Large lake water level regulation method, device, equipment, storage medium and product

Abstract

This application relates to the field of water level regulation technology, and more particularly to a method, apparatus, device, storage medium, and product for regulating the water level of a large lake. This method determines the range of water level variation based on factors affecting the water level of the large lake to be controlled; constructs an economic entropy weight model based on the water level variation range and preset interest demand data; determines the optimal water level based on the economic entropy weight model; predicts the water level of the large lake to be controlled based on a time series model; and adjusts the current water level of the large lake to be controlled based on the predicted results and the optimal water level, thereby improving the effectiveness of large lake water level regulation.

Description

Technical Field

[0001] The present application relates to the field of water level regulation technology, and in particular to a large lake water level regulation method, device, equipment, storage medium and product. Background Art

[0002] Large lake water level regulation is a complex systemic project, addressing the needs of multiple stakeholders, including ecological protection, shipping needs, flood control, and residential water supply. Large lake water levels are influenced by a variety of natural factors and human activities, such as precipitation, evaporation, and inflowing river flows. These factors exhibit significant dynamic changes and temporal correlations. Therefore, accurately predicting water level fluctuations and developing appropriate regulation plans presents a major technical challenge in water level management. Existing large lake water level regulation schemes often rely on empirical rules or analysis of single factors. While these traditional approaches may be effective in simple scenarios, the increasing complexity of the ecological environment, climate change, and human activities often limits their effectiveness. For example, relying solely on historical water level data for predictions can overlook the impacts of, for example, long-term climate change. Water level regulation methods that focus solely on a single demand can also fail to fully consider other needs, compromising the overall effectiveness of water level regulation. Therefore, how to achieve real-time water level regulation that addresses these multiple factors while balancing the needs of all parties and improving the effectiveness of large lake water level regulation remains an urgent challenge. Summary of the Invention

[0003] The main purpose of this application is to provide a method, device, equipment, storage medium and product for regulating the water level of a large lake, aiming to solve the technical problem of how to improve the effect of regulating the water level of a large lake.

[0004] To achieve the above objectives, the present application provides a method for regulating the water level of a large lake, the method comprising:

[0005] Determine the range of water level changes based on the factors affecting the water level of the large lake to be controlled;

[0006] Based on the water level variation range and the preset interest demand data, an economic entropy weight model is constructed;

[0007] Determining the optimal water level according to the economic entropy weight model;

[0008] Predicting the water level of the large lake to be controlled based on a time series model;

[0009] Based on the prediction result and the optimal water level, the current water level of the large lake to be controlled is adjusted.

[0010] In one embodiment, after the step of predicting the water level of the large lake to be controlled based on the time series model, the method further includes:

[0011] Acquiring water level impact data of the large lake to be controlled, and normalizing the water level impact data to obtain normalized data;

[0012] Based on a preset statistical method, the normalized data is screened to obtain screened data;

[0013] Using the screening data as independent variables, a multiple regression model is constructed;

[0014] Based on the multiple regression model, the error of the prediction result is corrected.

[0015] In one embodiment, the method further comprises:

[0016] Performing sensitivity analysis on the economic entropy weight model, the time series model, and the multiple regression model;

[0017] Based on the results of sensitivity analysis, the model parameters were adjusted.

[0018] In one embodiment, the step of constructing an economic entropy weight model based on the water level variation range and preset benefit demand data includes:

[0019] Converting the preset benefit demand data into quantitative indicators;

[0020] Constructing a decision matrix based on the water level variation range and the quantitative indicators;

[0021] performing standardization processing on the data in the decision matrix to obtain standardized data;

[0022] Determining the entropy value of the quantitative indicator according to the ratio of each element in the standardized data;

[0023] According to the entropy value, the weight of the corresponding indicator is determined, and based on the weight, the economic entropy weight model is constructed.

[0024] In one embodiment, the step of determining the optimal water level according to the economic entropy weight model includes:

[0025] Based on the economic entropy weight model, obtaining the weight of each demand indicator;

[0026] Combining the weight of each demand indicator with the standardized score under the corresponding water level change range;

[0027] Based on the combined results, determine the comprehensive score of each water level change range;

[0028] The water level variation range corresponding to the maximum value of the comprehensive score is used as the optimal water level.

[0029] In one embodiment, before the step of predicting the water level of the large lake to be controlled based on the time series model, the method further includes:

[0030] Obtaining time series data affecting the water level, and sorting the time series data in chronological order;

[0031] Post-processing the time series data to obtain post-processed data, wherein the post-processing includes one or more of missing value filling processing and stabilization processing;

[0032] Extracting features of the post-processed data based on a preset data analysis algorithm;

[0033] Determining corresponding initial models and model parameters according to characteristics of the post-processed data;

[0034] The initial model is fitted with the model parameters to obtain the time series model.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a large lake water level regulating device, which comprises:

[0036] The water level change module is used to determine the water level change range based on the factors affecting the water level of the large lake to be controlled;

[0037] A model building module, configured to build an economic entropy weight model based on the water level variation range and preset benefit demand data;

[0038] A water level determination module, configured to determine an optimal water level according to the economic entropy weight model;

[0039] A water level prediction module, used for predicting the water level of the large lake to be controlled based on a time series model;

[0040] The regulating module is used to regulate the current water level of the large lake to be controlled based on the prediction result and the optimal water level.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a large lake water level regulation device, which includes: a memory, a processor, and a large lake water level regulation program stored on the memory and runnable on the processor, and the large lake water level regulation program is configured to implement the steps of the large lake water level regulation method described above.

[0042] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which a large lake water level regulation program is stored. When the large lake water level regulation program is executed by a processor, the steps of the large lake water level regulation method described above are implemented.

[0043] In addition, to achieve the above objectives, the present application also proposes a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the large lake water level regulation method as described above.

[0044] This application determines the range of water level changes based on the factors affecting the water level of the large lake to be controlled; constructs an economic entropy weight model based on the water level change range and preset interest demand data; determines the optimal water level based on the economic entropy weight model; predicts the water level of the large lake to be controlled based on the time series model; and adjusts the current water level of the large lake to be controlled based on the predicted results and the optimal water level. This application first comprehensively analyzes the factors affecting the water level, accurately determines the range of water level changes, and provides a scientific data basis for regulation; secondly, constructs an economic entropy weight model based on the preset economic interest demand, balances the needs of multiple parties, and ensures the rationality and comprehensiveness of water level regulation; thirdly, uses the entropy weight model to determine the optimal water level and achieve the optimal water level decision; then, predicts the water level change trend through the time series model, which improves the accuracy and foresight of the prediction; finally, dynamically adjusts the current water level based on the predicted results and the optimal water level to achieve real-time regulation; through these steps, the overall regulation effect of the large lake water level is optimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a flow chart of the first embodiment of the large lake water level regulation method of the present application;

[0046] Figure 2 This is a schematic diagram of a sub-flow in the second embodiment of the large lake water level regulation method of this application;

[0047] Figure 3 This is a schematic diagram of a sub-flow in the third embodiment of the large lake water level regulation method of this application;

[0048] Figure 4 This is a schematic diagram of the module structure of the large lake water level regulating device according to an embodiment of the present application;

[0049] Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the large lake water level regulation method in the embodiment of the present application.

[0050] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0051] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0052] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0053] It's important to note that regulating large lake water levels is a complex systemic project, encompassing the needs of multiple stakeholders, including ecological protection, shipping needs, flood control, and residential water supply. Large lake water levels are influenced by a variety of natural factors and human activities, such as precipitation, evaporation, and inflowing river flows. These factors exhibit significant dynamic changes and temporal correlations. Therefore, accurately predicting water level fluctuations and developing appropriate regulation plans presents a major technical challenge in water level management. Existing large lake water level regulation schemes often rely on empirical rules or analysis of single factors. While these traditional approaches may be effective in simple scenarios, the increasing complexity of the ecological environment, climate change, and human activities often limits their effectiveness. For example, relying solely on historical water level data for predictions can overlook the impacts of, for example, long-term climate change. Water level regulation methods that focus solely on a single demand can also fail to fully consider other needs, compromising the overall effectiveness of water level regulation. Therefore, how to achieve real-time water level regulation in response to these multiple factors while balancing the needs of all parties and improving the effectiveness of large lake water level regulation remains an urgent challenge.

[0054] The main solutions of this application are: determining the range of water level changes based on the factors affecting the water level of the large lake to be controlled; constructing an economic entropy weight model based on the water level change range and preset interest demand data; determining the optimal water level based on the economic entropy weight model; predicting the water level of the large lake to be controlled based on the time series model; and adjusting the current water level of the large lake to be controlled based on the prediction results and the optimal water level.

[0055] This application first comprehensively analyzes the factors affecting water levels, accurately determines the range of water level changes, and provides a scientific data basis for regulation; secondly, it constructs an economic entropy weight model based on preset economic interest needs, balances the needs of multiple parties, and ensures the rationality and comprehensiveness of water level regulation; thirdly, it uses the entropy weight model to determine the optimal water level and achieve optimal water level decision-making; then, it predicts the water level change trend through a time series model, which improves the accuracy and foresight of the prediction; finally, it dynamically adjusts the current water level based on the prediction results and the optimal water level to achieve real-time regulation; through these steps, the overall regulation effect of the large lake water level is optimized.

[0056] It should be noted that the execution entity of the method of this embodiment can be a computing service device with data processing, network communication, and program execution capabilities, or it can be the aforementioned large lake water level regulation device with the same or similar functions. This embodiment and the following embodiments will be described using the large lake water level regulation device as an example.

[0057] Based on this, the first embodiment of the large lake water level regulation method of this application is proposed, please refer to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the large lake water level regulation method of the present application.

[0058] In this embodiment, the method includes the following steps:

[0059] S1: Determine the range of water level variation based on the factors affecting the water level of the large lake to be controlled;

[0060] It should be noted that large lakes under control refer to those currently in need of regulation, potentially involving multiple uses such as water resource management, ecological protection, navigation, and flood control. Water level influencing factors refer to the various natural and human factors that affect the water level of large lakes, including but not limited to precipitation, evaporation, inflow of rivers, temperature fluctuations, wind speed, and human activities (such as water diversion and water diversion projects).

[0061] Specifically, the first step is to collect and analyze historical water level data for the large lakes under investigation. This data can come from a variety of sources, including meteorological stations, environmental monitoring agencies, or lake management departments. By analyzing historical water level changes, it is possible to identify overall trends in large lake water levels, as well as seasonal fluctuations and long-term variations. Furthermore, for specific large lake regions, further analysis is required to identify key factors directly related to water level fluctuations, such as precipitation and evaporation. This data typically exhibits time series characteristics, and by analyzing these influencing factors, the range of water level fluctuations can be more accurately predicted.

[0062] Furthermore, it's necessary to consider other external factors to determine the range of water level fluctuations. These factors might include the operation of water conservancy projects, the demand for water levels from surrounding economic activities, and the potential impact of climate change. By incorporating these factors into the actual water level fluctuations of the Great Lakes through mathematical models (such as regression or correlation analysis), a reasonable range of water level fluctuations can be derived. This range not only reflects the influence of natural factors but also provides an important reference for subsequent regulatory models.

[0063] By comprehensively considering both natural and human factors affecting the water level of the Great Lakes, the range of water level fluctuations can be accurately determined, providing a more reliable data basis for water level regulation. This process helps reduce uncertainty in the regulation process and avoids the risk of regulatory failure due to overlooking key influencing factors, thereby laying a solid foundation for subsequent water level prediction and control. Accurately determining the range of water level fluctuations not only improves the precision of water level regulation but also effectively responds to complex environmental and climate changes, making water level management more scientific and precise.

[0064] S2: Constructing an economic entropy weight model based on the water level variation range and the preset interest demand data;

[0065] It should be noted that the water level fluctuation range refers to the reasonable range of fluctuations in the water level of large lakes, determined based on factors affecting their water levels. Water level fluctuations within this range must meet both natural constraints and regulatory requirements. Pre-set interest demand data refers to the demand data of various stakeholders related to large lake water levels (such as ecological protection, shipping, flood control, and residential water supply). These demands are quantified into specific values or indicators to measure the requirements of various stakeholders for different water levels. The economic entropy weight model is a multi-factor weighted model that uses the entropy weight method to assign weights to different interest demands. The entropy weight method assigns weights based on the degree of difference in each data point, reflecting the importance of each demand to overall water level regulation.

[0066] Specifically, the first step is to convert the pre-determined interest demand data into quantifiable indicators. For example, ecological protection may require that the water level of a large lake be maintained within a certain range to protect habitats, while shipping requires sufficient water depth for passage. These diverse needs must be represented through reasonable quantitative indicators, such as the appropriate water level range for ecological protection, the minimum water depth for shipping, and the water level requirements for residential water supply. Next, combining these quantitative indicators with the water level ranges determined previously, a decision matrix is formed.

[0067] Furthermore, the data in the decision matrix is processed based on the entropy weight method. The core idea of the entropy weight method is to determine the impact of each indicator on the decision by calculating the degree of dispersion of the data. First, each indicator is standardized to eliminate the influence of dimension. Then, the entropy value of each indicator is calculated. A larger entropy value indicates a lower degree of dispersion of the data, indicating that the indicator has a smaller impact on the overall decision. Conversely, a smaller entropy value indicates that the indicator plays a more important role in water level regulation. By calculating the weight of each indicator and applying it to the water level regulation model, an economic entropy weight model is constructed.

[0068] By constructing an economic entropy weight model, we can effectively balance the interests of multiple parties and ensure that the needs of all stakeholders are properly considered during the water level regulation process. The introduction of the entropy weight method makes the weighting of different demands more scientific, avoiding the bias caused by subjectivity. This model can quantify the importance of large lake water level regulation based on the needs of various parties, thereby ensuring more accurate and reasonable water level regulation decisions. This not only optimizes the effectiveness of water level regulation, but also improves the economic efficiency of regulation, ultimately achieving the goal of win-win water level management for all parties.

[0069] S3: Determine the optimal water level according to the economic entropy weight model;

[0070] It should be noted that the optimal water level refers to the water level that can meet the maximum interest demand, calculated through the economic entropy weight model after comprehensively considering the interests and needs of all parties. It can not only balance the requirements of ecology, shipping, flood control, etc., but also ensure the water level with the best economic benefits.

[0071] Specifically, we first extract the weights of each interest demand indicator from the economic entropy weight model. These weights represent the importance of each demand in water level regulation. For example, ecological protection may have a higher weight, while the weight of shipping demand may vary depending on shipping seasons and changes in transportation demand. Using these weights, we can quantify the importance of each water level range in meeting the needs of each party.

[0072] Furthermore, these weights are combined with the previously determined water level ranges to create a comprehensive score. Specifically, each water level range's performance on various demand indicators (such as the water level's suitability for navigation and its impact on ecological protection) is multiplied by the corresponding weight to obtain a comprehensive score for each water level range. This comprehensive score reflects the degree to which the water level range comprehensively meets the needs of all parties. Ultimately, by comparing the comprehensive scores of different water level ranges, the water level range with the highest score is selected as the optimal water level.

[0073] Determining the optimal water level based on an economic entropy weight model effectively addresses the problem of finding the optimal balance between the demands of multiple parties. This process fully leverages the scientific weighting assigned by the entropy weight method to ensure that the needs of each stakeholder are properly considered, avoiding the limitations of a single demand that overly influences regulatory decisions. Determining the optimal water level maximizes the interests of all parties, avoiding the shortcomings of traditional empirical regulation methods that are imprecise or biased towards one party's demands, ultimately improving the scientific and economic efficiency of water level regulation.

[0074] S4: Predicting the water level of the large lake to be controlled based on the time series model;

[0075] It's important to note that a time series model is a statistical model used to analyze time series data (i.e., data arranged in chronological order). It can predict future data based on patterns and trends in historical data. Common time series models include ARIMA, SARIMA, and LSTM, which can handle periodic, trend-based, and random water level fluctuations. Water level forecasting involves using time series models to infer future trends in large lake water levels based on historical water level data and its influencing factors, facilitating early regulatory decisions.

[0076] Specifically, the first step is to collect and process historical water level data for the Great Lakes. This data includes past water level changes and factors influencing water levels (such as precipitation, evaporation, and river flow into the lake), and is organized in chronological order. Next, the data is stabilized to ensure that the mean and variance are stable over the entire time period. For water level changes that exhibit trends or seasonality, differencing or seasonal decomposition methods are also needed to remove non-stationary components to ensure the applicability of the time series model.

[0077] After data preprocessing is complete, a time series model tailored to the data characteristics is selected based on historical data. For example, if water level fluctuations exhibit significant periodicity, a SARIMA model can be used; if complex nonlinear dynamic relationships exist, deep learning models such as LSTM can be considered. By modeling historical data, the model can extract trends, seasonality, and random fluctuations in the time series, and then use the fitted model to predict water level fluctuations over a specific time period in the future. Finally, the predicted results are used in subsequent water level regulation to enable proactive responses to excessively high or low water levels.

[0078] Forecasting large lake water levels based on time series models can effectively address the difficulty of predicting dynamic water level changes. By analyzing trends and cyclical patterns in historical data, time series models can predict future water level changes in advance, allowing managers to formulate control plans based on these forecasts and mitigate the adverse impacts of abnormal water level fluctuations on shipping, ecology, and flood control. This step improves the foresight and accuracy of water level control, ensuring more scientific and efficient water level management and enhancing the dynamic responsiveness of large lake water level control.

[0079] S5: Based on the prediction result and the optimal water level, adjust the current water level of the large lake to be controlled.

[0080] It should be noted that the forecast results are based on a time series model that estimates the future water level changes of the Great Lakes over time, reflecting future water level trends and fluctuations. Current water level regulation refers to the adjustment of the Great Lakes' current water levels through the control of dams, sluice gates, and other regulatory measures, gradually approaching or maintaining them within the optimal range.

[0081] Specifically, the system first compares the predicted results from the time series model with the previously determined optimal water level. If the predicted results indicate that the future water level will deviate from the optimal level, the system determines regulatory measures based on the magnitude, direction, and impact of the deviation. Common regulatory measures include opening and closing dams or sluice gates, increasing water discharge or storage, and other methods to manually adjust the water level to within the optimal range.

[0082] Furthermore, the system monitors changes in the current water level in real time and continuously adjusts control parameters based on the difference between the predicted results and the optimal water level. For example, if the water level is predicted to rise above the optimal level, the system will preemptively initiate drainage measures to reduce the magnitude of the water level rise and prevent the impact of excessive water levels on shipping or the environment. Conversely, if the water level is predicted to fall below the optimal level, the system can temporarily suspend drainage or increase water storage to maintain ecological balance and shipping needs. Throughout the entire process, water level regulation is a dynamic and continuous adjustment process that requires real-time monitoring, feedback, and correction.

[0083] By combining the predictions of time series models with the optimal water level to adjust the current water level, the lag problem in water level management can be effectively addressed. This step has the beneficial effect of enabling dynamic and proactive water level regulation, ensuring that the water level of the Great Lakes remains within a reasonable range, thereby mitigating potential risks associated with water level fluctuations. Real-time regulation not only reduces the adverse impacts of excessively high or low water levels on ecosystems and shipping, but also improves the flexibility and precision of the regulation process, making Great Lakes water level management more efficient and intelligent.

[0084] This embodiment determines the range of water level changes based on the factors affecting the water level of the large lake to be controlled; constructs an economic entropy weight model based on the water level change range and preset interest demand data; determines the optimal water level based on the economic entropy weight model; predicts the water level of the large lake to be controlled based on the time series model; and adjusts the current water level of the large lake to be controlled based on the prediction results and the optimal water level. This embodiment first comprehensively analyzes the factors affecting the water level and accurately determines the range of water level changes, providing a scientific data basis for regulation; secondly, constructs an economic entropy weight model based on preset economic interest requirements to balance the needs of multiple parties and ensure the rationality and comprehensiveness of water level regulation; thirdly, uses the entropy weight model to determine the optimal water level and achieve the optimal water level decision; then, uses the time series model to predict the water level change trend, improving the accuracy and foresight of the prediction; finally, dynamically adjusts the current water level based on the prediction results and the optimal water level to achieve real-time regulation; through these steps, the overall regulation effect of the large lake water level is optimized.

[0085] Based on the above first embodiment, the second embodiment of the large lake water level regulation method of this application is proposed. Figure 2 , Figure 2 This is a schematic diagram of a sub-process in the second embodiment of the large lake water level regulation method of this application.

[0086] like Figure 2 As shown, in this embodiment, after step S4, the following steps are further included:

[0087] S4a: obtaining water level impact data of the large lake to be controlled, and normalizing the water level impact data to obtain normalized data;

[0088] S4b: Filtering the normalized data based on a preset statistical method to obtain filtered data;

[0089] S4c: using the screening data as independent variables to construct a multiple regression model;

[0090] S4d: Based on the multiple regression model, correct the error of the prediction result.

[0091] It should be noted that normalization is a data preprocessing method that scales the data within a certain range to eliminate dimensional differences between different data and enable data to be compared and analyzed on the same scale. Preset statistical methods are statistical methods that are pre-set based on specific application scenarios, usually including correlation analysis, principal component analysis (PCA), etc., which aim to screen out the most significant influencing factors on water level changes from multiple variables. The multiple regression model is a statistical analysis model that predicts dependent variables (such as water level changes) through multiple independent variables (i.e. influencing factors) and is used to analyze the degree of influence of each variable on the dependent variable. Error correction refers to the correction of the deviation of the time series model in the prediction process through the application of the multiple regression model to improve the accuracy of the prediction results.

[0092] Specifically, first, data on influencing changes in the water level of the large lake to be controlled are collected from various channels. Common water level influencing data include precipitation, evaporation, river flow into the lake, temperature, etc. The dimensions and ranges of these data may be different, so they need to be normalized. The purpose of normalization is to scale data of different ranges to the same scale range (such as 0 to 1), so as to facilitate subsequent analysis and comparison. Common methods of normalization include minimum-maximum normalization and Z-score normalization. The specific choice depends on the characteristics of the data and the application scenario. After normalization, the data is screened based on the preset statistical method to select the factors that have the most significant impact on water level changes. Correlation analysis or principal component analysis (PCA) is usually used to screen data, with the aim of removing redundant or noisy data, so as to obtain the core influencing factors that play a dominant role in water level changes. For example, through correlation analysis, the correlation between variables such as precipitation and evaporation and water level changes can be found, and the variables with the highest correlation can be screened as independent variables.

[0093] Furthermore, the selected important influencing factors are used as independent variables to construct a multiple regression model. The core of this model is to predict the dependent variable (i.e., water level changes) through multiple independent variables. Through training with historical data, the model can learn the degree of influence of each variable on water level changes, thereby establishing a multiple regression model for water level prediction. Finally, the multiple regression model is applied to the prediction results of the time series model to correct its errors. Although the time series model can capture the dynamic trend of water level changes, it may have deviations when dealing with the complex relationship between multiple variables. Through the multiple regression model, the linear relationship between water level changes and various influencing factors can be analyzed, thereby correcting the prediction error of the time series model and improving the accuracy and reliability of the prediction.

[0094] By obtaining water level influencing data and normalizing it, we ensured that the data was analyzed at the same scale, thus eliminating the impact of different data dimensions. Based on the preset statistical method, we screened out the factors that most significantly affected water level changes, removed redundant data, and simplified the complexity of the model. By constructing a multivariate regression model, we further revealed the relationship between water level changes and various influencing factors, and by correcting the errors in the time series model prediction results, we greatly improved the accuracy of water level prediction. This step ensures that water level predictions are more accurate and reliable, provides more scientific data support for large lake water level regulation, and thus significantly improves the effectiveness of water level management.

[0095] Based on the above first embodiment, in this embodiment, the method further includes:

[0096] S6: Performing sensitivity analysis on the economic entropy weight model, the time series model, and the multiple regression model;

[0097] S7: Adjust model parameters based on sensitivity analysis results.

[0098] It should be noted that sensitivity analysis is a method used to evaluate the impact of changes in parameters or input variables in the model on the output results. The purpose is to identify parameters in the model that play a key role in the change of results.

[0099] Specifically, sensitivity analysis first assesses the impact of changes in key parameters or variables within each model on the model's output. For economic entropy weight models, the primary goal of sensitivity analysis is to understand the impact of changes in different weights on the optimal water level. For example, by simulating fluctuations in the weights of various stakeholders, the impact on the final optimal water level decision can be assessed. The more sensitive the weight is to changes, the more important it is to water level regulation decisions. In time series models, sensitivity analysis primarily focuses on parameters such as the autoregressive order, differencing order, and moving average order of the time series. By analyzing the impact of different parameter settings on water level forecasts, it is possible to identify which parameters are most critical to the accuracy of water level forecasts, thereby improving the model's predictive capabilities. For multivariate regression models, sensitivity analysis primarily analyzes the impact of individual variables (such as precipitation, evaporation, and flow) on the forecast results. By varying the values or ranges of individual variables and observing their contribution and sensitivity to water level forecasts, it is possible to reveal which factors play a key role in predicting water level changes.

[0100] Furthermore, after completing the sensitivity analysis, the parameters of each model can be adjusted based on the results. For the economic entropy weight model, the weight distribution of various stakeholders can be adjusted based on the weight sensitivity results. For example, if the demand weight of a particular stakeholder has too large or too small an impact on water level changes, the weights can be reallocated based on the analysis results to make the model more balanced and reasonable. In time series models, if certain parameters (such as the autoregressive order and the differencing order) have a significant impact on forecast accuracy, these parameters can be adjusted to improve the model's accuracy in predicting future water level changes. By adjusting these parameters, the model can better capture the cyclical and trend characteristics of water levels. For multivariate regression models, sensitivity analysis can help identify the most critical influencing factors. For independent variables that have a significant impact on water level changes, the model can increase their weights or refit the relevant parameters to ensure more accurate forecasts. Furthermore, if certain independent variables have low sensitivity, the model can simplify the processing of these variables, reducing computational effort and improving operational efficiency.

[0101] By conducting sensitivity analyses on economic entropy weight models, time series models, and multivariate regression models, we were able to identify the most critical parameters and variables for water level prediction and regulation within the models. This sensitivity analysis helped optimize model parameter settings, making the models more accurate and efficient. Adjusting the parameters of each model based on the sensitivity analysis results not only improved the scientific nature and rationality of water level regulation decisions but also significantly improved the accuracy of water level forecasts. This process ensured the flexibility and adaptability of the water level regulation models in practical applications, enabling them to cope with complex environmental changes and ultimately achieve better water level management results for large lakes.

[0102] This embodiment determines the range of water level changes based on the factors affecting the water level of the large lake to be controlled; constructs an economic entropy weight model based on the water level change range and preset interest demand data; determines the optimal water level based on the economic entropy weight model; predicts the water level of the large lake to be controlled based on the time series model; and adjusts the current water level of the large lake to be controlled based on the prediction results and the optimal water level. This embodiment first comprehensively analyzes the factors affecting the water level and accurately determines the range of water level changes, providing a scientific data basis for regulation; secondly, constructs an economic entropy weight model based on preset economic interest requirements to balance the needs of multiple parties and ensure the rationality and comprehensiveness of water level regulation; thirdly, uses the entropy weight model to determine the optimal water level and achieve the optimal water level decision; then, uses the time series model to predict the water level change trend, improving the accuracy and foresight of the prediction; finally, dynamically adjusts the current water level based on the prediction results and the optimal water level to achieve real-time regulation; through these steps, the overall regulation effect of the large lake water level is optimized.

[0103] Based on the above second embodiment, the third embodiment of the large lake water level regulation method of this application is proposed. Figure 3 , Figure 3 This is a schematic diagram of a sub-process in the third embodiment of the large lake water level regulation method of this application.

[0104] In this embodiment, step S2 includes:

[0105] S21: Converting the preset benefit demand data into quantitative indicators;

[0106] S22: constructing a decision matrix based on the water level variation range and the quantitative index;

[0107] S23: performing standardization processing on the data in the decision matrix to obtain standardized data;

[0108] S24: Determine the entropy value of the quantitative indicator according to the ratio of each element in the standardized data;

[0109] S25: Determine the weight of the corresponding indicator according to the entropy value, and construct the economic entropy weight model based on the weight.

[0110] It should be noted that quantitative indicators translate the pre-defined needs of various stakeholders into specific, measurable indicators for computation and analysis within the model. The decision matrix, formed by the performance of each quantitative indicator under different water level ranges, is used for entropy weight analysis. Standardization refers to the process of converting data of different dimensions to the same dimension for comparative analysis. In the entropy weight method, entropy is used to measure the information content of each indicator. The lower the entropy value, the greater its importance to decision-making. Weights are the relative importance assigned to each indicator based on the entropy value and are used to calculate the overall score under different water level ranges.

[0111] Specifically, the demand data from various stakeholders must first be quantified for use in the model. Different stakeholders may have different water level requirements. For example, ecological protection may require water levels to be maintained within a certain range to protect habitats, while shipping may require water levels to be high enough for ships to pass. These demands are then translated into specific quantitative indicators, such as a water level range suitable for ecological protection, a minimum water level required for shipping, and an optimal water level range for residential use. Each stakeholder demand is converted into a measurable value to enable analysis corresponding to the range of water level fluctuations.

[0112] Furthermore, a decision matrix is constructed based on the previously determined water level ranges and the converted quantitative indicators. The rows of the decision matrix represent different water level ranges, and the columns represent the scores for each quantitative indicator. In the decision matrix, each element represents the performance of a specific water level range on a specific indicator. For example, at a specific water level, a range may score highly for meeting shipping needs but low for meeting ecological needs. Because the quantitative indicators in the decision matrix may have different dimensions or ranges, they require normalization. Normalization can be performed through methods such as min-max normalization or Z-score normalization, which adjusts all data to the same range (e.g., between 0 and 1) for subsequent analysis. This standardized matrix makes the indicators comparable, ensuring the accuracy of the subsequent entropy weight analysis. Based on the standardized data, the entropy value of each quantitative indicator is calculated. The entropy value is calculated based on the ratio of each element in the standardized data. Based on the calculated entropy value, the weight of each quantitative indicator is determined. Finally, based on these weights, an economic entropy weight model is constructed to integrate various demand indicators and optimize water level control decisions.

[0113] By converting the pre-determined data on the interests and needs of various stakeholders into quantitative indicators and constructing a decision-making matrix, the needs of various stakeholders can be systematically addressed. Standardization eliminates differences in data dimensions, ensuring that all data are analyzed on a consistent scale. The entropy weight method, by calculating entropy values and assigning weights, makes the decision-making process more scientific and objective, avoiding the bias caused by subjective weight allocation. Ultimately, by constructing an economic entropy weight model, it is possible to rationally balance the needs of multiple parties and determine the optimal water level, thereby enhancing the scientific nature of large lake water level regulation and the rationality of decision-making.

[0114] Based on the above second embodiment, in this embodiment, step S3 includes:

[0115] S31: Obtaining the weight of each demand indicator based on the economic entropy weight model;

[0116] S32: combining the weight of each demand indicator with the standardized score under the corresponding water level variation range;

[0117] S33: Determine the comprehensive score of each water level variation range based on the combined results;

[0118] S34: The water level variation range corresponding to the maximum value of the comprehensive score is used as the optimal water level.

[0119] It's important to note that the weights of demand indicators represent the relative importance of different stakeholder demands in the decision-making process. The larger the weight, the greater the impact of that demand on water level regulation. The standardized score is a standardized score for each water level range across each demand indicator, ensuring that data is comparable on a consistent scale. The comprehensive score, derived by combining the weights with the standardized score, is used to determine the optimal water level.

[0120] Specifically, the weights of each demand indicator are first determined using the economic entropy weight model. These weights are calculated based on the entropy weight method and reflect the relative importance of the needs of various stakeholders to the overall water level regulation decision. For large lake water level regulation, common demand indicators include ecological protection, shipping, flood control, and residential water use. The weight distribution results indicate the priority of these needs in the regulation process. For example, if ecological protection is more important in a certain period, its weight value will be increased accordingly. Next, the weight of each demand indicator is combined with the standardized score under different water level variation ranges. The standardized score is the score after the performance of the demand indicator is standardized under each water level variation range. By multiplying the weight of each demand indicator by its corresponding standardized score, the weighted score of the water level variation range is obtained.

[0121] Furthermore, the weighted scores of all demand indicators are summed up to obtain a comprehensive score for each water level range. The comprehensive score reflects the overall performance of each water level range under the demands of multiple parties. The higher the score of the water level range, the better the water level range can meet the comprehensive requirements of multiple demands. For example, if a water level range has a high comprehensive score, it means that it is suitable for ecological protection and meets other needs such as shipping and flood control. Finally, by comparing the comprehensive scores of each water level range, the water level range with the highest score is selected. The water level range corresponding to the maximum comprehensive score is the optimal water level, because this water level can achieve the best balance among multiple demands and meet the requirements of different stakeholders. Taking this optimal water level as the target of water level regulation can maximize the economic and ecological benefits of regulation.

[0122] By combining the weights of demand indicators with standardized scores for the water level range, the impact of multiple demands on water level regulation can be comprehensively considered, making regulatory decisions more scientific and reasonable. Determining the maximum value of the comprehensive score ensures that the regulation plan is not limited to a single objective, but rather balances the needs of all parties to find an optimal water level that serves the overall interests. This process greatly improves the accuracy and applicability of water level regulation, ensuring that the ecological, economic, and social needs of the lake are met to the greatest extent possible. Ultimately, the optimal water level determined based on this model can significantly improve the efficiency and effectiveness of water level regulation, achieving a win-win situation for all parties.

[0123] Based on the above second embodiment, in this embodiment, before step S4, the following steps are further included:

[0124] S4A: Obtain time series data affecting the water level, and sort the time series data in chronological order;

[0125] S4B: performing post-processing on the time series data to obtain post-processed data, wherein the post-processing includes one or more of missing value filling processing and stabilization processing;

[0126] S4C: extracting features of the post-processed data based on a preset data analysis algorithm;

[0127] S4D: determining a corresponding initial model and model parameters according to the characteristics of the post-processed data;

[0128] S4E: Fitting the initial model to the model parameters to obtain the time series model.

[0129] It should be noted that post-processing is the process of cleaning and adjusting the original time series data, which usually includes missing value filling and stabilization to ensure data quality and model applicability. Missing value filling refers to the reasonable completion of the missing parts in the data. Common methods include interpolation and mean filling. Stabilization is to eliminate the trend and seasonal components in the data and ensure that the mean and variance of the time series data are stable over the entire time period. Common methods include difference method and logarithmic transformation. Feature extraction refers to the extraction of key features related to water level changes from the post-processed data. These features will be used to select a suitable model and optimize parameters. The initial model and model parameters refer to the model type (such as ARIMA, SARIMA, etc.) selected in time series analysis and its initial parameters, which are used to fit the water level change trend.

[0130] Specifically, first, time series data related to changes in the water levels of the Great Lakes are obtained from historical records. These data are arranged in chronological order and typically include factors that affect water level changes, such as historical water levels, precipitation, and evaporation. Ensure that these data are sorted in chronological order by date or time to maintain the temporal dependence of the data. The sorted time series data lays the foundation for the subsequent model construction. In the acquired and sorted time series data, some data may be missing, anomalies, or non-stationary. To improve the accuracy of the model, these data need to be post-processed. Post-processing includes: Missing value filling: If there are some missing values in the data, these missing values need to be filled through interpolation, mean filling, or regression to ensure data integrity. Stationary processing: Many time series models require stationary data, that is, the mean and variance of the data remain constant over time. For water level data with trends or seasonality, non-stationary components can be removed through differencing (i.e., performing one or more differencing operations on the data) or logarithmic transformation, thereby obtaining data more suitable for modeling. After completing data post-processing, feature extraction is performed on the data based on the preset data analysis algorithm. Feature extraction involves analyzing data trends, periodicity, and correlations to extract the most relevant features related to water level changes. Common feature extraction methods include autocorrelation analysis (ACF) and partial autocorrelation analysis (PACF), which are used to identify lags, periodicity, or trends in time series. These features provide a reference for model selection and parameter setting.

[0131] Furthermore, based on the extracted features, the most appropriate time series model is selected. For example, if the data exhibits significant seasonal variation, a seasonal ARIMA (SARIMA) model can be selected; if trends are more pronounced, an autoregressive integrated moving average (ARIMA) model can be used. Furthermore, the initial model parameters, such as the autoregressive order, differencing order, and moving average order, are determined based on the feature analysis results. Properly setting these initial parameters is crucial for model fit and forecasting accuracy. After selecting the initial model and determining its parameters, the model is fitted to the processed time series data. The fitting process involves adjusting the model parameters to ensure that the model accurately interprets the patterns and trends in the historical data. During the fitting process, statistical methods such as maximum likelihood estimation (MLE) can be used to optimize the model parameters to improve forecasting accuracy. Once the fitting is complete, the resulting time series model can be used to forecast future water levels.

[0132] By processing time series data that influences water levels and constructing a time series model, the accuracy of water level forecasts can be effectively improved. Missing value filling ensures data integrity, stabilization makes the data suitable for modeling, feature extraction provides a basis for model selection, and model fitting improves model accuracy by adjusting parameters. Ultimately, this time series model allows for more accurate predictions of future water level changes in the Great Lakes, providing a scientific basis for water level regulation. This step ensures the foresight and reliability of water level forecasts, helping to optimize Great Lakes water level regulation strategies and mitigate the adverse effects of water level fluctuations.

[0133] This embodiment determines the range of water level changes based on the factors affecting the water level of the large lake to be controlled; constructs an economic entropy weight model based on the water level change range and preset interest demand data; determines the optimal water level based on the economic entropy weight model; predicts the water level of the large lake to be controlled based on the time series model; and adjusts the current water level of the large lake to be controlled based on the prediction results and the optimal water level. This embodiment first comprehensively analyzes the factors affecting the water level and accurately determines the range of water level changes, providing a scientific data basis for regulation; secondly, constructs an economic entropy weight model based on preset economic interest requirements to balance the needs of multiple parties and ensure the rationality and comprehensiveness of water level regulation; thirdly, uses the entropy weight model to determine the optimal water level and achieve the optimal water level decision; then, uses the time series model to predict the water level change trend, improving the accuracy and foresight of the prediction; finally, dynamically adjusts the current water level based on the prediction results and the optimal water level to achieve real-time regulation; through these steps, the overall regulation effect of the large lake water level is optimized.

[0134] The present application also provides a large lake water level regulating device, please refer to Figure 4 , Figure 4 This is a schematic diagram of the module structure of the large lake water level regulating device according to an embodiment of the present application, and the large lake water level regulating device includes:

[0135] The water level change module 401 is used to determine the water level change range according to the factors affecting the water level of the large lake to be controlled;

[0136] A model building module 402 is used to build an economic entropy weight model based on the water level variation range and preset benefit demand data;

[0137] The water level determination module 403 is used to determine the optimal water level according to the economic entropy weight model;

[0138] A water level prediction module 404 is used to predict the water level of the large lake to be controlled based on a time series model;

[0139] The adjustment module 405 is used to adjust the current water level of the large lake to be controlled based on the prediction result and the optimal water level.

[0140] The large lake water level regulating device provided in the embodiments of this application utilizes the large lake water level regulating method described in the aforementioned embodiments, thereby solving the technical problem of improving the effectiveness of large lake water level regulation. Compared to the prior art, the large lake water level regulating device provided in the embodiments of this application achieves the same beneficial effects as the large lake water level regulating method described in the aforementioned embodiments. Other technical features of the large lake water level regulating device are the same as those disclosed in the aforementioned embodiments and are not further detailed here.

[0141] The present application provides a large lake water level regulation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the large lake water level regulation method in the above-mentioned embodiment.

[0142] Reference below Figure 5 , which shows a schematic diagram of the structure of a large lake water level regulating device suitable for implementing an embodiment of the present application. The large lake water level regulating device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 5 The large lake water level regulating device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0143] like Figure 5As shown, the large lake water level regulating device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the large lake water level regulating device. Processing device 1001, ROM 1002, and RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to I / O interface 1006: input device 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output device 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003 including, for example, a magnetic tape, hard disk, etc.; and communication device 1009. Communication device 1009 may allow the Great Lakes water level regulating device to communicate with other devices wirelessly or by wire to exchange data. Although the Great Lakes water level regulating device is shown with various systems, it should be understood that implementation or presence of all the illustrated systems is not required. More or fewer systems may alternatively be implemented or present.

[0144] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0145] The large lake water level regulation device provided in this application, employing the large lake water level regulation method described in the aforementioned embodiment, can address the technical problem of improving the effectiveness of large lake water level regulation. Compared to the prior art, the large lake water level regulation device provided in this application achieves the same beneficial effects as the large lake water level regulation method described in the aforementioned embodiment. Other technical features of this large lake water level regulation device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0146] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0147] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0148] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, a computer program) stored thereon, wherein the computer-readable program instructions are used to execute the large lake water level regulation method in the above-mentioned embodiment.

[0149] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof. The computer-readable storage medium may be included in the large lake water level regulating device; or it may exist independently without being assembled into the large lake water level regulating device.

[0150] The computer-readable storage medium carries one or more programs. When executed by a large lake water level regulating device, the one or more programs cause the large lake water level regulating device to: determine a water level variation range based on factors affecting the water level of the large lake to be controlled; construct an economic entropy weight model based on the water level variation range and preset benefit demand data; determine an optimal water level based on the economic entropy weight model; predict the water level of the large lake to be controlled based on a time series model; and adjust the current water level of the large lake to be controlled based on the predicted results and the optimal water level. The computer program code for performing the operations of this application can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0151] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0152] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0153] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned large lake water level regulation method. This computer-readable storage medium can address the technical problem of improving the effectiveness of large lake water level regulation. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the large lake water level regulation method provided in the aforementioned embodiments and are not further elaborated here.

[0154] An embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the large lake water level regulation method as described above.

[0155] The computer program product provided in this application can solve the technical problem of how to improve the effectiveness of large lake water level regulation. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiments of this application are the same as the beneficial effects of the large lake water level regulation method provided in the above embodiments, and will not be repeated here.

[0156] The above are only preferred embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A method for regulating the water level of a large lake, characterized in that: The method comprises: Determine the range of water level changes based on the factors affecting the water level of the large lake to be controlled; Convert preset benefit demand data into quantitative indicators; Constructing a decision matrix based on the water level variation range and the quantitative indicators; performing standardization processing on the data in the decision matrix to obtain standardized data; Determining the entropy value of the quantitative indicator according to the ratio of each element in the standardized data; Determine the weight of the corresponding indicator according to the entropy value, and construct an economic entropy weight model based on the weight; Based on the economic entropy weight model, obtaining the weight of each demand indicator; Combining the weight of each demand indicator with the standardized score under the corresponding water level change range; Based on the combined results, determine the comprehensive score of each water level change range; The water level variation range corresponding to the maximum value of the comprehensive score is taken as the optimal water level; Obtaining time series data affecting the water level, and sorting the time series data in chronological order; Post-processing the time series data to obtain post-processed data, wherein the post-processing includes one or more of missing value filling processing and stabilization processing; Extracting features of the post-processed data based on a preset data analysis algorithm; Determining corresponding initial models and model parameters according to characteristics of the post-processed data; Fitting the initial model with the model parameters to obtain a time series model; Predicting the water level of the large lake to be controlled based on a time series model; Acquiring water level impact data of the large lake to be controlled, and normalizing the water level impact data to obtain normalized data; Based on a preset statistical method, the normalized data is screened to obtain screened data; Using the screening data as independent variables, a multiple regression model is constructed; By simulating weight fluctuations, the impact of weight changes on the optimal water level is evaluated, and the model parameters of the economic entropy weight model are adjusted according to the evaluation results; Determining key parameters based on the impact of the autoregressive order, the difference order, and the moving average order of the time series on the prediction results under different parameter settings, and adjusting the model parameters of the time series model based on the key parameters; Determining the contribution and sensitivity of the precipitation, evaporation, and flow rate based on the degree of influence of the precipitation, evaporation, and flow rate on the prediction result, and adjusting the model parameters of the multiple regression model based on the contribution and sensitivity; Based on the multivariate regression model, the error of the prediction result is corrected; Based on the prediction result and the optimal water level, the current water level of the large lake to be controlled is adjusted.

2. A large lake water level regulating device, characterized in that: The device comprises: The water level change module is used to determine the water level change range based on the factors affecting the water level of the large lake to be controlled; A model building module is used to convert preset interest demand data into quantitative indicators; construct a decision matrix based on the water level change range and the quantitative indicators; standardize the data in the decision matrix to obtain standardized data; determine the entropy value of the quantitative indicator based on the ratio of each element in the standardized data; determine the weight of the corresponding indicator based on the entropy value, and construct an economic entropy weight model based on the weight; A water level determination module is configured to obtain the weights of each demand indicator based on the economic entropy weight model; combine the weights of each demand indicator with the standardized scores under the corresponding water level variation range; determine the comprehensive scores of each water level variation range based on the combination results; and use the water level variation range corresponding to the maximum value of the comprehensive score as the optimal water level; A water level prediction module is configured to obtain time series data affecting the water level and sort the time series data in chronological order; post-process the time series data to obtain post-processed data, wherein the post-processing includes one or more of missing value filling and stabilization; extract features of the post-processed data based on a preset data analysis algorithm; determine a corresponding initial model and model parameters based on the features of the post-processed data; fit the initial model with the model parameters to obtain a time series model; and predict the water level of the large lake to be controlled based on the time series model. An adjustment module is used to obtain the water level impact data of the large lake to be controlled, and normalize the water level impact data to obtain normalized data; based on a preset statistical method, the normalized data is screened to obtain screened data; the screened data is used as an independent variable to construct a multiple regression model; by simulating weight fluctuations, the impact of weight changes on the optimal water level is evaluated, and the model parameters of the economic entropy weight model are adjusted according to the evaluation results; based on the impact of the autoregressive order, difference order and moving average order of the time series on the prediction results under different parameter settings, key parameters are determined, and the model parameters of the time series model are adjusted based on the key parameters; based on the degree of influence of precipitation, evaporation and flow on the prediction results, the contribution and sensitivity of the precipitation, evaporation and flow are determined, and based on the contribution and sensitivity, the model parameters of the multiple regression model are adjusted; based on the multiple regression model, the error of the prediction result is corrected; based on the prediction result and the optimal water level, the current water level of the large lake to be controlled is adjusted.

3. A computer device, characterized in that: The device includes: a memory, a processor, and a large lake water level regulation program stored in the memory and executable on the processor, wherein the large lake water level regulation program is configured to implement the steps of the large lake water level regulation method according to claim 1 .

4. A storage medium, characterized in that The storage medium stores a large lake water level regulation program, which, when executed by the processor, implements the steps of the large lake water level regulation method according to claim 1.

5. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the steps of the large lake water level regulation method according to claim 1.

Images