Using IoT technology, pump stations, valves and water level sensors are connected to the network;

[0129] Sensor connection and data collection:

[0130] Connect pump stations, valves, and water level sensors to edge computing nodes via wireless or wired networks.

[0131] Configure the device to collect data and send the data to the edge computing node or the cloud through communication protocols.

[0132] Receive device status data:

[0133] Configure the data interaction module to receive data from sensors and devices for real-time monitoring.

[0134] Send control instructions:

[0135] Based on the monitoring data, control instructions are sent to the equipment to achieve remote monitoring and control.

[0136] Specific implementation of the data execution module:

[0137] Receive control instructions:

[0138] The edge computing node receives control instructions from the cloud control center and transmits them to the device via wireless or wired connection.

[0139] The edge computing node parses the instruction and performs the operation:

[0140] The edge computing node parses the control instructions and extracts the specific operation content (such as starting and stopping the pump station and changing the opening and closing degree of the valve).

[0141] Issue specific instructions to the device and feed back the execution results to the cloud control center.

[0142] Specific implementation methods of public feedback:

[0143] Create a feedback channel:

[0144] Provide feedback channels through mobile apps, websites and social media for the public to submit drainage issues and comments.

[0145] Collect public feedback information and incorporate it into the system's management and processing procedures.

[0146] Analysis and processing of feedback information:

[0147] Analysis feedback information:

[0148] The system analyzes the collected feedback information to identify common problems and emergency situations.

[0149] Based on the analysis results, relevant processing is carried out and the processing process is recorded.

[0150] Specific implementation of user interaction:

[0151] The data display and control interface displays the operation status, historical data and trend prediction results of the drainage system in real time through charts and graphs.

[0152] Use data visualization tools such as Plotly and Matplotlib to generate visual charts.

[0153] Control unit:

[0154] Allow users to operate and control the drainage system through the interface, such as adjusting drainage strategies and activating emergency plans.

[0155] User interaction is achieved through a web interface or mobile app.

[0156] Through the above methods, a complete urban drainage system monitoring and management platform can be established. The platform realizes two-way communication between devices and the cloud through standard communication protocols, uses IoT technology for data collection and control, uses machine learning models for predictive analysis, and generates waterlogging risk maps through GIS technology. At the same time, public feedback and user interaction functions further improve the practicality and responsiveness of the system, helping municipal departments to formulate effective flood control and drainage strategies.

[0157] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. An urban smart drainage management system based on cloud-edge collaboration, It is characterized in that include: A cloud control center, wherein the cloud control center is communicatively connected to a data acquisition module, a data analysis module, an edge data computing node, a data prediction module, a data interaction module, and a data execution module; Data collection module, used to collect rainfall, water level and water quality data in various areas of the city; Edge data nodes are small computing units located near data sources, equipped with high-performance processors, storage devices, and necessary software, which can process data close to the data source; Data analysis module, which performs real-time analysis on the collected data and identifies the operating status of the drainage system; Data prediction module, which predicts future rainfall and drainage demand based on uploaded data and real-time data; Data interaction module, used for two-way communication with urban drainage facilities, receiving equipment status information and sending control instructions; The data execution module is responsible for executing the control instructions sent by the cloud control center and remotely operating the urban drainage facilities.

2. According to the urban smart drainage management system based on cloud-edge collaboration according to claim 1, It is characterized in that The data collection process of the data acquisition module includes: The data collection module collects rainfall, water level and water quality data in real time through a network of sensors distributed at key locations in the city. The specific steps include: First, we need to select liquid level sensors, flow meters, water quality detectors and rainfall sensors at different locations according to monitoring needs, install the sensors at key nodes of drainage pipes and water storage tanks, send the collected rainfall, water level and water quality data to the data acquisition module via WiFi, and transmit the data to the edge computing node via wired and wireless connections; The specific steps are as follows: First, we need to clean the data to remove invalid data, write a data cleaning script, and write code to detect and remove invalid data; Secondly, the collected rainfall, water level and water quality data are divided into several groups at the same time intervals, according to the calculation formula Z = \frac{X-\mu}{\sigma}; (Z) is the Z score of the data point (X), (X) is the specific data point value, (\mu) is the mean of the data set, (\sigma) is the standard deviation of the data set. The relative position of each value in a set of data is calculated. If the calculated result is greater than 3, it means that its difference from the mean exceeds the range reached by normal data points and is regarded as an outlier. Find and eliminate outliers greater than 3; Finally, the pre-processed data is customized to output date and time format by writing code to ensure that the time format of all sensor data is consistent. Then, the same type of data is expressed in one unit through unit conversion. Finally, data with the same time interval is selected for data aggregation, and the data within the set time range is aggregated and merged. At the same time, the same type of sensor data in the same geographical area is merged, added and averaged to calculate the regional average and total. The edge computing node preprocesses the data as above and uploads the preprocessed data to the cloud control center via a wireless connection through an API interface, a tool that allows different software systems to communicate with each other.

3. According to the urban smart drainage management system based on cloud-edge collaboration as described in claim 2, It is characterized in that The operation process of the data analysis module includes: After the collected data is initially cleaned and formatted by the data acquisition module, it is also transmitted to the data analysis module through the interface. Different machine learning algorithm models are selected according to the needs. For high real-time requirements, LSTM and GRU time series models are used; for tasks with high data complexity, deep learning models and integrated learning models are used. For resource-constrained tasks: When deployed on edge devices, TinyML and random forests are selected; After selecting the learning algorithm, upload the previously transmitted pre-processed rainfall, water level and water quality data to train the machine learning algorithm model until its accuracy and stability reach the preset goals.

4. According to the urban smart drainage management system based on cloud-edge collaboration as described in claim 3, It is characterized in that The prediction process of the data prediction module includes: First, select an API through the interface to send a request to obtain the latest weather forecast data, including rainfall, rainfall intensity, and rainfall duration. Then combine the weather forecast data with the previously preprocessed drainage data to let the machine learning model predict future rainfall conditions and generate results. At the same time, based on previously input data and weather forecast data, the time series data is analyzed and meaningful statistical features and patterns are extracted from it to predict possible waterlogging points in the future. The waterlogging risks in different areas are analyzed through spatial aggregation to generate waterlogging risk maps. According to real-time weather data and forecast results, the operation strategy of the drainage system is dynamically adjusted. At the same time, a feedback mechanism for the forecast results is established, that is, the forecast model is debugged by comparing the forecast results with the actual situation.

5. According to the urban smart drainage management system based on cloud-edge collaboration according to claim 4, It is characterized in that The communication process of the data interaction module includes: The interaction between data cannot avoid the establishment of a two-way communication mechanism. Specifically, it is necessary to use standard communication protocols such as TCP / IP protocol, HTTP protocol, MQTT protocol, and use specific communication rules and parameters. After the two-way communication mechanism is established, the data interaction module can receive data from the drainage facilities and send control instructions to the drainage facilities, thereby realizing remote monitoring and control of the drainage facilities. Then, through the Internet of Things technology, real-time communication between the drainage facilities and the data interaction module is realized. The Internet of Things technology can connect various drainage facilities such as pump stations, valves and water level sensors to the network. Through various sensors and equipment deployed on the drainage facilities, the system can monitor the operating status of the drainage facilities in real time, and transmit the data collected by the sensors to the data interaction module through the wireless network. The operating status information of the pump station, the start and stop status of the pump, and the operating power fault alarm will be collected in real time through the sensors installed in the pump station, and the collected operating status information of the pump station will be sent to the data interaction module through wireless transmission. Similarly, the opening and closing status information of the valve is collected through the valve position sensor, which can detect the specific position and opening and closing angle of the valve, and transmit the opening and closing status information of the valve to the data interaction module in real time. The real-time collected water level data can help the system determine the load of the drainage network and take timely measures to prevent internal, realize real-time communication between the drainage facilities and the data interaction module, and receive and process the operating status of the pump station, the opening and closing status of the valve and the water level sensor data in real time.

6. According to the urban smart drainage management system based on cloud-edge collaboration according to claim 5, It is characterized in that The execution process of the data execution module includes: After receiving instructions from the cloud control center through wireless transmission and wired connection, Python's built-in library json is used to parse the instructions and extract the specific content of the instructions from the parsed content. The edge computing node sends specific instructions to the device through the interface to start and stop the pump station, change the degree of valve opening, and then feed back the execution results to the cloud control center to achieve closed-loop control.

7. According to claim 6, the urban smart drainage management system based on cloud-edge collaboration, It is characterized in that The urban smart drainage management system based on cloud-edge collaboration further includes: The public feedback platform is a platform for collecting, processing and managing public issues and opinions on the urban drainage system, and submitting drainage problems such as drainage blockage, overflow and improper sewage treatment encountered in their daily lives through mobile applications, websites and social media.

8. According to claim 7, the urban smart drainage management system based on cloud-edge collaboration, It is characterized in that The user interaction interface comprises: A data display unit, which displays the operation status, historical data and trend prediction results of the drainage system in real time through charts and graphs; The control unit allows the user to operate and control the drainage system through the interface, such as adjusting the drainage strategy and enabling the emergency plan. It supports multi-platform access and the user can view and operate it at any time through the PC and mobile terminals.

Citation Information

Cited By

  • Intelligent water affair management analysis system

    CN119250585A

  • Heat pump centralized control management system and method based on Internet of Things platform

    CN119892894A

  • Automatic feed treatment system and treatment method for livestock breeding

    CN120111070A

  • Management system based on internet of things pump station

    CN120980113A