Intelligent water supply management system and method based on wind, solar and water multi-source data fusion

Abstract

The present invention discloses an intelligent water supply management system and method based on multi-source data fusion of wind, solar and water, and relates to the field of electrical digital data processing technology. The system includes a time alignment deviation quantification module, a time alignment control module, a data fusion timeliness response quantification module and a timeliness response control module. The present invention obtains a time alignment deviation quantification result by quantifying the time parameters of multi-source data, and determines whether to perform time alignment control. If so, the timeliness response parameter is obtained after the control. Otherwise, the timeliness response parameter is directly obtained and quantified to obtain the data fusion timeliness response quantification result. Based on the data fusion timeliness response quantification result, it is determined whether to perform PLC scanning interval control and monitoring verification, thereby improving the timeliness of water supply management demand response and solving the problem of poor flexibility of water supply management execution response caused by insufficient consideration of the time difference of multi-source data processing in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to an intelligent water supply management system and method based on the fusion of wind, solar and water multi-source data. Background Art

[0002] In mountainous terrain with complex terrain and uneven wind speed distribution, magnetically levitated vertical-axis wind turbines that start at low wind speeds are used, combined with lidar to collect wind speed and direction data to accurately capture wind fields in valleys. Furthermore, smart water meters and pressure sensors are deployed at high points and inflection points in the mountainous water supply network, and acoustic leak detectors are used to collect real-time water source data. This collected data is transmitted to edge computing nodes using IoT technology. Multimodal data fusion is used to integrate multi-source data from wind, solar, and water sources (including but not limited to wind speed, water pH, water level, light intensity, and gate opening). This fused data is used to predict subsequent water supply management operations. A programmable logic controller (PLC) converts predicted water demand instructions issued from the cloud into specific control actions, such as dynamically adjusting pump speed based on future water demand forecasts. This analyzes predicted water demand instructions, ensuring precise alignment between predicted water demand and actual water demand control, preventing a disconnect between prediction and execution.

[0003] For example, the patent announcement number CN111340316B discloses a smart water supply management method and system, which includes: predicting the future water consumption of each area, judging whether each area can consume the existing water storage within the set time based on the water storage capacity, future normal water supply and predicted water consumption of each area, and if not, calculating the excess water storage; if so, calculating the lack of water storage; and dispatching the existing water storage between the areas based on the value of the excess water storage or lack of water storage in each area.

[0004] For example, the patent application with publication number CN120145219A discloses a method and device for monitoring acoustic leakage in a water supply network based on multimodal data fusion and multi-task learning, which includes: inputting an original acoustic signal and labeling it; converting the original acoustic signal to obtain a corresponding log-Mel spectrum graph; extracting features from the original acoustic signal to construct a time-frequency feature set; forming a data set from the original acoustic signal, the log-Mel spectrum graph, the label, and the time-frequency feature set; constructing a multi-level task prediction network based on a residual convolutional neural network framework; using the data set to perform multi-task training on the multi-level task prediction network to obtain a water supply network acoustic leakage monitoring model; and inputting the original acoustic signal of the collection point into the water supply network acoustic leakage monitoring model to obtain a prediction result.

[0005] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0006] In scenarios with complex mountainous terrain and uneven wind speed distribution, multi-source data collection covers multiple types of data such as meteorological data and hydrological data. Since meteorological data is updated frequently and hydrological data is updated relatively slowly, the meteorological data and hydrological data at the same time point do not truly correspond to the actual situation. Forced fusion will cause data confusion, causing the original data to enter the fusion stage directly, which will inevitably lead to fusion failure. Wind speed monitoring is single-point data, and regional rainfall forecasts have a wider coverage. After simply fusing wind speed monitoring data with regional rainfall forecast data, it is difficult to accurately judge the impact of local environmental changes in mountainous areas on water supply management. These differences lead to reduced accuracy and effectiveness of the fused data. The redundant data fusion features lead to delays in the output of the prediction model, such as water consumption prediction delays, and the PLC executes at fixed intervals, resulting in scheduling instructions that are different from actual needs. There is a problem of poor flexibility in water supply management execution response due to insufficient consideration of the time differences in multi-source data processing. Summary of the Invention

[0007] The embodiments of the present application provide an intelligent water supply management system and method based on the fusion of wind, solar and water multi-source data, thereby solving the problem of poor flexibility in water supply management execution response caused by insufficient consideration of the time differences in multi-source data processing in the prior art, and improving the timeliness of water supply management demand response.

[0008] The embodiment of the present application provides an intelligent water supply management system based on the fusion of wind, solar and water multi-source data, including: a time alignment deviation quantification module, a time alignment control module, a data fusion timeliness response quantification module and a timeliness response control module: wherein, the time alignment deviation quantification module is used to obtain a time alignment deviation quantification result based on the acquired multi-source data time parameters after multi-source data collection to reflect the time alignment deviation degree of multi-source data processing caused by the timestamp difference of multi-source data collection. Multi-source data collection means collecting wind, solar and water multi-source data through a specified data collection method to generate a predictive water supply instruction to realize water supply management; the time alignment control module is used to judge whether to perform time alignment control based on the time alignment deviation quantification result. If so, it will perform time alignment control when performing time alignment control. After control, the timeliness response parameters are obtained to reflect the response timeliness of executing the predicted water supply demand instruction based on the multi-source data fusion results. Otherwise, the timeliness response parameters are directly obtained. The time alignment control includes average delay control and response time control; the data fusion timeliness response quantification module is used to obtain the data fusion timeliness response quantification results based on the obtained timeliness response parameters to quantify the timeliness from the completion of multi-source data fusion to the reception and response of the predicted water supply demand instruction; the timeliness response control module is used to determine whether to perform PLC scanning interval control and monitoring verification based on the data fusion timeliness response quantification results. If so, the water supply management operation corresponding to the predicted water supply demand instruction is executed after the PLC scanning interval control and monitoring verification are performed, otherwise the water supply management operation is directly executed.

[0009] The embodiment of the present application provides an intelligent water supply management method based on the fusion of wind, solar and water multi-source data, comprising the following steps: after multi-source data collection, according to the obtained multi-source data time parameters, a time alignment deviation quantification result is obtained to reflect the time alignment deviation of multi-source data processing caused by the timestamp difference of multi-source data collection, multi-source data collection means collecting wind, solar and water multi-source data by a specified data collection method to generate a predictive water supply instruction to realize water supply management; according to the time alignment deviation quantification result, it is judged whether to perform time alignment regulation, and if so, after performing time alignment regulation, a timeliness response parameter is obtained to reflect the timeliness response based on multi-source data. The fusion result executes the response timeliness of the predicted water supply demand instruction, otherwise the timeliness response parameters are directly obtained. The time alignment control includes average delay control and response time control; based on the obtained timeliness response parameters, the data fusion timeliness response quantitative results are obtained to quantify the timeliness from the completion of multi-source data fusion to the reception and response of the predicted water supply demand instruction; based on the data fusion timeliness response quantitative results, it is determined whether to perform PLC scanning interval control and monitoring verification. If so, the water supply management operation corresponding to the predicted water supply demand instruction is executed after performing PLC scanning interval control and monitoring verification, otherwise the water supply management operation is directly executed.

[0010] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0011] 1. By collecting and quantifying the time parameters of multi-source data, the quantitative results of time alignment deviation are obtained. Due to the differences in time tags of data provided by different data sources, the collected time parameters of multi-source data are compared and analyzed to more accurately quantify the degree of time deviation before multi-source data fusion. Then, based on the quantitative results of time alignment deviation, it is determined whether to perform time alignment regulation. By quantifying the time alignment deviation and performing time alignment regulation accordingly, it can be ensured that the multi-source data of wind, solar and water participating in the fusion are synchronized in time. For the delay in the data processing process, the expected multi-source data completion time of the next time window is adjusted to achieve accurate compensation for the delay, ensuring that the multi-source data maintains consistency in the time dimension before fusion. Finally, for the completion time of the final task of predicting water supply demand instructions, compensation is performed by adjusting the actual response time to ensure that the timeliness of the output meets the requirements, thereby improving the accuracy of wind, solar and water multi-source data fusion and the accuracy of predicting water supply demand.

[0012] 2. The quantitative results of the data fusion timeliness response are obtained based on the acquired timeliness response parameters to reflect the timeliness from the completion of multi-source data fusion to the reception and response to the predicted water supply demand instruction. Based on the quantitative results of the data fusion timeliness response, it is determined whether to perform PLC scanning interval regulation and monitoring verification. If the quantitative results of the data fusion timeliness response are lower than the preset threshold, if the PLC scanning interval regulation and monitoring verification are performed, time can be reserved for the predicted water supply demand instruction link, thereby ensuring that more complete, accurate and timely fusion data and predicted instructions can be obtained each time the PLC scans, thereby ensuring higher timeliness when executing the predicted water supply demand instruction.

[0013] 3. Water supply management is achieved by executing the predicted water supply demand instruction after performing PLC scanning interval regulation and monitoring verification. Otherwise, the predicted water supply demand instruction is executed directly and the PLC scanning interval is regulated. When the instruction response is delayed, the PLC scanning interval is increased to wait for more complete instructions and data to arrive, thereby ensuring that more reliable information can be obtained at the next scan. By increasing the PLC scanning interval, the possibility of erroneous execution due to incomplete data or untimely response to instructions is reduced, and the accuracy of water supply instructions is improved; the PLC scanning interval after regulation is monitored and verified to prevent the scanning interval from becoming too large or too small due to the PLC scanning interval compensation or correction, thereby affecting the normal operation or control effect of the PLC, ensuring that the PLC scanning interval does not exceed the safety upper limit of the system design, maintains the basic operating rhythm of the PLC and the real-time control capability of the system, and does not fall below the safety lower limit of the system design, ensuring that the PLC has enough time to complete the necessary processing tasks. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1A schematic diagram of the structure of an intelligent water supply management system based on wind, solar and water multi-source data fusion provided in an embodiment of the present application;

[0015] Figure 2 A flow chart showing the response time control of an intelligent water supply management system based on wind, solar, and water multi-source data fusion according to an embodiment of the present application;

[0016] Figure 3 A flow chart of the PLC scanning interval control of the intelligent water supply management system based on wind, solar and water multi-source data fusion provided in the embodiment of the present application;

[0017] Figure 4 Flowchart of the intelligent water supply management method based on the fusion of wind, solar and water multi-source data provided in the embodiment of this application. DETAILED DESCRIPTION

[0018] The embodiments of the present application provide an intelligent water supply management system and method based on multi-source data fusion of wind, solar and water, which solves the problem of poor flexibility in water supply management execution response caused by insufficient consideration of time differences in multi-source data processing in the prior art. By quantifying the time parameters of multi-source data, a time alignment deviation quantification result is obtained, and based on the time alignment deviation quantification result, it is determined whether time alignment regulation is to be performed. If so, the timeliness response parameter is obtained after regulation. Otherwise, the timeliness response parameter is directly obtained and quantified to obtain the data fusion timeliness response quantification result. Based on the data fusion timeliness response quantification result, it is determined whether PLC scanning interval regulation and monitoring verification are to be performed, thereby improving the timeliness of water supply management demand response.

[0019] The technical solution in the embodiments of the present application is to solve the problem of poor flexibility in water supply management execution response caused by insufficient consideration of the time differences in multi-source data processing. The overall idea is as follows:

[0020] The time alignment deviation quantification result is obtained by quantifying the time parameters of the obtained multi-source data. The time alignment deviation quantification result is used to determine whether time alignment regulation should be performed. If so, the timeliness response parameter is obtained after time alignment regulation to reflect the response timeliness of executing the predicted water supply demand instruction based on the multi-source data fusion result. Otherwise, the timeliness response parameter is directly obtained. The data fusion timeliness response quantification result is obtained based on the obtained timeliness response parameter. The data fusion timeliness response quantification result is used to determine whether PLC scanning interval regulation and monitoring verification should be performed. If so, the predicted water supply demand instruction is executed after PLC scanning interval regulation and monitoring verification to realize water supply management, thereby improving the timeliness of water supply management demand response.

[0021] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0022] like Figure 1 As shown, this is a structural diagram of the intelligent water supply management system based on the fusion of wind, solar and water multi-source data provided in an embodiment of the present application. The intelligent water supply management system based on the fusion of wind, solar and water multi-source data provided in an embodiment of the present application includes: a time alignment deviation quantification module, a time alignment control module, a data fusion timeliness response quantification module and a timeliness response control module.

[0023] As the first module of the intelligent water supply management system of this application, the time alignment deviation quantification module specifically includes a multi-source data time parameter acquisition unit, a time threshold storage unit, and a time alignment deviation evaluation unit. Specifically, this module is used to obtain a time alignment deviation quantification result based on the acquired multi-source data time parameters after multi-source data acquisition to reflect the time alignment deviation of multi-source data processing caused by timestamp differences in multi-source data acquisition. Multi-source data acquisition refers to the collection of wind, solar, and water multi-source data through a specified data acquisition method to generate predictive water supply instructions to implement water supply management.

[0024] It should be further explained that the multi-source data time parameter acquisition unit is used to obtain the multi-source data time parameters before multi-source data processing, specifically including the multi-source data time alignment error to reflect the degree of deviation between the actual aligned timestamp and the preset alignment timestamp when the multi-source data is aligned on the time axis, the meteorological-hydrological data delay difference to reflect the time difference between the meteorological data and the hydrological data before arriving at the fusion processing, and the edge-cloud time synchronization error. The edge-cloud time synchronization error is used to reflect the time deviation between the local clock of the edge computing node and the cloud server.

[0025] The time threshold storage unit is used to obtain the time threshold and time correction factor from the constructed intelligent water supply management database. The time threshold is used to compare with the time parameters of multi-source data to reflect the time alignment difference of multi-source data processing. The time correction factor is used to reflect the influence of the time parameters of multi-source data on the time alignment deviation of multi-source data processing. The time threshold specifically includes the multi-source data time alignment error threshold, the meteorological-hydrological data delay difference threshold and the edge-cloud time synchronization error threshold. The time correction factor specifically includes the multi-source data time alignment error correction factor, the meteorological-hydrological data delay difference correction factor and the edge-cloud time synchronization error correction factor.

[0026] The time alignment deviation evaluation unit is used to weight the multi-source data time parameters and the time threshold proportion processing results through the time correction factor to obtain the time alignment deviation quantification result.

[0027] In addition, when designing an intelligent water supply management system that integrates wind, solar, and water multi-source data, a pre-built intelligent water supply management database was used to store various key setting data. This includes various preset data required by the system, such as the multi-source data time alignment error threshold, the meteorological-hydrological data delay difference, and the edge-cloud time synchronization error threshold. The initial values ​​of these parameters are not set out of thin air, but are calculated by summing and averaging the data accumulated in the database, ensuring that the initial settings are objective and representative. In addition, to adapt to the complexity and ever-changing needs of actual application scenarios, all these values ​​in the database are not fixed. Instead, technicians can manually set, adjust, and fine-tune the system based on its performance during actual debugging, thereby optimizing the system parameters.

[0028] It should be noted that the specific steps to obtain the quantification result of the time alignment deviation are:

[0029] First, the multi-source data time alignment error correction factor is used to weight the ratio of the multi-source data time alignment error to the multi-source data time alignment error threshold to obtain the error impact value. The specific restriction expression is:

[0030] ;

[0031] Where F represents the error impact value, Q1 represents the multi-source data time alignment error correction factor obtained from the intelligent management database, M represents the multi-source data time alignment error obtained by the GPS (Global Positioning System) receiver. The multi-source data time alignment error refers to the absolute difference between the actual timestamp and the preset timestamp when the multi-source data is time-aligned on the time axis, and M0 represents the multi-source data time alignment error threshold obtained from the intelligent management database. It should be understood that there is a positive correlation between the multi-source data time alignment error and the time alignment deviation quantification result. The larger the multi-source data time alignment error, the less accurate the time alignment, and the larger the time alignment deviation quantification result.

[0032] Secondly, the delay difference correction factor of meteorological-hydrological data is used to weight the ratio of the delay difference of meteorological-hydrological data to the delay difference threshold of meteorological-hydrological data to obtain the delay difference impact value. The specific restriction expression is:

[0033] ;

[0034] Where B represents the delay impact value, Q2 represents the meteorological-hydrological data delay correction factor obtained from the intelligent management database, Y represents the meteorological-hydrological data delay calculated by recording the timestamps of the meteorological data arrival timeline and the timestamps of the hydrological data arrival timeline, and Y0 represents the meteorological-hydrological data delay threshold obtained from the intelligent management database. It is important to understand that the meteorological-hydrological data delay is positively correlated with the quantified time alignment deviation. A larger meteorological-hydrological data delay indicates a greater deviation in the arrival timestamps of the meteorological and hydrological data, and a larger quantified time alignment deviation.

[0035] Then, the edge-cloud time synchronization error correction factor is used to weight the ratio of the edge-cloud time synchronization error to the edge-cloud time synchronization error threshold to obtain the synchronization error impact value. The specific restriction expression is:

[0036] ;

[0037] Where H represents the synchronization error impact value, Q3 represents the edge-cloud time synchronization error correction factor obtained from the intelligent management database, D represents the edge-cloud time synchronization error obtained from the time server, which refers to the time deviation between the local clock on the edge computing node and the cloud server, and D0 represents the edge-cloud time synchronization error threshold obtained from the intelligent management database. It can be understood that there is a positive correlation between the edge-cloud time synchronization error and the quantified time alignment deviation. A larger edge-cloud time synchronization error means a larger time deviation between the local clock on the edge computing node and the cloud server, and a larger quantified time alignment deviation.

[0038] Finally, the error impact value, delay impact value, and synchronization error impact value are coupled to obtain the time alignment deviation quantification result. The specific restriction expression is:

[0039] ;

[0040] Where A represents the quantization result of time alignment deviation.

[0041] Specifically, the intelligent management database stores correction factors corresponding to the time parameters of multi-source data, namely the multi-source data time alignment error correction factor, the meteorological-hydrological data delay difference correction factor, and the edge-cloud time synchronization error correction factor. The values ​​usually range from 0 to 1, and the sum of the three is 1. There is a pre-set mapping relationship between these correction factors and the time parameters of multi-source data. This mapping relationship can be one-to-one or many-to-one. For example, in actual applications, the real-time multi-source data time parameters can be input into this mapping relationship to quickly obtain the corresponding correction factors.

[0042] Furthermore, the parameters involved in quantifying time alignment deviations are correlated, as follows: A larger delay difference between meteorological and hydrological data leads to inaccurate timestamp alignment of meteorological and hydrological data on the time axis, which in turn increases the time alignment error for multi-source data. A larger delay difference between meteorological and hydrological data leads to an instantaneous increase in cloud server load, resulting in large synchronization errors and larger edge-cloud time synchronization errors. Larger edge-cloud time synchronization errors also lead to an overall advance or lag in the timestamps of data uploaded to the cloud, causing alignment errors when fused with other source data (such as cloud-based meteorological data), and increasing the time alignment error for multi-source data. In summary, by understanding the correlation between the three parameters of edge-cloud time synchronization error, meteorological-hydrological data delay difference, and edge-cloud time synchronization error, the adaptive adjustment of multi-source data time parameters has a global vision capability, which helps to improve the adaptive adjustment of multi-source data time parameters, thereby reducing the multi-source data time alignment error, so that data from different sources can be more accurately matched on the time axis, thereby improving the accuracy of time alignment; by considering the positive and negative correlation between the above three parameters and the quantification results of time alignment deviation, it is helpful to perform time alignment regulation, thereby significantly improving the reliability of time alignment.

[0043] As the second module of the intelligent water supply management system of the present application, the time alignment control module is used to determine whether to perform time alignment control based on the quantification result of the time alignment deviation. If so, the timeliness response parameter is obtained after the time alignment control is performed to reflect the response time of executing the predicted water supply demand instruction based on the multi-source data fusion result. Otherwise, the timeliness response parameter is directly obtained. The time alignment control includes average delay control and response time control. The time alignment control including average delay control and response time control is determined based on the quantification result of the time alignment deviation to correct the data time deviation. The delay in the data processing process is compensated by the average delay control, and the actual completion time of the multi-source data processing is more accurately predicted, thereby improving the timeliness of the multi-source data in time alignment. When the predicted completion time of the multi-source data processing is greater than its preset threshold through response time control, additional response time compensation adjustment is performed, thereby improving the timeliness of the multi-source data in time alignment.

[0044] Specifically, the time alignment deviation quantification module accurately quantifies the time alignment deviation by performing threshold comparison and weighted coupling on the time parameters of multi-source data of wind, solar and water, providing data support for subsequent regulation; the time alignment control module initiates average delay control and response time control based on the deviation quantification results, compensates for data processing delay and corrects the predicted completion time, effectively improving the timeliness and timeliness of the alignment of multi-source data on the time axis.

[0045] As the third module of the intelligent water supply management system of this application, the data fusion timeliness response quantification module specifically includes: a timeliness response parameter acquisition unit, a timeliness response threshold storage unit and a timeliness response evaluation unit, which is used to obtain the data fusion timeliness response quantification result based on the acquired timeliness response parameters, so as to quantify the timeliness from the completion of multi-source data fusion to the reception and response of the predicted water supply demand instructions.

[0046] Specifically, the timeliness response parameter acquisition unit is used to obtain the time alignment deviation value of multi-source data and timeliness response parameters. The timeliness response parameters include data fusion-prediction delay, prediction instruction transmission delay, and prediction instruction reception and response delay. The data fusion-prediction delay represents the time from the completion of multi-source data fusion to the generation of water supply demand prediction instructions. The prediction instruction transmission delay represents the time from the generation of the water supply demand prediction instruction to the target execution device. The prediction instruction reception and response delay represents the time from the target execution device receiving the predicted water supply demand instruction to the completion of instruction parsing and preparation for executing the water supply management operation corresponding to the predicted water supply demand instruction.

[0047] Timeliness response threshold storage unit: used to obtain the timeliness response threshold, preset time alignment deviation threshold, time alignment deviation correction factor and timeliness response correction factor from the constructed intelligent water supply management database. The timeliness response threshold is used to compare with the timeliness response parameter to reflect the timeliness of the execution of the water supply demand forecast instruction from data fusion. The timeliness response correction factor is used to reflect the quantitative degree of the timeliness response parameter to the timeliness response of data fusion. The timeliness response threshold includes the time alignment deviation threshold, the prediction delay threshold, the transmission delay threshold and the response delay threshold. The timeliness response correction factor includes the time alignment deviation correction factor, the prediction delay correction factor, the transmission delay correction factor and the response delay correction factor.

[0048] Timeliness response evaluation unit: used to couple the first timeliness response indicator with the second timeliness response indicator to obtain the data fusion timeliness response quantitative result. The first timeliness response indicator is represented by the result of weighted coupling of the timeliness response threshold and the proportion of the timeliness response parameter through the timeliness response correction factor. The second timeliness response indicator is represented by the result of weighted coupling of the time alignment deviation threshold and the proportion of the time alignment deviation value of multi-source data through the preset time alignment deviation correction factor.

[0049] It should be noted that the specific steps to obtain the quantitative results of the data fusion timeliness response are: weighting the time alignment deviation threshold and the proportion of the multi-source data time alignment deviation value by the time alignment deviation correction factor to obtain the deviation correction value. The specific restriction expression is:

[0050] ;

[0051] Where S represents the deviation correction value, G1 represents the time alignment deviation correction factor obtained from the intelligent management database, N0 represents the preset time alignment deviation threshold obtained from the intelligent management database, and N represents the multi-source data time alignment deviation value. It is important to understand that the multi-source data time alignment deviation value is negatively correlated with the quantitative results of the data fusion timeliness response. A larger multi-source data time alignment deviation value indicates longer data preparation time, increased overall data fusion time consumption, and a smaller quantitative result of the data fusion timeliness response. k1 represents a constant term to avoid meaningless numbers.

[0052] Secondly, the predicted delay correction factor is used to weight the predicted delay threshold and the data fusion-predicted delay ratio to obtain the predicted delay correction value. The specific restriction expression is:

[0053] ;

[0054] Where C represents the prediction delay correction value, G2 represents the prediction delay correction factor obtained from the intelligent management database, R0 represents the prediction delay threshold obtained from the intelligent management database, and R represents the data fusion-prediction delay obtained from the cloud server, which refers to the time difference between data fusion completion and prediction result generation. It is important to understand that there is a negative correlation between the data fusion-prediction delay and the quantitative results of data fusion timeliness response. A longer data fusion-prediction delay means a longer period from data input to prediction result output, and a lower quantitative result of data fusion timeliness response.

[0055] Next, the transmission delay correction factor is used to weight the transmission delay threshold and the ratio of the predicted instruction transmission delay to obtain the transmission delay correction value. The specific restriction expression is:

[0056] ;

[0057] Where V represents the transmission delay correction value, G3 represents the transmission delay correction factor obtained from the intelligent management database, U0 represents the transmission delay threshold obtained from the intelligent management database, and U represents the predicted instruction transmission delay obtained using network measurement equipment such as a delay meter. It is important to understand that there is a negative correlation between the predicted instruction transmission delay and the quantitative results of data fusion timeliness response. A longer predicted instruction transmission delay indicates a greater deviation between the scenario at the time the instruction arrives and the predicted scenario, and a lower quantitative result of data fusion timeliness response.

[0058] Then, the response delay correction factor is used to weight the response delay threshold and the ratio of the predicted instruction reception and response delay to obtain the response delay correction value. The specific restriction expression is:

[0059] ;

[0060] Where T represents the response delay correction value, G4 represents the response delay correction factor obtained from the intelligent management database, Q0 represents the response delay threshold obtained from the intelligent management database, and Q represents the predicted instruction reception and response delay calculated from the timestamp recorded from the time the predicted water supply demand instruction is received to the time the instruction is parsed and the corresponding water supply management operation is executed. It should be understood that the predicted instruction reception and response delay is negatively correlated with the quantitative results of data fusion timeliness response. The longer the predicted instruction reception and response delay, the longer the time from instruction reception to action completion, and the smaller the quantitative results of data fusion timeliness response.

[0061] Finally, the quantitative result of data fusion timeliness response is obtained by coupling the deviation correction value, prediction delay correction value, transmission delay correction value, and response delay correction value. The specific restriction expression is:

[0062] ;

[0063] Where P represents the quantitative result of data fusion timeliness response.

[0064] It should be noted that the intelligent management database stores correction factors corresponding to timeliness response parameters, namely, the time alignment deviation correction factor, the prediction delay correction factor, the transmission delay correction factor, and the response delay correction factor. These correction factors typically range from 0 to 1, and their sum is 1. These correction factors are mapped to timeliness response parameters in a pre-defined relationship, which can be either one-to-one or many-to-one. For example, in practical applications, real-time response parameters can be input into this mapping relationship to quickly obtain the corresponding correction factors.

[0065] In addition, the parameters involved in the quantitative results of data fusion timeliness response are correlated, as follows: the larger the time alignment deviation of multi-source data, the longer the data preprocessing time, which in turn prolongs the overall time consumption of data fusion and prediction, and the longer the data fusion-prediction delay; instructions can only be generated after data fusion and prediction are completed. The longer the data fusion-prediction delay, the later the instruction generation time is, the correspondingly delayed transmission start time is, and the longer the prediction instruction transmission delay is; the execution end is not triggered until the instruction transmission is completed. The longer the prediction instruction transmission delay, the later the instruction arrives at the execution end, the delayed execution start time is, and the longer the prediction instruction reception and response delay is. In short, by understanding the correlation between the above four parameters, it is helpful to improve the adaptive adjustment of timeliness response parameters, thereby reducing the delay from the completion of multi-source data fusion to the execution of the predicted water supply demand instruction, making the response speed of the predicted water supply demand instruction execution faster and improving the timeliness of response; by considering the positive and negative correlations between the above four parameters and the quantitative results of data fusion timeliness response, it is helpful to control and monitor the PLC scan interval, thereby significantly improving the timeliness from the completion of multi-source data fusion to the execution of the predicted water supply demand instruction.

[0066] As the fourth module of the intelligent water supply management system of the present application, the timeliness response control module is used to determine whether to perform PLC scanning interval control and monitoring verification based on the data fusion timeliness response quantification results. If so, the water supply management operation corresponding to the predicted water supply demand instruction is executed after the PLC scanning interval control and monitoring verification are performed. Otherwise, the water supply management operation is directly executed. Whether to perform PLC scanning interval control and monitoring verification is determined based on the data fusion timeliness response quantification results to improve the reliability of water supply management. PLC scanning interval control is used to reduce low operating efficiency caused by delays in processing predicted water supply demand instructions, thereby improving the timeliness of executing predicted water supply demand instructions. The purpose of monitoring verification is to prevent data lag due to inaccurate PLC scanning intervals, thereby improving the response speed of predicted water supply demand instructions.

[0067] Specifically, the data fusion timeliness response quantification module quantifies the timeliness of the entire process from data fusion to command response through evaluation and coupling calculation, while the timeliness response control module reduces command processing delays through PLC scanning interval control, combines monitoring verification to prevent data lag, and further improves the execution reliability of water supply management operations.

[0068] In this embodiment, this application achieves a dual improvement in the time alignment accuracy of multi-source data and the response efficiency of water supply management through the collaborative work of multiple modules. Through the dynamic quantification, regulation and adaptive correction of the time parameters and response time of multi-source data by each module, a full-link time accuracy control mechanism from data acquisition to instruction execution is formed, which not only achieves accurate matching of multi-source data in the time dimension and reduces the data fusion error caused by time deviation, but also shortens the cycle from water supply demand prediction to actual execution through real-time response regulation, improves the real-time response capability of the water supply management system to changes in wind, solar and water data, and ultimately realizes intelligent, precise and efficient water supply management.

[0069] It should be noted that wind power generation uses small and medium-sized horizontal-axis wind turbines suitable for mountainous environments, equipped with variable pitch control and low-wind-speed start-up capabilities. Photovoltaic power generation uses high-efficiency bifacial photovoltaic modules equipped with intelligent tracking brackets to adapt to the complex terrain and lighting conditions of mountainous areas. Hydropower generation uses micro-hydroelectric power generation equipment suitable for local hydrological conditions, including impulse, tubular, or Francis turbines. A water resource monitoring subsystem comprehensively monitors the water resource status and environmental conditions of the water supply system, including: water level sensors to monitor water level changes at key nodes such as water sources, reservoirs, and water towers; flow sensors to monitor water flow and flow rate at key points in the pipeline network; water quality sensors to monitor water quality parameters such as turbidity, pH, and dissolved oxygen; and meteorological monitoring equipment to collect meteorological data such as rainfall, temperature, and humidity.

[0070] In response to the strong seasonality and wide speed variations of wind resources in mountainous areas, this invention utilizes variable-pitch wind turbine technology. This technology adjusts the blade angle in real time based on wind speed, enabling power generation in low-speed areas and automatically adjusting to a safe state in high-wind conditions, improving power generation efficiency. This wide-wind-speed-range power generation technology, employing a doubly-fed asynchronous generator and an intelligent control system, effectively expands the turbine's operating wind speed range and significantly increases wind energy utilization in mountainous areas. Under low-speed conditions, optimized torque control and power curve adjustment ensure maximum wind energy capture efficiency. A wind resource assessment and prediction algorithm employs multi-point wind speed and direction monitoring devices. This, combined with meteorological data and terrain characteristics, establishes a machine-learning-based wind resource assessment and prediction model. This model offers a long prediction timeframe and significantly improves accuracy, providing a key basis for optimized wind energy scheduling. Through decentralized wind turbine cluster control, a small wind turbine cluster network control system is designed to address the dispersed nature of mountainous areas. This allows for flexible deployment in diverse terrain conditions, and the intelligent control system enables coordinated cluster operation and smooth power output.

[0071] Furthermore, the specific control steps for determining whether to perform time alignment control based on the quantification result of the time alignment deviation are as follows: if the quantification result of the time alignment deviation is lower than or equal to the preset time alignment deviation threshold, time alignment control is not performed; if the quantification result of the time alignment deviation is greater than the preset time alignment deviation threshold, whether to perform average delay control is determined based on the average processing time of multi-source data within the preset time window; if so, whether to perform response time control is determined after performing average delay control; otherwise, whether to perform response time control is directly determined; the average processing time of multi-source data represents the average efficiency of processing multi-source data of wind, solar and water within the preset time window.

[0072] As a further specific solution, the specific steps for determining whether to perform average delay control are as follows:

[0073] If the average processing time of multi-source data in the current preset time window is greater than the preset multi-source data processing time threshold, the average delay compensation amount in the preset time window is obtained by weighted averaging the time base deviation contribution and the processing time contribution. The result of adding the average delay compensation amount and the multi-source data preset processing completion time of a single preset time window is used as the multi-source data predicted processing completion time of the next preset time window, which is used to predict the processing completion time of the multi-source data to be processed, thereby more accurately capturing the temporal change law in the data processing process. The average delay compensation amount is obtained by weighted averaging the time base deviation contribution and the processing time contribution, so that the prediction result is closer to the actual processing time, and finally realizes dynamic and accurate prediction of the multi-source data processing completion time, provides a reliable time base for the timely triggering of subsequent water supply management instructions, improves the prediction accuracy of the multi-source data processing completion time, and thereby improves the timeliness of time alignment. Among them, the weights of the time base deviation contribution and the processing time contribution are obtained from the intelligent water supply management database. The time base deviation contribution represents the difference between the time alignment deviation quantification result and the preset time alignment deviation threshold. The processing time contribution represents the difference between the average processing time of multi-source data in the current preset time window and the preset multi-source data processing time threshold. The average processing time of multi-source data in the preset time window represents the average time spent on processing multi-source data in the preset time window obtained in the intelligent water supply management database.

[0074] If the average processing time of multi-source data in the current preset time window is less than or equal to the preset multi-source data processing time threshold, the preset processing completion time of multi-source data in a single preset time window is used as the predicted processing completion time of multi-source data in the next preset time window, and it is directly determined whether to perform response time control.

[0075] In this embodiment, by monitoring the average processing time of multi-source data within a preset time window and comparing it with a preset threshold, adaptive adjustment of data processing delay is achieved, significantly improving the accuracy of the prediction of the completion time of multi-source data processing in the next preset time window, thereby improving the timeliness of time alignment and making the time synchronization of multi-source data in the processing flow more accurate. Overall, average delay control effectively alleviates the problem of multi-source data timestamp discrepancies caused by data processing delays, enhances the real-time performance and reliability of the data fusion link in intelligent water supply management, and lays a solid foundation for subsequent precise control based on time-aligned data.

[0076] like Figure 2 As shown, it is a response time control flow chart of the intelligent water supply management system based on the fusion of wind, solar and water multi-source data provided in an embodiment of the present application, which specifically includes: judging whether the multi-source data predicted processing completion time is greater than the preset multi-source data predicted completion time threshold; if so, calculating the time reference deviation contribution and the predicted time contribution weighted to obtain the response time compensation amount, and adding the response time compensation amount to the preset processing response time as the corresponding actual processing response time; otherwise, no response time control is performed.

[0077] As a further specific solution, the specific execution steps for determining whether to perform response time control are as follows:

[0078] If the multi-source data prediction processing completion time of the next preset time window is greater than the preset multi-source data prediction completion time threshold, the response time compensation amount is obtained by weighted average based on the time benchmark deviation contribution and the prediction time contribution, and the result of adding the response time compensation amount and the processing response preset time of a single preset time window is used as the corresponding processing response actual time, wherein the prediction time contribution represents the difference between the multi-source data prediction processing completion time of the next preset time window and the preset multi-source data prediction completion time threshold.

[0079] If the multi-source data prediction processing completion time of the next preset time window is less than or equal to the preset multi-source data prediction completion time threshold, no response time control is performed.

[0080] In this embodiment, the weighted average of the benchmark deviation contribution and the predicted time contribution is coupled, where the time benchmark deviation contribution reflects the processing rhythm deviation caused by the inconsistency of the time benchmark, and the predicted time contribution reflects the deviation amplitude of the current predicted time. The weighted fusion of the two can simultaneously take into account the dual effects of the time benchmark offset and the predicted time deviation, avoiding compensation deviation caused by a single factor; then, a response time compensation amount is generated, and the amount of time required for additional compensation is determined by the weighted average result. This compensation amount can dynamically match the actual situation of the current processing delay. For example, when the time benchmark deviation is large and the predicted time deviation is serious, the compensation amount will automatically increase to cover the potential delay; finally, the actual processing response time is adjusted, and the compensation amount is added to the preset processing response time to form a corrected actual response time. This operation enables the response time prediction model to absorb the combined impact of the predicted processing time deviation and the time benchmark error in real time. When the predicted processing completion time is greater than the predicted processing completion time threshold, the response buffer time is reserved in advance through the compensation amount to ensure that the water supply instruction can be quickly triggered and executed after the actual processing is completed, avoiding the instruction response lag caused by the prediction deviation. If the predicted processing completion time does not exceed the threshold, no regulation is performed to ensure that the system maintains efficient operation under normal conditions. The entire process achieves dynamic calibration of the response time of multi-source data processing through a closed-loop mechanism of "deviation identification-contribution quantification-weighted compensation-response correction". It not only accurately responds to systematic delays caused by time base deviations, but also adaptively compensates according to the degree of deviation from the predicted time. This significantly improves the timeliness and reliability of the water supply management system's response to instructions after data processing is completed, reduces water supply scheduling delays caused by time prediction errors, and ensures the efficiency of water resource allocation.

[0081] Furthermore, the specific judgment steps for determining whether to perform PLC scanning interval regulation and monitoring verification based on the data fusion timeliness response quantification result are as follows: if the data fusion timeliness response quantification result is greater than or equal to the preset timeliness response threshold, data fusion timeliness response optimization is not performed; if the data fusion timeliness response quantification result is within the preset timeliness response safety interval, the PLC scanning interval is regulated to adapt to the scanning requirements of the water supply management operation corresponding to the predicted water supply demand instruction, and the regulated PLC scanning interval is verified. The preset timeliness response safety interval represents the open interval formed by the preset timeliness response safety threshold and the preset timeliness response threshold; if the data fusion timeliness response quantification result is less than or equal to the preset timeliness response safety threshold, an early warning prompt is sent to the staff.

[0082] like Figure 3As shown, a PLC scanning interval control flow chart of an intelligent water supply management system based on wind, solar and water multi-source data fusion provided in an embodiment of the present application, the specific logic is: according to the predicted instruction reception and response delay, it is judged whether it is greater than or equal to the preset response delay threshold value; if so, the data fusion timeliness response quantification result and the response delay contribution are input into the intelligent water supply management database to map to obtain the PLC scanning interval compensation amount, and the result of adding the PLC scanning interval compensation amount and the preset PLC scanning interval is used as the PLC scanning interval to be determined; otherwise, it is judged whether the predicted instruction reception and response delay is within the preset response delay safety range; if so, the data fusion timeliness response quantification result and the predicted instruction reception and response delay are input into the intelligent water supply management database to map to obtain the PLC scanning interval correction amount, and the result of calculating the difference between the PLC scanning interval correction amount and the preset PLC scanning interval is used as the PLC scanning interval to be determined; otherwise, the PLC scanning interval control is not performed, and the preset PLC scanning interval is used as the final PLC scanning interval.

[0083] As a further specific solution, the specific execution steps for PLC scanning interval control are:

[0084] If the predicted command reception and response delay is greater than or equal to the preset response delay threshold, the data fusion timeliness response quantification result and the response delay contribution are input into the intelligent water supply management database to map the PLC scan interval compensation value. The PLC scan interval compensation value is added to the preset PLC scan interval as the PLC scan interval to be determined. The response delay contribution value represents the difference between the predicted command reception and response delay and the preset response delay threshold. In the case of excessive delay (predicted command reception and response delay is greater than the preset response delay safety threshold), the scan interval is increased by the compensation value, reducing the processor load and alleviating the command processing delay. This extension operation ensures that the PLC has more time to process the control logic that may become complex due to the increased delay, reducing the risk of control command loss or incomplete execution due to too short a scan interval, thereby improving the stability and reliability of the control system.

[0085] If the predicted instruction reception and response delay is within the preset response delay safety interval, the data fusion timeliness response quantification result and the predicted instruction reception and response delay are input into the intelligent water supply management database to map and obtain the PLC scan interval correction value. The difference between the PLC scan interval correction value and the preset PLC scan interval is used as the PLC scan interval to be determined, and a shortened PLC scan interval to be determined is obtained. This shortening operation aims to optimize system performance and improve the real-time and response speed of control through a faster scanning frequency, especially when the system load is light and the processing capacity is sufficient, thereby improving resource utilization efficiency. The scanning frequency is fine-tuned by the correction value to preventively optimize the response efficiency. The preset response delay safety interval represents the open interval formed by the preset response delay safety threshold and the preset response delay threshold.

[0086] If the predicted command reception and response delay is less than or equal to the preset response delay safety threshold, the PLC scan interval is not adjusted, and the preset PLC scan interval is used as the final PLC scan interval. This mechanism not only avoids the problems of excessive scanning congestion or insufficient scanning lag caused by fixed scan intervals, but also enables the PLC scanning strategy to respond to delay changes in real time through the dynamic adaptability of database mapping. Ultimately, this improves the timeliness and reliability of water supply management command execution, prevents data lag or processing congestion caused by the PLC scanning mechanism, and ensures real-time synchronization of water resource allocation operations with multi-source data fusion results.

[0087] In this embodiment, the system achieves precise control of the PLC scan frequency through a closed-loop mechanism: delay interval determination, contribution quantification, dynamic mapping compensation, and adaptive adjustment of the scan interval. This mechanism dynamically adjusts the scan interval based on actual operating conditions, achieving an optimal balance between control accuracy, response speed, and system stability, making PLC control more intelligent, efficient, and reliable.

[0088] As a further specific solution, the specific steps for verifying the adjusted PLC scanning interval are as follows:

[0089] If the PLC scan interval to be determined is greater than or equal to the preset interval upper limit threshold, the data fusion timeliness response quantification result and the interval maximum deviation are input into the intelligent water supply management database to map the PLC scan interval control value. The result of subtracting the PLC scan interval control value from the PLC scan interval is used as the final PLC scan interval. The maximum interval deviation represents the difference between the PLC scan interval to be determined and the preset interval upper limit threshold. It can be understood that when the interval to be determined is too large, by introducing the "maximum interval deviation" and the timeliness response quantification result to calculate the "control value" and subtracting it from the interval to be determined, the problem of control response lag and system real-time performance degradation caused by excessively long scan intervals is effectively prevented, ensuring that control instructions can be processed and executed in a timely manner.

[0090] If the PLC scan interval to be determined is within the preset interval, the PLC scan interval to be determined is directly used as the final PLC scan interval. The preset interval represents the open interval formed by the preset lower and upper thresholds. It can be understood that when the interval to be determined is within the preset interval, the interval is directly determined as the final value. This demonstrates the system's adaptive adjustment capability within a reasonable range, responding to previous control requirements while avoiding unnecessary additional calculations and ensuring efficiency. This ensures system stability and avoids two extreme problems caused by unbounded adjustment of the PLC scan interval: missed instructions due to an excessively large interval or hardware congestion due to a too small interval. The dynamic adaptability of the database mapping enables the scanning strategy to respond in real time to data fusion timeliness and hardware load status. Ultimately, the PLC scan interval is precisely constrained within a reasonable range, ensuring the timely capture and execution of water supply management instructions while avoiding excessive consumption of hardware resources. This improves the reliability, stability, and operational efficiency of the entire intelligent water supply system and ensures real-time synchronization between multi-source data fusion results and water supply scheduling operations.

[0091] If the PLC scan interval to be determined is less than or equal to the preset lower threshold, the data fusion timeliness response quantification result and the minimum interval deviation are input into the intelligent water supply management database to map the PLC scan interval correction value. The sum of the PLC scan interval and the PLC scan interval correction value is used as the final PLC scan interval. The PLC scan interval correction value is used to extend the cycle to alleviate processor load. The minimum interval deviation represents the difference between the preset lower threshold and the PLC scan interval to be determined. It can be understood that when the interval to be determined is too short, the "minimum interval deviation" and the timeliness response quantification result are used to calculate the "correction value" and add it to the interval to be determined. This effectively prevents excessive CPU processing pressure, instruction execution conflicts, or frame drops that may be caused by a short scan interval, ensuring the stable operation and reliability of the PLC system. PLC interval control calculates a preliminary, expected PLC scan interval adjustment value based on the predicted instruction reception and response delay. This verification step calibrates this preliminary result based on the overall system safety constraints (upper and lower thresholds).

[0092] In this embodiment, a closed-loop mechanism of "interval determination-deviation quantification-dynamic mapping-interval correction" is used to achieve bidirectional constraint and adaptive optimization of the PLC scan interval: the cycle is reduced by comparing the PLC scan interval to improve the response sensitivity. This verification step is a crucial safety and rationality guarantee link in the dynamic adjustment process of the PLC scan interval, ensuring that the PLC scan interval to be determined calculated by predicting the instruction reception and response delay falls within the reasonable working range allowed by the system. The PLC scan interval regulation determines the direction and initial amplitude of the adjustment, while the monitoring verification ensures that the final scan interval not only meets the optimization goal of the previous step, but also does not exceed the stability limit of the system hardware or control logic, making the entire dynamic adjustment process of the PLC scan interval both flexible and safe, achieving dual optimization of system performance and stability, and ensuring that the intelligent water supply management system can operate stably and efficiently under various working conditions.

[0093] like Figure 4 As shown, it is a flow chart of the intelligent water supply management method based on the fusion of wind, solar and water multi-source data provided by the embodiment of the present application. The intelligent water supply management method based on the fusion of wind, solar and water multi-source data provided by the embodiment of the present application includes the following steps: after multi-source data collection, according to the acquired multi-source data time parameters, a time alignment deviation quantification result is obtained to reflect the time alignment deviation degree of multi-source data processing caused by the timestamp difference of multi-source data collection. Multi-source data collection means collecting wind, solar and water multi-source data through a specified data collection method to generate a predictive water supply instruction to realize water supply management; judging whether to perform time alignment regulation according to the time alignment deviation quantification result, and if so, performing time alignment regulation Then, the timeliness response parameters are obtained to reflect the response timeliness of executing the predicted water supply demand instruction based on the multi-source data fusion results. Otherwise, the timeliness response parameters are directly obtained. The time alignment control includes average delay control and response time control. According to the obtained timeliness response parameters, the quantitative results of data fusion timeliness response are obtained to quantify the timeliness from the completion of multi-source data fusion to the reception and response of the predicted water supply demand instruction. According to the quantitative results of data fusion timeliness response, it is determined whether to perform PLC scanning interval control and monitoring verification. If so, the water supply management operation corresponding to the predicted water supply demand instruction is executed after performing PLC scanning interval control and monitoring verification. Otherwise, the water supply management operation is executed directly.

[0094] In this embodiment, in mountainous terrain with complex and uneven wind speed distribution, a sensor network collects real-time data on wind, solar, and hydropower generation, as well as energy storage status, water level, flow rate, and water demand, to ensure timely and accurate control decisions. The system supports local caching of high-frequency data and uploading of low-frequency data, balancing real-time performance with communication overhead. Based on superior dispatch instructions and local status, it controls the operating status and output power of each energy device in real time, controlling pumps, valves, and other equipment to achieve precise energy distribution and water supply control. It receives strategic dispatch instructions from the cloud-based decision-making layer, breaks them down into specific instructions executable by each local site, monitors their execution, and provides feedback on execution results and regional status to the cloud. A two-way feedback mechanism is established to ensure effective execution and timely adjustments to strategic decisions. A closed-loop mechanism, from data prediction to decision execution and feedback optimization, is established to achieve continuous system optimization. The system innovatively employs a four-step "prediction-execution-feedback-learning" cycle. Each dispatch cycle includes: predicting future trends based on historical data and current status; developing an optimal dispatch strategy based on the predicted results; executing the strategy and collecting feedback data; and adjusting the forecast and decision models based on the feedback. This closed-loop mechanism can continuously improve the system's prediction accuracy and decision-making quality, enabling the system to have self-optimization capabilities and continuously improve performance over time.

[0095] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0099] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0100] Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if such modifications and variations fall within the scope of the claims and their equivalents, the present invention is intended to include such modifications and variations.

Claims

1. Intelligent water supply management system based on wind, solar and water multi-source data fusion, characterized by: It includes time alignment deviation quantification module, time alignment control module, data fusion timeliness response quantification module and timeliness response control module: The time alignment deviation quantification module is used to obtain a time alignment deviation quantification result based on the acquired multi-source data time parameters after multi-source data collection to reflect the time alignment deviation of multi-source data processing caused by the timestamp difference of multi-source data collection. The multi-source data collection means collecting wind, solar and water multi-source data through a specified data collection method to generate a predicted water supply instruction to realize water supply management; The time alignment control module is used to determine whether to perform time alignment control based on the quantified result of the time alignment deviation. If so, after performing time alignment control, a timeliness response parameter is obtained to reflect the response time of executing the predicted water supply demand instruction based on the multi-source data fusion result. Otherwise, the timeliness response parameter is directly obtained. The time alignment control includes average delay control and response time control. The data fusion timeliness response quantification module is used to couple the first timeliness response indicator with the second timeliness response indicator according to the acquired timeliness response parameter to obtain a data fusion timeliness response quantification result, so as to quantify the timeliness from the completion of multi-source data fusion to the reception and response of the predicted water supply demand instruction. The first timeliness response indicator is represented by a result of weighted coupling of a timeliness response threshold and a proportion of the timeliness response parameter using a timeliness response correction factor, and the second timeliness response indicator is represented by a result of weighted coupling of a time alignment deviation threshold and a proportion of the multi-source data time alignment deviation value using a preset time alignment deviation correction factor. The timeliness response control module is used to determine whether to perform PLC scanning interval control and monitoring verification based on the data fusion timeliness response quantification results. If so, the water supply management operation corresponding to the predicted water supply demand instruction is executed after the PLC scanning interval control and monitoring verification are performed; otherwise, the water supply management operation is directly executed.

2. The intelligent water supply management system based on wind, solar and water multi-source data fusion as claimed in claim 1 is characterized in that: The time alignment deviation quantification module includes a multi-source data time parameter acquisition unit, a time threshold storage unit and a time alignment deviation evaluation unit; The multi-source data time parameter acquisition unit is used to obtain the multi-source data time parameters before multi-source data processing, specifically including the multi-source data time alignment error, the meteorological-hydrological data delay difference, and the edge-cloud time synchronization error; The time threshold storage unit is used to obtain a time threshold and a time correction factor from the constructed intelligent water supply management database, wherein the time threshold is used to compare with the multi-source data time parameter to reflect the time alignment difference of the multi-source data processing, and the time correction factor is used to reflect the influence of the multi-source data time parameter on the time alignment deviation of the multi-source data processing; The time alignment deviation evaluation unit is used to perform weighted coupling on the processing results of the proportion of multi-source data time parameters and time thresholds through a time correction factor to obtain a quantitative result of the time alignment deviation.

3. The intelligent water supply management system based on wind, solar and water multi-source data fusion as claimed in claim 2 is characterized in that: The specific control steps for determining whether to perform time alignment control according to the quantified result of the time alignment deviation are: If the time alignment deviation quantification result is lower than or equal to the preset time alignment deviation threshold, no time alignment control is performed; If the time alignment deviation quantification result is greater than the preset time alignment deviation threshold, then determine whether to perform average delay control based on the average processing time of multi-source data within the preset time window. If so, determine whether to perform response time control after performing average delay control. Otherwise, determine whether to perform response time control directly. The average multi-source data processing time represents the average efficiency of processing wind, solar, and water multi-source data within a preset time window.

4. The intelligent water supply management system based on wind, solar and water multi-source data fusion as claimed in claim 3 is characterized in that: The specific steps of determining whether to perform average delay control are as follows: If the average processing time of the multi-source data in the current preset time window is greater than the preset multi-source data processing time threshold, the average delay compensation amount in the preset time window is obtained by weighted averaging the time base deviation contribution and the processing time contribution, and the result of superimposing the average delay compensation amount and the preset processing completion time of the multi-source data in a single preset time window is used as the multi-source data predicted processing completion time of the next preset time window. The time base deviation contribution represents the degree of deviation between the time alignment deviation quantization result and the preset time alignment deviation threshold, and the processing time contribution represents the degree of deviation between the average processing time of the multi-source data in the current preset time window and the preset multi-source data processing time threshold; If the average processing time of multi-source data in the current preset time window is less than or equal to the preset multi-source data processing time threshold, the preset processing completion time of multi-source data in a single preset time window is used as the predicted processing completion time of multi-source data in the next preset time window, and it is directly determined whether to perform response time control.

5. The intelligent water supply management system based on wind, solar and water multi-source data fusion as claimed in claim 4 is characterized in that: The specific execution steps of determining whether to perform response time regulation are as follows: If the multi-source data predicted processing completion time of the next preset time window is greater than the preset multi-source data predicted completion time threshold, a response time compensation amount is obtained by weighted average based on the time base deviation contribution and the predicted time contribution, and the result of superimposing the response time compensation amount and the processing response preset time of a single preset time window is used as the corresponding processing response actual time. The predicted time contribution indicates the degree of deviation between the multi-source data predicted processing completion time of the next preset time window and the preset multi-source data predicted completion time threshold; If the multi-source data prediction processing completion time of the next preset time window is less than or equal to the preset multi-source data prediction completion time threshold, no response time control is performed.

6. The intelligent water supply management system based on wind, solar and water multi-source data fusion as claimed in claim 1 is characterized in that: The data fusion timeliness response quantification module includes a timeliness response parameter acquisition unit, a timeliness response threshold storage unit and a timeliness response evaluation unit; The timeliness response parameter acquisition unit is used to acquire a multi-source data time alignment deviation value and a timeliness response parameter, wherein the timeliness response parameter includes a data fusion-prediction delay, a prediction instruction transmission delay, and a prediction instruction reception and response delay; The timeliness response threshold storage unit is used to obtain a timeliness response threshold, a preset time alignment deviation threshold, a time alignment deviation correction factor and a timeliness response correction factor from the constructed intelligent water supply management database. The timeliness response threshold is used to be compared with the timeliness response parameter to reflect the timeliness of the execution of the water supply demand forecast instruction from data fusion. The timeliness response correction factor is used to reflect the degree of quantification of the timeliness response parameter to the timeliness response of the data fusion.

7. The intelligent water supply management system based on wind, solar and water multi-source data fusion as claimed in claim 6 is characterized in that: The specific judgment steps for judging whether to perform PLC scanning interval control and monitoring verification based on the data fusion timeliness response quantification result are as follows: If the quantitative result of the data fusion timeliness response is greater than or equal to the preset timeliness response threshold, the data fusion timeliness response optimization will not be performed; If the data fusion timeliness response quantification result is within the preset timeliness response safety interval, the PLC scanning interval is adjusted to adapt to the scanning demand of the water supply management operation corresponding to the predicted water supply demand instruction, and the adjusted PLC scanning interval is verified. The preset timeliness response safety interval represents the open interval formed by the preset timeliness response safety threshold and the preset timeliness response threshold; If the quantitative result of the data fusion timeliness response is less than or equal to the preset timeliness response safety threshold, an early warning prompt will be sent to the staff.

8. The intelligent water supply management system based on wind, solar and water multi-source data fusion as claimed in claim 7 is characterized in that: The specific steps for performing PLC scanning interval control are: If the predicted instruction reception and response delay is greater than or equal to the preset response delay threshold, the data fusion timeliness response quantification result and the response delay contribution are input into the intelligent water supply management database to map and obtain the PLC scan interval compensation amount. The result of superimposing the PLC scan interval compensation amount and the preset PLC scan interval is used as the PLC scan interval to be determined. The response delay contribution indicates the degree of deviation between the predicted instruction reception and response delay and the preset response delay threshold. If the predicted instruction reception and response delay is within the preset response delay safety interval, the data fusion timeliness response quantification result and the predicted instruction reception and response delay are input into the intelligent water supply management database for mapping to obtain the PLC scan interval correction value, and the difference between the PLC scan interval correction value and the preset PLC scan interval is used as the PLC scan interval to be determined. The preset response delay safety interval represents an open interval formed by a preset response delay safety threshold and a preset response delay threshold. If the predicted instruction reception and response delay is less than or equal to the preset response delay safety threshold, the PLC scan interval adjustment is not performed, and the preset PLC scan interval is used as the final PLC scan interval.

9. The intelligent water supply management system based on wind, solar and water multi-source data fusion as claimed in claim 8, characterized in that: The specific steps for verifying the adjusted PLC scanning interval are as follows: If the PLC scanning interval to be determined is greater than or equal to the preset interval upper limit threshold, the data fusion timeliness response quantification result and the interval maximum deviation are input into the intelligent water supply management database to map and obtain the PLC scanning interval control value. The result of correcting the PLC scanning interval based on the PLC scanning interval control value is used as the final PLC scanning interval. The interval maximum deviation value represents the degree of deviation between the PLC scanning interval to be determined and the preset interval upper limit threshold; If the PLC scanning interval to be determined is within the preset interval range, the PLC scanning interval to be determined is directly used as the final PLC scanning interval, where the preset interval range represents an open interval formed by a preset interval lower limit threshold and a preset interval upper limit threshold; If the PLC scanning interval to be determined is less than or equal to the preset interval lower limit threshold, the data fusion timeliness response quantification result and the interval minimum deviation are input into the intelligent water supply management database to map to obtain the PLC scanning interval correction amount. The result of correcting the PLC scanning interval based on the PLC scanning interval correction amount is used as the final PLC scanning interval. The minimum interval deviation represents the degree of deviation between the preset interval lower limit threshold and the PLC scanning interval to be determined.

10. An intelligent water supply management method based on wind, solar, and water multi-source data fusion, applied to an intelligent water supply management system based on wind, solar, and water multi-source data fusion as claimed in any one of claims 1 to 9, characterized in that: The following steps are involved: After multi-source data collection, a time alignment deviation quantification result is obtained based on the acquired multi-source data time parameters to reflect the time alignment deviation degree of multi-source data processing caused by the timestamp difference of multi-source data collection. The multi-source data collection means collecting wind, solar and water multi-source data through a specified data collection method to generate a predictive water supply instruction to realize water supply management; Determine whether to perform time alignment control based on the quantified result of the time alignment deviation. If so, obtain the timeliness response parameter after performing the time alignment control to reflect the response time of executing the predicted water supply demand instruction based on the multi-source data fusion result. Otherwise, directly obtain the timeliness response parameter. The time alignment control includes average delay control and response time control. According to the acquired timeliness response parameters, the quantitative results of the data fusion timeliness response are obtained to quantify the timeliness from the completion of multi-source data fusion to the reception and response of the predicted water supply demand instruction; Based on the quantitative results of the data fusion timeliness response, it is determined whether to perform PLC scanning interval control and monitoring verification. If so, the water supply management operation corresponding to the predicted water supply demand instruction is executed after performing PLC scanning interval control and monitoring verification. Otherwise, the water supply management operation is executed directly.

Images