Database monitoring processing method and system for reservoir, medium and electronic equipment
By setting up multiple types of sensors in the reservoir and dynamically adjusting the sampling frequency, and combining historical data to predict water level, the problem of low prediction accuracy of traditional reservoir monitoring methods is solved, and more accurate water level monitoring and timely warning prompts are achieved.
Patent Information
- Application Number
- CN202411032725.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-30
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional reservoir monitoring methods rely on fixed-position sensors, which are difficult to fully and accurately reflect the actual situation of the reservoir, especially when the reservoir has complex geographical characteristics and dynamic environment changes, resulting in large deviations in water level prediction.
By setting up multiple sensors of different types in the reservoir, dynamically adjusting the sampling frequency according to their location, quantity and reservoir information, water level prediction is performed based on historical data, and an early warning prompt is generated when the preset threshold reaches or exceeds.
It significantly improves the representativeness and prediction accuracy of water level monitoring data, ensures that reservoir managers can take timely flood prevention and disaster reduction measures to adapt to the complexity of the geographical characteristics of the reservoir and environmental changes.
Smart Images

Figure CN119004019A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing, and in particular to a database monitoring and processing method, system, medium and electronic equipment for a reservoir. Background Art
[0002] As an important water resource management facility, water level monitoring of reservoirs is of great significance for flood prevention and disaster reduction, water resource scheduling, and ecological and environmental protection. Traditional reservoir monitoring methods usually rely on sensors at fixed locations to collect water level data. However, due to the complex geographical characteristics of reservoirs, their shapes and sizes vary. In addition, the reservoir environment may change over time, such as siltation and bank erosion, which further increases the complexity of water level monitoring.
[0003] The above factors may lead to large deviations in water level predictions based on traditional monitoring methods. It is difficult to fully and accurately reflect the actual situation of the entire reservoir by collecting water level data through sensors at fixed locations. Summary of the invention
[0004] The present application provides a database monitoring and processing method, system, medium and electronic equipment for a reservoir, which can adjust the sensor layout and sampling strategy according to the dynamic changes in the geographical characteristics of the reservoir, thereby improving the representativeness and prediction accuracy of water level monitoring data.
[0005] In a first aspect of the present application, the present application provides a database monitoring and processing method for a reservoir, comprising: Obtaining the locations and quantities of multiple sensors of different types set up in the reservoir; Determine a first sampling frequency of each sensor according to the location, quantity and reservoir information of each type of sensor; Acquire first reservoir data collected by each of the sensors at the first sampling frequency at a first time; Predicting a first water level of the reservoir after a preset time period based on the first reservoir data and historical reservoir data in a database; If the first water level is greater than or equal to a threshold, an early warning prompt is generated.
[0006] In a second aspect of the present application, a database monitoring and processing system for a reservoir is provided, comprising: A sensor information acquisition module is used to obtain the locations and quantities of multiple sensors of different types arranged in the reservoir; A first sampling frequency determination module, used to determine the first sampling frequency of each sensor according to the location, quantity and reservoir information of each type of sensor; A first reservoir data acquisition module, used for acquiring first reservoir data acquired by each of the sensors at the first sampling frequency at the first time; A first water level prediction module, used to predict a first water level of the reservoir after a preset time period based on the first reservoir data and historical reservoir data in a database; The early warning prompt generating module is used to generate an early warning prompt if the first water level is greater than or equal to a threshold.
[0007] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above method steps.
[0008] In a fourth aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.
[0009] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By setting up multiple sensors of different types in the reservoir and determining the first sampling frequency based on the location, quantity and reservoir information of each type of sensor, the problem that the traditional fixed-position sensor monitoring method is difficult to fully and accurately reflect the actual situation of the entire reservoir is effectively solved. By obtaining the first reservoir data collected at the first sampling frequency at the first time, combined with the historical reservoir data in the database, the first water level of the reservoir after a preset time can be more accurately predicted. When the predicted first water level reaches or exceeds the preset threshold, the system will automatically generate an early warning prompt to provide decision-making support for reservoir managers to take flood prevention and disaster reduction measures in a timely manner.
[0010] Compared with the traditional fixed-position sensor monitoring method, this solution fully considers the complexity of the reservoir's geographical characteristics and the dynamic changes of the environment. By flexibly adjusting the sensor layout and sampling strategy, it significantly improves the representativeness and prediction accuracy of water level monitoring data. The collaborative work of multiple types of sensors can capture the reservoir status in multiple dimensions, while the dynamically optimized sampling frequency ensures the efficiency and pertinence of the monitoring process. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] Figure 1 It is a flow chart of a database monitoring method for a reservoir provided in an embodiment of the present application; Figure 2 It is a structural schematic diagram of a database monitoring system for a reservoir provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.
[0012] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION
[0013] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.
[0014] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.
[0015] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.
[0016] Please refer to Figure 1 , Figure 1 This is a flow chart of a database monitoring and processing method for a reservoir provided by an embodiment of the present application. The method can be implemented by a computer program, can be implemented by a single-chip microcomputer, or can be run on a database monitoring and processing system for a reservoir. The computer program can be integrated into an application or run as an independent tool application. Specifically, the database monitoring and processing method for a reservoir can include the following steps: S101: Acquire the locations and quantities of multiple sensors of different types arranged in a reservoir.
[0017] Among them, the sensor refers to a device that can convert physical or chemical quantities into usable electrical signals. In the embodiment of the present application, it can be understood as various measuring instruments installed inside or around the reservoir for collecting reservoir-related parameters. The above sensors are mainly used to monitor various indicators of the reservoir in real time and provide data support for reservoir management and disaster prevention and mitigation.
[0018] Furthermore, the location and quantity of sensors refer to the spatial distribution of various types of sensors in the reservoir and their specific number. In the embodiment of the present application, it can be understood as the geographic coordinate information of different types of sensors in the reservoir monitoring system and the specific number of each type of sensor installed. The above information is used to describe the overall layout and density of the reservoir monitoring network, providing basic parameters for subsequent data collection, analysis and water level prediction.
[0019] In the embodiment of the present application, the types of sensors may include water level sensors, rainfall sensors, flow rate sensors, temperature and humidity sensors and other measuring instruments for assisting in monitoring the water level. The above sensors are used to directly measure the water surface height, rainfall per unit time, water flow velocity, water body temperature and surrounding air humidity through different measurement principles. In order to comprehensively monitor the reservoir conditions, the above sensors need to be reasonably distributed in key locations and surrounding areas of the reservoir.
[0020] Among them, the layout of water level sensors needs to consider the topographic characteristics, hydrological conditions and monitoring needs of the reservoir. Usually, water level sensors are installed at key locations of the reservoir, such as near the dam, the main water inlet and outlet, and different areas of the reservoir. In practical applications, the number and distribution of water level sensors may vary depending on the size and shape of the reservoir. For example, for a large reservoir, several water level sensors may be densely arranged near the dam to accurately monitor the changes in the water storage capacity of the reservoir; several sensors are set at the main water inlet and outlet to monitor the amount of water entering and leaving the reservoir; in addition, multiple sensors can be distributed in different areas of the reservoir to comprehensively monitor the changes in the water level of the entire reservoir.
[0021] Among them, rainfall sensors are used to measure rainfall per unit time, usually using a tipping bucket or weighing principle. Such sensors are mainly installed in open areas around reservoirs and major catchment areas to monitor rainfall in the entire catchment area. In practical applications, the number and distribution of rainfall sensors need to take into account the catchment area and terrain characteristics of the reservoir. For example, for a large reservoir, several rainfall sensors may be installed at key locations such as near the confluence of its upstream tributaries, highlands and plains around the reservoir, etc., to fully capture the spatial distribution characteristics of rainfall.
[0022] Among them, flow velocity sensors are used to measure water flow velocity. Common types include electromagnetic flow meters, acoustic Doppler flow meters, etc. Such sensors are mainly installed at the main water inlets and outlets of the reservoir, as well as some important internal waterways. The layout of flow velocity sensors needs to take into account the hydrological characteristics and main water flow channels of the reservoir. In a typical reservoir monitoring system, several flow velocity sensors may be installed at each main water inlet, outlet, and key water flow channels inside the reservoir to monitor water flow dynamics and provide important data support for water balance calculations and flood warnings.
[0023] Among them, temperature and humidity sensors are used to measure water temperature and surrounding air humidity, usually using thermistors or capacitive sensors. This type of sensor plays an auxiliary role in reservoir monitoring, and is mainly used to evaluate the thermodynamic properties of the reservoir and the surrounding meteorological conditions. Temperature and humidity sensors are usually distributed at different water depths and surrounding areas of the reservoir. In practical applications, water temperature sensors may be installed at multiple water depths at different locations in the reservoir, and air temperature and humidity sensors may be installed on the land around the reservoir. The above arrangement helps to monitor water temperature stratification and evaluate water surface evaporation, providing additional reference data for reservoir water balance calculations.
[0024] Specifically, the system can access the database or management system of the reservoir monitoring system to obtain the location coordinates and quantity statistics of various types of sensors such as water level sensors, rainfall sensors, flow rate sensors, and temperature and humidity sensors that have been deployed. This information is usually stored in the form of spreadsheets, database records, or geographic information system (GIS) data, including the precise geographic coordinates of each sensor and the total number of each type of sensor.
[0025] Obtaining the arrangement of sensors can provide necessary reference for subsequent sampling frequency adjustments. By fully understanding the spatial distribution and number of sensors, the system can better determine the optimal sampling frequency for each sensor in subsequent steps. For example, for densely distributed areas, the system may consider reducing the sampling frequency of a single sensor to avoid data redundancy; while for key areas with sparse sensor coverage, the sampling frequency of sensors in these areas may be increased to ensure sufficient data accuracy. At the same time, based on the distribution of different types of sensors, the system can set a higher sampling frequency for sensors in areas sensitive to water level changes.
[0026] S102: Determine a first sampling frequency of each sensor according to the location, quantity and reservoir information of each type of sensor.
[0027] The reservoir information refers to a series of parameters and data describing the physical characteristics and environmental conditions of the reservoir, which can be understood as key characteristic data such as the reservoir's geometric shape, area size, capacity, geographical location, and surrounding terrain in the present application embodiment.
[0028] The first sampling frequency refers to the data collection frequency initially set by the system for each sensor. In the embodiment of the present application, it can be understood as the initial data collection time interval calculated based on the sensor layout and reservoir characteristics.
[0029] Specifically, the first sampling frequency indicates the number of times each sensor collects data per unit time, usually in Hertz, or expressed as the number of samples per hour or day. The above frequency is the initial value calculated by the system through a specific algorithm based on factors such as the location and number of sensors and the shape and area of the reservoir.
[0030] The first sampling frequency is used to guide the data collection behavior of each sensor, ensuring that the system can obtain various parameters of the reservoir at appropriate time intervals. Reasonable first sampling frequency setting can ensure data quality while avoiding resource waste caused by oversampling.
[0031] For example, for areas where the water level changes rapidly, a higher first sampling frequency may be set; while for areas where the water level changes slowly, a lower frequency may be used. Through the above differentiated frequency settings, the system can allocate monitoring resources more effectively and improve overall monitoring efficiency.
[0032] It should be noted that the first sampling frequency is not fixed. The system will dynamically adjust the sampling frequency based on the subsequently collected data and prediction results to adapt to changes in reservoir conditions.
[0033] Based on the above embodiment, as an optional embodiment, the reservoir information includes the reservoir shape and the reservoir area. In S101, the step of determining the first sampling frequency of each sensor according to the location, quantity and reservoir information of each type of sensor may further include the following steps: S201: Determine the standard location and standard quantity of each type of sensor according to the shape and area of the reservoir.
[0034] Among them, the reservoir shape refers to the geometric characteristics and contours of the reservoir water surface on the plane projection. In the embodiment of the present application, it can be understood as the plane geometric shape characteristics of the reservoir, which is usually quantified by the shape coefficient. The shape coefficient is a dimensionless parameter used to characterize the degree of deviation of the plane shape of the reservoir from the standard geometric shape, which can be defined by the ratio of the square of the perimeter of the reservoir to the area or the ratio of the maximum length of the reservoir to the maximum width.
[0035] In the embodiment of the present application, the shape of the reservoir is mainly used to evaluate the rationality of the existing sensor layout and provide a basis for adjusting the sampling frequency. Reservoirs of different shapes may lead to spatial inhomogeneity of hydrological changes, which directly affects the representativeness of the deployed sensors and the effectiveness of data collection.
[0036] For example, in a long and narrow reservoir, sensors at different locations may require different sampling frequencies to accurately capture local hydrological changes. By considering the shape of the reservoir, the embodiment of the present application can more accurately calculate the deviation coefficient of the sensor layout, which is the basis for subsequent adjustment of the sampling frequency. The system can set differentiated sampling frequencies for sensors at different locations according to the shape characteristics of the reservoir to compensate for possible deficiencies in the sensor layout.
[0037] Correspondingly, the reservoir area refers to the size of the coverage of the reservoir water surface on the plane projection. In the embodiment of the present application, it can be understood as the water surface area of the reservoir at the normal water storage level, usually expressed in square kilometers or hectares. The reservoir area is a direct reflection of the scale of the reservoir, reflecting the water storage capacity and scope of influence of the reservoir.
[0038] In the embodiments of the present application, the reservoir area is mainly used to evaluate the coverage density of the existing sensor network and the rationality of the sampling strategy. Reservoirs with larger areas usually require more sensors or higher sampling frequencies to ensure the comprehensiveness of monitoring, while reservoirs with smaller areas may require relatively fewer data collection points or lower sampling frequencies. As an important parameter for calculating the sensor layout deviation coefficient, the reservoir area directly affects the sampling frequency adjustment strategy.
[0039] For example, for a large reservoir, even if the number of sensors is relatively sufficient, the system may increase the sampling frequency of sensors at certain key locations to compensate for the lack of spatial coverage. On the contrary, for a small reservoir, the system may reduce the sampling frequency of some sensors to avoid data redundancy. By combining reservoir area information, this scheme can more accurately evaluate the effectiveness of the existing sensor layout and optimize the sampling frequency accordingly, thereby improving the efficiency and representativeness of data collection without changing the physical layout of the sensors.
[0040] According to the shape and area of the reservoir, the standard location and standard number of each type of sensor are determined. The purpose of this step is to establish an ideal sensor layout reference model as a benchmark for evaluating the actual sensor layout. The shape and area of the reservoir are key factors affecting the efficiency of sensor distribution because they determine the spatial characteristics of hydrological changes and the difficulty of monitoring. By considering these factors, a standard sensor configuration scheme that best reflects the characteristics of the reservoir can be developed, providing a scientific basis for subsequent adjustments to the sampling frequency. In specific implementation, the system first analyzes the shape characteristics of the reservoir, which may be quantified through shape coefficients, such as circularity or slenderness ratio.
[0041] For example, for a nearly circular reservoir, the standard positions may be evenly distributed, while for a narrow and long reservoir, the standard positions may be denser along the main axis. The area of the reservoir directly affects the determination of the number of standards. Generally, the larger the area, the more standard sensors are required to ensure adequate spatial coverage.
[0042] When determining the standard locations, the system may use grid division or key point identification methods. For example, the reservoir area can be divided into several grids, and the center point of each grid is used as a potential standard sensor location. For water level sensors, standard locations may include the vicinity of the dam, the main inlet and outlet, and different depth areas of the reservoir.
[0043] The determination of standard quantities is usually based on hydrological theory and practical experience. The system may use a preset algorithm to substitute parameters such as reservoir area and shape coefficient into a specific formula for calculation.
[0044] Exemplarily, the standard position of the water level sensor is determined by the key point identification method. First, the system sets the vicinity of the dam, the main water inlet and the water outlet as required positions. Then, representative positions are selected in different depth areas according to the depth distribution of the reservoir. Specifically, the system divides the reservoir into shallow water areas (water depth is less than 1 / 3 of the maximum water depth), medium water areas (water depth is between 1 / 3 and 2 / 3 of the maximum water depth) and deep water areas (water depth is greater than 2 / 3 of the maximum water depth), and selects several representative points in each area. The standard number of water level sensors can be calculated by the following formula: ; In the formula, A represents the reservoir area, S is the shape coefficient, and k w is the density coefficient, ceil() means rounding up.
[0045] The grid division method can be used for the standard location of rainfall sensors. The system divides the reservoir and its surrounding catchment area into hexagonal grids of equal area, and the center point of each grid is used as a potential standard location. The size of the grid is dynamically adjusted according to the area of the reservoir to ensure coverage of the entire catchment area.
[0046] The standard location of flow sensors is based on the flow characteristics. The system sets standard locations at major water inlets, outlets, narrow areas of the reservoir body, and areas where the flow direction changes significantly. For large reservoirs, standard locations are also set at key sections of major waterways. The standard number of flow sensors can be calculated using the following formula: ; Where, L in and L out Respectively represent the sum of the lengths of the main inlet and outlet, k fRepresents the density coefficient.
[0047] For the standard locations of temperature and humidity sensors, a stratified sampling method is used. In the horizontal direction, the system selects representative locations in different areas of the reservoir, such as the nearshore area, the central area, the water inlet area, and the water outlet area. In the vertical direction, standard locations are selected in the surface layer, the thermocline layer, and the bottom layer.
[0048] S202: Compare the position and quantity of each type of sensor with the standard position and standard quantity to determine the position error and quantity error of each type of sensor.
[0049] After determining the standard position and standard number of each type of sensor, this embodiment further compares the actual deployed sensor position and number with these standards to determine the position error and quantity error of each type of sensor. This quantitatively evaluates the difference between the existing sensor layout and the ideal layout, providing a basis for subsequent sampling frequency adjustment. By determining the position error and quantity error of the sensor, weak links and over-coverage areas in the monitoring network can be identified, so that the data collection strategy can be optimized by adjusting the sampling frequency without changing the physical layout.
[0050] S203: Calculate the deviation coefficient of each sensor according to the position error and quantity error of each type of sensor, and determine whether the deviation coefficient is greater than or equal to the coefficient threshold.
[0051] Among them, the deviation coefficient is an important evaluation indicator used to quantify the degree to which each sensor deviates from the ideal layout. The deviation coefficient can be defined as a comprehensive measure of the deviation of a single sensor from the ideal state in terms of spatial layout and quantity distribution. In an embodiment of the present application, the deviation coefficient can be understood as a dimensionless indicator that combines position error and quantity error. It reflects the degree of deviation of a single sensor from its ideal layout, while also taking into account the appropriateness of the overall number of sensors of this type. The above coefficients not only reflect the position deviation of the sensor itself, but also include the distribution of its type in the overall monitoring network.
[0052] Based on the above embodiment, as an optional embodiment, the method for calculating the deviation coefficient may specifically include the following steps: Substituting the position error and quantity error of each type of sensor into the first preset formula to obtain the deviation coefficient of each sensor; Among them, the first preset formula is: ; in, represents the deviation coefficient, A represents the reservoir area, S represents the reservoir shape factor, N represents the total number of sensors, represents the standard position of the i-th sensor, represents the actual position of the i-th sensor, M represents the number of sensor types, represents the quantity error weight of the j-th type of sensor, represents the standard number of sensors of the jth type, represents the actual number of sensors of the jth type, and α and β represent the corresponding weight coefficients respectively.
[0053] Among them, the basis for setting the first preset formula is derived from a comprehensive consideration of the sensor layout in the reservoir monitoring system, aiming to create a comprehensive indicator that can accurately reflect the quality of sensor network deployment. The design of the first preset formula fully considers two key aspects of sensor layout: the accuracy of spatial distribution and the rationality of the number of sensors of each type, so it is divided into two main parts, corresponding to location error and quantity error respectively.
[0054] Among them, the location error part is set to accurately evaluate the spatial distribution quality of the sensor network while taking into account the differences in scale and shape of different reservoirs.
[0055] Among them, the Euclidean distance is first used To quantify the position deviation of each sensor. Euclidean distance is the straight-line distance between two points in three-dimensional space, which directly reflects the spatial deviation between the actual position of the sensor and the ideal position. It can accurately capture the position offset of the sensor in the horizontal and vertical directions.
[0056] By summing the position deviations of all sensors, we can get the overall position error of the entire sensor network. This sum reflects the spatial distribution of the entire system and includes the position information of all sensors. If the position deviation of some sensors is large, they can make a greater contribution to the sum and thus receive more attention in the final evaluation.
[0057] The purpose of dividing the overall location error by the ratio of the reservoir area to the reservoir shape factor is to standardize the location error so that the results are comparable between reservoirs of different sizes and shapes. The reservoir area divided by the shape factor can be considered the characteristic scale of the reservoir, and the above ratio has the dimension of length, the same as the dimension of the location error.
[0058] Specifically, the reservoir area reflects the overall size of the reservoir. Obviously, in a large reservoir, the position deviation of the sensor may be large in absolute value, but it may not be significant relative to the scale of the reservoir. The shape factor reflects the geometric characteristics of the reservoir. For example, a long and narrow reservoir and a nearly circular reservoir may have very different reasonable sensor arrangements even if they have the same area.
[0059] By dividing by the ratio of the reservoir area to the reservoir shape coefficient, the position error is actually relativized. After processing, reservoirs of different sizes and shapes can be compared under the same standard. For example, in a large reservoir, a position deviation of 5 meters may be acceptable, while in a small reservoir, the same 5-meter deviation may lead to significant monitoring errors. Through the above standardization, a dimensionless ratio can be obtained, which better reflects the importance of the position error relative to the characteristic scale of the reservoir.
[0060] The above design also takes into account the complexity of the reservoir. The reservoir not only has different shapes in the plane, but also has depth changes in the vertical direction. By using the Euclidean distance and the characteristic scale of the reservoir, the above formula can evaluate the position error of the sensor in three-dimensional space, thereby more comprehensively reflecting the spatial distribution quality of the sensor network.
[0061] For example, take China's Three Gorges Reservoir, one of the largest water conservancy projects in the world, with a reservoir area of about 1,084 square kilometers, long and narrow, spanning multiple provinces. In such a large-scale reservoir, the layout of sensors directly affects the hydrological monitoring, ecological assessment and flood control scheduling of the entire basin. For a large reservoir like the Three Gorges, even if the actual location of the sensor differs from the planned location by a few hundred meters, the impact may not be significant relative to the scale of the entire reservoir. For a small mountain reservoir, such as the Baihua Lake Reservoir in Guizhou, which covers an area of only about 4 square kilometers, the same position deviation may cause serious distortion of monitoring data.
[0062] The first preset formula uses Euclidean distance to quantify position deviation, which is particularly important in practical applications. For example, in water quality monitoring, certain sensors need to be precisely positioned at a specific depth and location in a reservoir to capture water stratification or monitor specific pollution sources. Euclidean distance can reflect both horizontal and vertical deviations, providing a guarantee for precise positioning in three-dimensional space.
[0063] The sum of all sensor position deviations reflects the overall quality of the entire monitoring network. In practice, the above sum can help managers quickly determine whether a comprehensive adjustment of the sensor network is needed. For example, if the sum suddenly increases, it may mean that some sensors have been displaced due to water flow impact or human interference, and need to be checked and repositioned immediately.
[0064] Dividing the overall position error by the ratio of the reservoir area to the reservoir shape coefficient reflects the adaptability to different types of reservoirs in practical applications. For example, comparing the Xiluodu Reservoir in the upper reaches of the Yangtze River (an area of about 246 square kilometers) and the Xinfengjiang Reservoir in Guangdong (an area of about 370 square kilometers), although the Xinfengjiang Reservoir is larger, its shape is closer to a circle, so it may require fewer sensors to achieve effective coverage than the long and narrow Xiluodu Reservoir. By introducing the shape coefficient S, the formula takes into account the above differences, allowing for a fairer comparison of reservoirs of different shapes when evaluating sensor placement.
[0065] Furthermore, in reservoirs with significant seasonal changes, such as the Poyang Lake Reservoir in the middle and lower reaches of the Yangtze River, the water level and area vary greatly during the flood season and the dry season. In the above case, the position error assessment of the sensor is particularly important. When the water level is low, some sensors originally designed for deep water areas may be exposed to the air and lose their monitoring function. By using standardized position error indicators, the system can detect problems in a timely manner and adjust the application strategy of the sensor in a timely manner to ensure that effective monitoring coverage can be maintained under different water level conditions.
[0066] Among them, the quantity error part mainly provides a scientific basis for the optimization of the reservoir monitoring system by accurately quantifying the deviation of the number of sensor configurations. First, the quantity error part calculates the difference in the number of sensors of each type. The absolute value representation directly reflects the degree of deviation between the number of sensors actually deployed and the ideal configuration. In reservoir monitoring, whether the number of sensors is more or less than the standard configuration, it may have a negative impact on the monitoring effect. For example, insufficient number of water level sensors may lead to monitoring blind spots in certain key areas, while too many sensors may cause data redundancy, increase system complexity and maintenance costs. By using absolute values, it can be ensured that both positive and negative deviations will be given equal attention, avoiding the misjudgment caused by positive and negative offsets.
[0067] However, in actual reservoir monitoring, different types of sensors often have different degrees of influence on the overall monitoring effect. Therefore, weight coefficients are further introduced. For example, for a reservoir mainly used for flood control, water level sensors and rainfall sensors may be given higher weights because these data are crucial for flood warning. In contrast, in a reservoir mainly used for power generation, in addition to water level sensors, flow rate sensors may receive higher weights because water flow velocity is directly related to power generation efficiency. By adjusting these weights, reservoirs of different types and uses can be adapted, and the versatility of application to different types of reservoirs can be enhanced. After multiplying the quantity difference by the weight, the quantity error part sums the weighted quantity errors of all types of sensors. Integrating the evaluation results of each local area into a global indicator provides an overall evaluation at the system level.
[0068] In an exemplary scenario, taking the Three Gorges Reservoir as an example, its main functions are concentrated on flood control and power generation. Therefore, in the sensor weight distribution, water level sensors and flow rate sensors are given the highest importance, because water level is directly related to flood control capabilities and power generation potential, and is the most critical monitoring parameter. The weight of the water level sensor can be set to 0.35. Water level sensors will be densely arranged in key locations such as near the dam, at the entrance of major tributaries, and in the middle of the reservoir. The flow rate sensor can be set with a weight of 0.3, mainly considering its direct impact on power generation efficiency and its important role in flood control scheduling. These sensors are usually arranged near the main waterways and turbine entrances. The rainfall sensor can be set to 0.25, because it is crucial to predict the amount of water entering the reservoir and directly affects flood control decisions. In contrast, the temperature and humidity sensor has a lower weight and can be set to a weight of 0.1. It is mainly used to assist in predicting evaporation and potential rainfall, and its impact is relatively small.
[0069] The first preset formula also introduces two weight coefficients, α and β, to balance the contribution of position error and quantity error to the final deviation coefficient. In different reservoir monitoring scenarios, the importance of sensor location accuracy and quantity configuration may vary significantly. For example, in a small experimental reservoir used for precise hydrological research, the precise positioning of sensors may be more critical than the quantity. In this case, we may set a larger α value and a smaller β value to ensure that the position error dominates the final deviation coefficient. On the contrary, in a large multi-functional reservoir, in order to obtain comprehensive monitoring coverage, the number and distribution of sensors may be more important than the precise location of a single sensor. In this case, the β value can be increased and the α value can be reduced to consider the impact of quantity errors more.
[0070] For example, in a small experimental reservoir for precision hydrological research, the precise positioning of sensors may be more critical than the number. In the above scenario, a larger α of 0.8 and a smaller β of 0.2 can be set to ensure that the position error dominates the final deviation coefficient. On the contrary, in a large multi-functional reservoir, in order to obtain comprehensive monitoring coverage, the number and distribution of sensors may be more important than the precise location of a single sensor. In the above scenario, the β value can be increased to 0.7 and the α value can be reduced to 0.3 to take more account of the impact of the number error.
[0071] By adjusting α and β, the system can optimize the evaluation criteria according to the specific monitoring objectives and reservoir characteristics. For example, during the flood season, the β value may be increased to ensure that a sufficient number of sensors are used to comprehensively monitor water level changes. During the dry season, the α value may be increased to focus more on accurate monitoring of key locations.
[0072] In addition, the settings of α and β can be adjusted dynamically over time. For example, in the early stages of reservoir operation, more attention may be paid to the precise positioning of the sensor, so a larger α value is set. With the accumulation of operating experience and a deeper understanding of reservoir characteristics, these weights may be gradually adjusted to optimize the overall monitoring effect.
[0073] S204: If the deviation coefficient is greater than or equal to the coefficient threshold, determining a first sampling frequency of each sensor according to the position error and quantity error of each type of sensor.
[0074] Specifically, when the deviation coefficient is greater than or equal to the coefficient threshold, the system will determine the first sampling frequency of each sensor according to the position error and quantity error of each type of sensor, thereby optimizing the data collection strategy.
[0075] Based on the above embodiment, as an optional embodiment, in S204: the step of determining the first sampling frequency of each sensor according to the position error and quantity error of each type of sensor may further include the following steps: S301: Determine the sampling frequency range of each type of sensor according to the position error and quantity error of each type of sensor.
[0076] The sampling frequency range refers to the upper and lower limits of a sampling frequency set for a specific type of sensor. In the embodiment of the present application, it can be understood as a frequency range calculated based on the position error and quantity error of the sensor, which limits the minimum and maximum sampling frequencies that can be used by this type of sensor. The sampling frequency range is used to provide a reasonable selection space for the subsequent determination of the first sampling frequency of each specific sensor.
[0077] In a feasible implementation, the system may need to determine the sampling frequency range of each type of sensor according to the position error and quantity error of each type of sensor. The system may calculate a suitable sampling frequency range for each type of sensor through an algorithm preset by a second preset formula.
[0078] Among them, the second preset formula is: F range =[F base +k1*(P error / P max )+k2*(N error / N std ), F max ] In the formula, F base is the basic sampling frequency, P error is the position error, P max is the maximum allowable position error, N error is the quantity error, N stdis the standard quantity, k1 and k2 are weight coefficients, F max is the highest sampling frequency allowed. Through the second preset formula, the system can dynamically adjust its sampling frequency range according to the actual arrangement of the water level sensor.
[0079] The above-mentioned method for determining the sampling frequency range based on position error and quantity error not only takes into account the actual situation of sensor layout, but also provides the system with sufficient flexibility to cope with the complexity and dynamic changes of the reservoir environment. For example, when the flood season is predicted to be approaching, the system can quickly increase the sampling frequency range of all types of sensors by adjusting the parameters in the formula to cope with possible emergencies; in the dry season, the sampling frequency range can be appropriately reduced to save energy and storage resources. This adaptive sampling strategy can significantly improve the overall efficiency of the monitoring system, while ensuring data quality and optimizing resource utilization. By determining a reasonable sampling frequency range for each type of sensor, the system lays the foundation for subsequent refined frequency adjustment, enabling the monitoring network to better adapt to the complex environment of the reservoir and provide more accurate and timely data support, thus making important contributions to the safe management and efficient operation of the reservoir.
[0080] In a feasible implementation, after calculating the deviation coefficient, the system can determine the sampling frequency range according to a preset mapping relationship. For example, the system may use the following mapping relationship: deviation coefficient 0-1: sampling frequency range 1-5Hz; deviation coefficient 1-2: sampling frequency range 5-10Hz; deviation coefficient 2-3: sampling frequency range 10-20Hz; deviation coefficient>3: sampling frequency range above 20Hz.
[0081] The above method allows the system to flexibly adjust the sampling strategy according to the actual situation of sensor layout. In large reservoirs, since sensors are difficult to install accurately in standard positions and the number may be insufficient, the system may set a higher sampling frequency range for sensors in key areas such as inlets or outlets to ensure that rapidly changing hydrological parameters can be captured. In reservoirs with complex terrain, the distribution of sensors may be uneven and the position error may be large. The system will identify areas that require high sampling frequencies through error calculations, such as setting a higher sampling frequency range in narrow areas or areas with faster flow changes to ensure data accuracy.
[0082] S302: Determine a first sampling frequency of each sensor within a sampling frequency range according to the position of each sensor.
[0083] Specifically, after the sampling frequency range of each type of sensor is determined, the system needs to further determine the first sampling frequency of each specific sensor within the determined sampling frequency range according to the position of the sensor.
[0084] For example, for water level sensors, the system may adopt the following strategy: For sensors located at the entrance, exit, or in areas where water flow changes dramatically, the system tends to select higher frequency values within the sampling frequency range. Because these locations are usually areas where water levels change fastest and most significantly, more frequent data collection is required to accurately capture hydrological changes. Specifically, if a water level sensor is located at the main water inlet and its sampling frequency range is 5-15Hz, the system may specify a sampling frequency of 12Hz or higher for it. In contrast, for water level sensors located in relatively static areas of the reservoir, the system may choose a lower sampling frequency, such as 7Hz, because water levels in these areas usually change slowly.
[0085] For flow velocity sensors, the system pays special attention to those located in water flow constrictions, rapids, or where the shape of the reservoir changes suddenly. The flow velocity changes at these locations are usually more dramatic and complex, requiring a higher sampling frequency to accurately record the flow characteristics. For example, if a flow velocity sensor is located in a narrow waterway and its sampling frequency range is 10-20Hz, the system may specify a sampling frequency of 18Hz or higher.
[0086] The first sampling frequency of the temperature and humidity sensor may be determined by considering its vertical position more. For example, a temperature sensor close to the water surface may be assigned a higher sampling frequency because the surface water temperature is greatly affected by the external environment and changes rapidly; while a temperature sensor in a deep water area may use a lower sampling frequency because the deep water temperature is usually more stable.
[0087] Through the above location-based refined sampling frequency determination method, the system can allocate monitoring resources more flexibly and efficiently. For key locations or areas where data changes rapidly, the system sets a higher sampling frequency to ensure that important hydrological changes are captured; while for areas with slower changes or less important areas, a lower sampling frequency can be used to save energy and data storage resources.
[0088] S205: If the deviation coefficient is less than the coefficient threshold, the preset sampling frequency is used as the first sampling frequency.
[0089] Specifically, when the deviation coefficient is less than the coefficient threshold, it means that the existing monitoring network is already quite close to the optimal configuration and there is no need to perform complex frequency adjustment.
[0090] S103: Acquire first reservoir data collected by each sensor at a first sampling frequency at a first time.
[0091] Specifically, after determining the first sampling frequency of each sensor, the system enters the actual data collection phase. The system first sends a sampling instruction to all sensors, specifying each sensor to start data collection according to its first sampling frequency.
[0092] For example, a water level sensor may be instructed to record water level data every 10 minutes, while a rainfall sensor may record rainfall every 5 minutes. At the first time, that is, the synchronization start time point specified by the system, all sensors simultaneously start to collect data according to their respective first sampling frequencies. This synchronous sampling method ensures the time consistency between different types of data, which is conducive to subsequent comprehensive analysis. The collected first reservoir data usually includes multiple parameters such as water level, rainfall, flow rate, water temperature, etc., which will be transmitted to the central data processing system in real time.
[0093] The system will conduct a preliminary quality check on the received data, remove obviously abnormal data points, and perform necessary unit conversion and standardization. For areas with faster or more important changes in the reservoir, a higher sampling frequency can capture more detailed changes; while for areas with slower changes, a lower sampling frequency can reduce redundant data and save storage and processing resources.
[0094] S104: Predicting a first water level of the reservoir after a preset period of time based on the first reservoir data and historical reservoir data in the database.
[0095] Based on the above embodiment, as an optional embodiment, in S104: the step of predicting the first water level of the reservoir after a preset time period according to the first reservoir data and the historical reservoir data in the database may specifically include the following steps: S401: Compare the first reservoir data with the historical reservoir data in the database to determine the target reservoir data with the highest similarity in the historical reservoir data.
[0096] Specifically, the system first needs to preprocess the data of the first reservoir, including data cleaning, standardization and feature extraction. Data cleaning can remove outliers and fill missing values, and standardization ensures that different types of data can be compared on the same scale. During the feature extraction process, the system may calculate some derived features, such as water level change rate, flow rate, etc. Next, the system uses a predefined similarity calculation method to compare the data of the first reservoir with each set of historical records in the historical database. The similarity calculation can be performed using Euclidean distance. The system calculates the distance between the first reservoir data and each set of historical data in the multidimensional feature space. The historical data with the smallest distance is considered to have the highest similarity.
[0097] Based on the above embodiment, as an optional embodiment, in S401: comparing the first reservoir data with the historical reservoir data in the database to determine the target reservoir data with the highest similarity in the historical reservoir data, this step may further include the following steps: S501: Extracting feature vectors from the data collected by each type of sensor in the first reservoir data, the feature vectors include periodic feature vectors, trend feature vectors and temporary feature vectors, and the types of sensors include water level sensors, rainfall sensors, flow rate sensors and temperature and humidity sensors.
[0098] Among them, the feature vector refers to a set of numerical values used to describe the key attributes of a data object. In the embodiment of the present application, it can be understood as a numerical sequence that can reflect the characteristics of the reservoir state extracted from the raw data collected by various types of sensors. The feature vector is used to convert complex multi-dimensional raw data into a more concise and representative data form, which is convenient for subsequent data analysis and similarity calculation. In the embodiment of the present application, the feature vector mainly includes three types: periodic feature vectors, trend feature vectors, and temporary feature vectors.
[0099] Among them, the periodic feature vector refers to a numerical sequence that describes the regular change pattern that recurs in the data. In the embodiment of the present application, it can be understood as a set of numerical values that reflects the periodic changes in various parameters of the reservoir, such as the daily periodic fluctuation of the water level, the seasonal change pattern of rainfall, etc. The periodic feature vector is used to capture the regular changes in the state of the reservoir, which helps the system to identify and predict the conventional hydrological change pattern and provide a basis for the daily management and scheduling of the reservoir.
[0100] Among them, the trend feature vector refers to a numerical sequence that describes the direction and amplitude of long-term changes in data. In the embodiment of the present application, it can be understood as a set of numerical values that reflects the long-term change trend of various parameters of the reservoir, such as the interannual change trend of water level, the seasonal change trend of flow rate, etc. The trend feature vector is used to identify the continuous changes in the state of the reservoir, which helps the system predict the long-term evolution trend of the reservoir.
[0101] Among them, the temporary feature vector refers to a numerical sequence that describes sudden events or short-term abnormalities in the data. In the embodiment of the present application, it can be understood as a numerical set that reflects sudden changes or short-term abnormalities in various parameters of the reservoir, such as a sharp rise in water level caused by a rainstorm, abnormally low water level during a drought, etc. The temporary feature vector is used to capture sudden changes and abnormalities in the state of the reservoir, which helps the system quickly identify potential risks and emergencies.
[0102] Exemplarily, the process of extracting periodic feature vectors is as follows: For water level sensor data, the system focuses on the daily and annual cycle change patterns. Through methods such as Fourier transform or wavelet analysis, the system identifies the main periodic components of water level changes. Daily cycle characteristics may reflect tidal effects or daily reservoir operation patterns, while annual cycle characteristics may reflect the impact of seasonal precipitation and water use patterns. The system extracts the amplitude and phase information of these periodic components as periodic feature vectors of water level sensors; The periodic feature extraction of rainfall sensor data focuses on identifying daily rainfall patterns and seasonal rainfall patterns. The system analyzes the temporal distribution of rainfall, identifies the peak and trough periods of daily rainfall, and the changes in rainfall intensity in different months of the year. These features can reflect local climate characteristics and rainfall patterns, and are crucial for predicting short-term and medium-term rainfall in the future; The periodic feature extraction of flow sensor data focuses on discovering intraday flow velocity variation patterns and seasonal flow velocity variation patterns. The system analyzes the daily variation of flow velocity, which may reflect the periodic influence of reservoir operation or upstream water. At the same time, the system also extracts seasonal flow velocity variation characteristics, which may be related to seasonal precipitation or snowmelt processes; The periodic feature extraction of temperature and humidity sensor data mainly focuses on the daily temperature difference change pattern and the seasonal temperature and humidity change pattern. The system analyzes the daily change pattern of temperature and humidity and extracts features such as daily temperature difference and daily humidity change range. At the same time, the system also identifies the seasonal change pattern of temperature and humidity, which is of great reference value for predicting water evaporation and possible precipitation.
[0103] Exemplarily, the process of extracting periodic feature vectors is as follows: For water level sensor data, the system focuses on long-term water level change trends, seasonal trends, and fluctuation trends. Long-term trends reflect the overall change direction of reservoir water levels, which may be affected by factors such as climate change, changes in upstream water, or human regulation. Seasonal trends reflect the cyclical change pattern of water levels within a year, such as rising water levels during flood season and falling water levels during dry season. Fluctuation trends reflect the irregularity of water level changes, which may be related to short-term weather changes or emergencies; The trend feature extraction of rainfall sensor data focuses on the long-term rainfall change trend, seasonal rainfall pattern change and rainfall intensity change trend. The system analyzes the long-term change trend of rainfall, which may reflect the impact of climate change. At the same time, the system also extracts the change trend of seasonal rainfall pattern, such as the change of the start time of the rainy season and the change of rainfall concentration. In addition, the system also analyzes the change trend of rainfall intensity, such as the change of the frequency of extreme rainfall events; The trend feature extraction of flow sensor data focuses on analyzing the long-term flow rate change trend, seasonal flow rate pattern change and flow rate fluctuation trend. The long-term flow rate change trend may reflect the change of water inflow upstream of the reservoir or the adjustment of reservoir operation strategy. The seasonal flow rate pattern change may be related to the change of rainfall pattern or the operation of upstream reservoir group. The flow rate fluctuation trend may reflect the increase or decrease of hydrological instability; The trend feature extraction of temperature and humidity sensor data mainly includes long-term temperature and humidity change trends, seasonal temperature and humidity pattern changes, and extreme temperature and humidity event trends. Long-term temperature and humidity change trends may reflect the impact of climate change. Seasonal temperature and humidity pattern changes may reflect the early or late transition of seasons. Extreme temperature and humidity event trends may reflect changes in the frequency of extreme weather.
[0104] Exemplarily, the temporary feature vector extraction process is as follows: For water level sensor data, the system focuses on sudden water level changes. By calculating the rate of change of water level over a short period of time, the system can identify abnormal water level rise or fall. This may indicate the sudden arrival of a flood or an emergency such as a reservoir discharge. The system also analyzes the acceleration of water level change to capture sudden changes in the speed of water level change; Temporal feature extraction of rainfall sensor data focuses on identifying short-term heavy rainfall events. The system calculates the cumulative rainfall and rainfall intensity in a short period of time and compares them with historical thresholds to identify heavy rain events that may cause sudden floods. At the same time, the system also pays attention to sudden changes in rainfall patterns, such as sudden rainfall after a prolonged drought; Temporary feature extraction of flow sensor data focuses on detecting rapid changes in flow velocity. The system analyzes the rate of change and change pattern of flow velocity in a short period of time to identify sudden changes in flow velocity that may be caused by upstream flood discharge, tributary inflow, or reservoir operation. The above information is crucial for predicting water level changes in the short term and conducting emergency operations; Temporary feature extraction of temperature and humidity sensor data focuses on abnormal changes in temperature and humidity in the short term. The system will identify a sharp rise or fall in temperature, which may indicate the arrival of extreme weather events. At the same time, the system will also pay attention to sudden changes in humidity, which may be related to upcoming rainfall or drought.
[0105] S502: Calculate the similarity between the feature vector of the first reservoir data and each group of feature vectors in the historical reservoir data.
[0106] Specifically, the feature vector of the first reservoir data and each group of feature vectors in the historical reservoir data may be substituted into a similarity calculation formula to obtain the similarity between the first reservoir data and each group of data in the historical reservoir data; The similarity calculation formula includes: ; In the formula, Represents the similarity between the feature vector of the first reservoir data and a set of feature vectors in the historical reservoir data, Represent the periodic feature vectors of the current data and historical data of the i-th sensor, Represent the trend feature vectors of the current data and historical data of the i-th sensor, Represent the temporary feature vectors of the current data and historical data of the i-th sensor, Respectively represent the weights of periodic features, trend features and temporary features.
[0107] in, ; In the formula, represents the Euclidean distance; Furthermore, ; In the formula, m represents the dimension of the feature vector, represents the jth periodic eigenvalue of the i-th sensor.
[0108] ; ; In the formula, Represents the jth trend characteristic value of the i-th sensor.
[0109] ; ; In the formula, Represents the jth temporary eigenvalue of the i-th sensor.
[0110] S503: Taking a group of data with the highest similarity in the historical reservoir data as target reservoir data.
[0111] S402: Calculate the rate of change of the water level according to the first reservoir data and the target reservoir data.
[0112] Specifically, the system first needs to determine an appropriate time window to calculate the rate of change. The selection of the above time window requires a trade-off between short-term fluctuations and long-term trends: a time window that is too short may over-amplify short-term fluctuations, while a time window that is too long may mask important short-term changes. Usually, the system dynamically adjusts the above time window based on the characteristics of the reservoir and the current hydrological and meteorological conditions. For example, during the flood season or when heavy rainfall is expected, a shorter time window may be selected to capture rapid water level changes; while in the dry season, a longer time window may be selected to reflect a more stable trend of change.
[0113] There are many ways to calculate the rate of change of water level. Linear regression can be used to fit a straight line in a selected time window, taking time as the independent variable and water level as the dependent variable through the least squares method. The slope of the straight line is the average rate of change of water level. The linear regression method can smooth short-term fluctuations.
[0114] In practical applications, the system may calculate the change rate of multiple time scales at the same time. For example, the water level change rate in the last 6 hours, 12 hours, 24 hours, and 48 hours can be calculated. This multi-scale calculation method can capture short-term fluctuations and long-term trends at the same time, providing more comprehensive information for subsequent water level forecasts.
[0115] S403: Calculate the first water level after a preset time period according to the reservoir data at the first time and the rate of change of the water level.
[0116] Specifically, the system first extracts the current water level value from the reservoir data at the first time, and then combines this water level value with the previously calculated water level change rate and the preset time length, and uses a simple linear prediction model to calculate the first water level. The prediction formula can be expressed as: H1=H0+R×T, where H1 is the predicted first water level, H0 is the current water level, R is the water level change rate, and T is the preset time length.
[0117] The above linear prediction method assumes that the water level will change at a constant rate within a preset time, which is usually a reasonable assumption in short-term predictions. However, considering the complexity of the hydrological system, the system may also introduce some correction factors to improve the prediction accuracy. For example, the linear prediction results can be appropriately adjusted based on the water level change pattern obtained from historical data analysis. In addition, the system may also consider setting a confidence interval for the prediction to reflect the uncertainty of the prediction results.
[0118] S105: If the first water level is greater than or equal to the threshold, a warning prompt is generated.
[0119] Based on the above embodiment, as a feasible implementation mode, in order to further improve the accuracy of the early warning prompt, S105 may further include the following steps: S601: If the first water level is greater than or equal to a threshold, the first sampling frequency of each sensor is adjusted within a preset range to obtain a second sampling frequency, and the corresponding sensor is controlled according to the second sampling frequency to collect second reservoir data of the reservoir.
[0120] Specifically, when the predicted first water level exceeds or equals the preset threshold, the system will not immediately issue a final warning prompt, but will start a verification mechanism to ensure the accuracy of the warning. The core of this verification mechanism is to obtain more refined data by adjusting the sampling frequency, so as to reconfirm the preliminary warning judgment. The system will adjust the first sampling frequency of each sensor within the preset range to obtain a more intensive second sampling frequency, and control the corresponding sensor to collect a new round of reservoir data, that is, the second reservoir data. By increasing the sampling frequency, the system can obtain more data points, thereby more accurately describing the short-term dynamic changes of the reservoir. This method is particularly helpful in identifying and filtering out short-term abnormal fluctuations that may cause false alarms.
[0121] S602: Predicting a second water level of the reservoir after a preset period of time based on the second reservoir data and historical reservoir data in the database.
[0122] The implementation principle of the above process is the same as that of S104, and will not be elaborated here.
[0123] S603: If the second water level is greater than or equal to the threshold, a warning prompt is generated.
[0124] Specifically, after completing high-frequency sampling and second water level prediction, the system enters the final decision-making stage, that is, judging whether to generate a formal warning prompt based on the second water level prediction results. Specifically, the system will compare the second water level predicted based on the second reservoir data with the pre-set threshold again. This step is a key link in the entire warning verification process, which aims to confirm the authenticity of potential risks through more sophisticated data analysis, thereby improving the accuracy and reliability of the early warning system.
[0125] The system will only generate a formal warning when the second water level is still greater than or equal to the threshold. The design of this double confirmation mechanism is based on an important understanding: the complexity and dynamics of the hydrological system may lead to short-term data fluctuations, and only a sustained over-threshold state can truly reflect potential dangerous situations. By comparing the second water level and the threshold, the system can effectively filter out false warnings caused by temporary factors or data noise, while retaining risk signals that really need attention.
[0126] Reference Figure 2 The present application also provides a database monitoring and processing system for a reservoir, comprising: A sensor information acquisition module is used to obtain the locations and quantities of multiple sensors of different types arranged in the reservoir; A first sampling frequency determination module, used to determine the first sampling frequency of each sensor according to the location, quantity and reservoir information of each type of sensor; A first reservoir data acquisition module, used for acquiring first reservoir data acquired by each of the sensors at the first sampling frequency at the first time; A first water level prediction module, used to predict a first water level of the reservoir after a preset time period based on the first reservoir data and historical reservoir data in a database; The early warning prompt generating module is used to generate an early warning prompt if the first water level is greater than or equal to a threshold.
[0127] On the basis of the above embodiments, as an optional embodiment, the first sampling frequency determination module is also used to determine the standard position and standard number of settings of each type of sensor according to the shape and area of the reservoir; compare the position and number of each type of sensor with the standard position and standard number to determine the position error and number error of each type of sensor; calculate the deviation coefficient of each sensor according to the position error and number error of each type of sensor, and determine whether the deviation coefficient is greater than or equal to a coefficient threshold; if the deviation coefficient is greater than or equal to the coefficient threshold, determine the first sampling frequency of each sensor according to the position error and number error of each type of sensor; if the deviation coefficient is less than the coefficient threshold, use the preset sampling frequency as the first sampling frequency.
[0128] Based on the above embodiment, as an optional embodiment, the first sampling frequency determination module is further used to substitute the position error and quantity error of each type of sensor into the first preset formula to obtain the deviation coefficient of each sensor; Wherein, the first preset formula is: ; in, represents the deviation coefficient, A represents the reservoir area, S represents the reservoir shape factor, N represents the total number of sensors, represents the standard position of the ith sensor, represents the actual position of the i-th sensor, M represents the number of sensor types, represents the quantity error weight of the j-th type of sensor, represents the standard number of sensors of the jth type, represents the actual number of sensors of the jth type, and α and β represent the corresponding weight coefficients respectively.
[0129] On the basis of the above embodiments, as an optional embodiment, the first sampling frequency determination module is also used to determine the sampling frequency range of each type of sensor according to the position error and quantity error of each type of sensor; and determine the first sampling frequency of each sensor within the sampling frequency range according to the position of each sensor.
[0130] On the basis of the above embodiment, as an optional embodiment, the first sampling frequency determination module is also used to adjust the first sampling frequency of each sensor within the preset range to obtain a second sampling frequency if the first water level is greater than or equal to a threshold value, and control the corresponding sensor to collect the second reservoir data of the reservoir according to the second sampling frequency; predict the second water level of the reservoir after a preset time period according to the second reservoir data and historical reservoir data in the database; if the second water level is greater than or equal to the threshold value, generate an early warning prompt.
[0131] On the basis of the above embodiment, as an optional embodiment, the first water level prediction module is also used to compare the first reservoir data with the historical reservoir data in the database to determine the target reservoir data with the highest similarity in the historical reservoir data; calculate the rate of change of the water level based on the first reservoir data and the target reservoir data; calculate the first water level after a preset time period based on the reservoir data at the first time and the rate of change of the water level.
[0132] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0133] The embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executed by a database monitoring and processing method for a reservoir such as the above-mentioned embodiment. The specific execution process can refer to the specific description of the embodiment shown, which will not be repeated here.
[0134] The present application also discloses an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .
[0135] The communication bus 302 is used to realize the connection and communication between the above components.
[0136] The user interface 303 may include a display interface and a camera interface. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.
[0137] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).
[0138] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface diagrams and applications, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.
[0139] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program for a database monitoring and processing method for a reservoir.
[0140] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program stored in the memory 305 for a database monitoring and processing method for a reservoir, and when executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.
[0141] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0142] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0143] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0144] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0145] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.
[0146] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.
[0147] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.
Claims
1. A database monitoring and processing method for a reservoir, characterized in that: include: Obtaining the locations and quantities of multiple sensors of different types set up in the reservoir; Determine a first sampling frequency of each sensor according to the location, quantity and reservoir information of each type of sensor; Acquire first reservoir data collected by each of the sensors at the first sampling frequency at a first time; Predicting a first water level of the reservoir after a preset time period based on the first reservoir data and historical reservoir data in a database; If the first water level is greater than or equal to a threshold, an early warning prompt is generated.
2. The database monitoring and processing method for a reservoir according to claim 1, characterized in that: The reservoir information includes the reservoir shape and the reservoir area. The first sampling frequency of each sensor is determined according to the location, quantity and reservoir information of each type of sensor, including: Determine the standard location and standard quantity of each type of sensor according to the shape and area of the reservoir; Comparing the position and quantity of each type of sensor with the standard position and standard quantity to determine the position error and quantity error of each type of sensor; Calculating a deviation coefficient of each sensor according to a position error and a quantity error of each type of sensor, and determining whether the deviation coefficient is greater than or equal to a coefficient threshold; If the deviation coefficient is greater than or equal to the coefficient threshold, determining a first sampling frequency of each of the sensors according to a position error and a quantity error of each of the types of sensors; If the deviation coefficient is less than the coefficient threshold, the preset sampling frequency is used as the first sampling frequency.
3. The database monitoring and processing method for a reservoir according to claim 2 is characterized in that: Calculating the deviation coefficient of each sensor according to the position error and quantity error of each type of sensor includes: Substituting the position error and quantity error of each type of sensor into a first preset formula to obtain a deviation coefficient of each sensor; Wherein, the first preset formula is: ; in, represents the deviation coefficient, A represents the reservoir area, S represents the reservoir shape factor, N represents the total number of sensors, represents the standard position of the i-th sensor, represents the actual position of the i-th sensor, M represents the number of sensor types, represents the quantity error weight of the j-th type of sensor, represents the standard number of sensors of the jth type, represents the actual number of sensors of the jth type, and α and β represent the corresponding weight coefficients respectively.
4. The database monitoring and processing method for a reservoir according to claim 2, characterized in that: Determining the first sampling frequency of each of the sensors according to the position error and the quantity error of each of the types of sensors comprises: Determining a sampling frequency range of each type of sensor according to a position error and a quantity error of each type of sensor; According to the position of each of the sensors, a first sampling frequency of each of the sensors is determined within the sampling frequency range.
5. The database monitoring and processing method for a reservoir according to claim 4, characterized in that: If the first water level is greater than or equal to a threshold, generating an early warning prompt includes: If the first water level is greater than or equal to a threshold, adjusting the first sampling frequency of each of the sensors within the preset range to obtain a second sampling frequency, and controlling the corresponding sensor to collect second reservoir data of the reservoir according to the second sampling frequency; Predicting a second water level of the reservoir after a preset time period based on the second reservoir data and historical reservoir data in a database; If the second water level is greater than or equal to a threshold, an early warning prompt is generated.
6. The database monitoring and processing method for a reservoir according to claim 1, characterized in that: The predicting, based on the first reservoir data and the historical reservoir data in the database, a first water level of the reservoir after a preset time period, comprises: Compare the first reservoir data with the historical reservoir data in the database to determine the target reservoir data with the highest similarity in the historical reservoir data; Calculating the rate of change of water level according to the first reservoir data and the target reservoir data; A first water level after a preset period of time is calculated based on the reservoir data at the first time and the rate of change of the water level.
7. The database monitoring and processing method for a reservoir according to claim 6, characterized in that: The comparing the first reservoir data with the historical reservoir data in the database to determine the target reservoir data with the highest similarity in the historical reservoir data includes: Extracting feature vectors from the data collected by each type of sensor in the first reservoir data, the feature vectors including periodic feature vectors, trend feature vectors and temporary feature vectors, and the types of sensors including water level sensors, rainfall sensors, flow rate sensors and temperature and humidity sensors; Calculating the similarity between the feature vector of the first reservoir data and each group of feature vectors in the historical reservoir data; A group of data with the highest similarity in the historical reservoir data is used as target reservoir data.
8. A database monitoring and processing system for a reservoir, characterized in that: include: A sensor information acquisition module is used to obtain the locations and quantities of multiple sensors of different types arranged in the reservoir; A first sampling frequency determination module, used to determine the first sampling frequency of each sensor according to the location, quantity and reservoir information of each type of sensor; A first reservoir data acquisition module, used for acquiring first reservoir data acquired by each of the sensors at the first sampling frequency at the first time; A first water level prediction module, used to predict a first water level of the reservoir after a preset time period based on the first reservoir data and historical reservoir data in a database; The early warning prompt generating module is used to generate an early warning prompt if the first water level is greater than or equal to a threshold.
9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.
10. A computer storage medium, characterized in that: The computer storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.
Citation Information
Cited By
Water affair data intelligent acquisition and management method based on machine learning
CN119313504A
Hydrological monitoring point dynamic planning method and system
CN119669726A
Dynamic acquisition awakening system and method for osmotic pressure terminal based on water level change
CN120780368A
