Mountain area water supply method, device and system based on intelligent module electricity meter

Abstract

The invention discloses a mountainous area water supply method, device and system based on intelligent module ammeters. The method comprises the steps that reservoir water level data, meteorological change data and water pump operation data are collected; predicting a predicted water supply demand in a first time period according to the reservoir water level data and the meteorological change data; according to the predicted water supply demand, inputting water pump operation data into a preset power-flow model to obtain a water pump power adjusting range meeting the predicted water supply demand; according to the predicted water supply demand and the water pump power adjusting range, a preset water supply scheduling control model is adjusted, and an optimal water supply scheduling strategy is obtained; according to the optimal water supply scheduling strategy, the output power of a water pump motor is adjusted through an intelligent module electricity meter. According to the water supply scheduling strategy generated according to the predicted future water demand, the output power of the water pump motor is adjusted, and continuity and high efficiency of water supply are guaranteed.

Description

Technical Field

[0001] The present application belongs to the technical field of integrated water management, and specifically relates to a method and system for water supply in mountainous areas based on smart module electric meters. Background Art

[0002] Some remote villages are difficult to access to the tap water system, and usually use local water resources for water supply. To achieve automatic water supply, the commonly used method is to build a water tank at a high place in the village and a water intake pool at the gathering point of the village water source. When taking water, you need to go to the water source to start the water pump to fill the water tank. When using water, judge the condition of the water tank according to the water pressure. When the water tank is about to run out, you need to switch to another water tank with water, or go to the water source to start pumping.

[0003] The water tank and the water intake pool obtain water level information through manual visual methods. When taking water, it is necessary to open the water tank for a long time to observe the water level, and observe back and forth between the water tank and the water intake pool to ensure the water level. This water supply method is extremely cumbersome and requires the participation of more people. The pumping process requires people to be on duty, and the start and stop of the pumping pump requires people to control it. The comprehensive pumping cost is high. In addition, diesel pumps are used for pumping. The water source is small and unstable, and the pumping efficiency is low. In addition, the roads in the mountainous environment are complex and inconvenient. Most of the pumping points are in valleys and cannot be reached by vehicles. Rainy weather makes the mountain roads slippery, and there are safety hazards when going to pump water manually. Summary of the invention

[0004] The present application proposes a method, device and system for mountain water supply based on a smart module electric meter, which generates a water supply scheduling strategy based on predicted future water demand, adjusts the output power of the water pump motor, and ensures the continuity and efficiency of water supply.

[0005] The first aspect of the present application provides a water supply method in a mountainous area based on a smart module electric meter, the method comprising:

[0006] Collect reservoir water level data, meteorological change data and water pump operation data through smart module meters;

[0007] Predicting the water supply demand in a first time period based on the water level data of the reservoir and the meteorological change data;

[0008] According to the predicted water supply demand, the water pump operation data is input into a preset power-flow model to obtain a water pump power adjustment range that meets the predicted water supply demand;

[0009] According to the predicted water supply demand and the water pump power adjustment range, the preset water supply scheduling control model is adjusted to obtain the optimal water supply scheduling strategy;

[0010] According to the optimal water supply scheduling strategy, the output power of the pump motor is adjusted by the intelligent module electric meter.

[0011] The above solution first studies the relationship between water level changes and weather conditions through a water consumption prediction model based on the reservoir water level data and meteorological change data, and realizes accurate prediction of future water consumption through weather changes to obtain the predicted water supply demand in the first time period. Then, according to the predicted water supply demand, the change relationship between the water level, water flow and output power of the pump motor in the reservoir is studied through a power-flow model to obtain the output power range corresponding to the water flow that can meet the predicted water supply demand in the first time period, providing data support for subsequent adjustment of the operation of the pump motor. Then, based on the predicted water supply demand and the pump power adjustment range, more attention is given to the key points of water supply operation through a water supply scheduling control model, so that the generated optimal water supply scheduling strategy can not only meet the predicted water supply demand, but also achieve the key points of water supply operation, such as reducing waste of water resources or saving electricity consumption, etc., to ensure the continuity and efficiency of water supply.

[0012] In a possible implementation method of the first aspect, predicting the water supply demand in the first time period according to the reservoir water level data and meteorological change data specifically includes:

[0013] Selecting several water consumption-related features from the reservoir water level data, meteorological change data and historical water consumption data by the Pearson correlation coefficient method;

[0014] Inputting the water consumption-related features into a preset water consumption prediction model, and predicting the predicted water supply demand in the first time period based on the preset typical water consumption periods;

[0015] Wherein, the typical water consumption periods include peak water consumption periods, low valley water consumption periods and emergency water consumption periods.

[0016] The above solution first identifies the key features required by the water consumption prediction model through the Pearson correlation coefficient method to ensure that the feature variables input into the model are highly correlated with the actual water consumption demand, thereby improving the prediction accuracy of the model. Then, based on the water consumption-related features, the predicted water supply demand in the first time period is predicted based on the set typical water consumption periods to determine whether the future water consumption period belongs to peak, low valley or emergency events, providing data support for subsequent adjustment of the output power of the pump motor.

[0017] In a possible implementation method of the first aspect, inputting the water consumption-related features into the water consumption prediction model and predicting the predicted water supply demand in the first time period from the preset typical water consumption periods specifically includes:

[0018] Constructing a first change relationship among historical water consumption, ambient temperature and water level according to the water consumption-related features;

[0019] Determine the predicted water consumption within the first time period according to the first variation relationship;

[0020] Obtain the predicted water supply demand from the typical water usage time periods according to the predicted water consumption within the first time period.

[0021] The above solution constructs the first variation relationship based on water usage-related characteristics and historical water consumption, which is used to predict the change in water consumption caused by weather changes within the first time period, and obtain the accurate predicted water consumption within the first time period. Then, according to the magnitude of the predicted water consumption, the corresponding water usage demand is determined from the preset typical water usage time periods, and the accurate predicted water supply demand is obtained.

[0022] In a possible implementation method of the first aspect, input the pump operation data into a preset power-flow model according to the predicted water supply demand to obtain the pump power adjustment range that meets the predicted water supply demand, specifically:

[0023] Determine the water flow rate within the first time period according to the predicted water supply demand;

[0024] Input the water flow rate and pump operation data into a preset power-flow model, and combine the bottom area of the reservoir and historical water level data to calculate the pump power adjustment range that meets the water flow rate within the first time period.

[0025] In a possible implementation method of the first aspect, combine the bottom area of the reservoir and historical water level data to obtain the pump power adjustment range that meets the water flow rate within the first time period, specifically:

[0026] Combine the bottom area of the reservoir and historical water level data to determine the water flow velocity at different output powers of the pump motor, and construct a second variation relationship between the water flow rate and the output power of the pump motor based on the water flow velocity;

[0027] Determine the pump power adjustment range that meets the water flow rate within the first time period according to the second variation relationship.

[0028] The above solution constructs a second variation relationship between the output power of the pump motor and the water flow rate through the historical water level change of the reservoir and the bottom area of the reservoir. Then, according to the water flow rate corresponding to the predicted water supply demand, the pump power adjustment range required for the predicted water supply demand within the first time period can be determined, which can ensure that the pump motor adjusts its power within the pump power adjustment range within the first time period, and the water volume that meets the predicted water supply demand can be obtained in the reservoir without water supply shortage, realizing the continuity of water supply.

[0029] In a possible implementation method of the first aspect, according to the predicted water supply demand and the water pump power adjustment range, the preset water supply scheduling control model is adjusted to obtain an optimal water supply scheduling strategy. Specifically:

[0030] According to the predicted water supply demand and the water pump power adjustment range, determine the water supply optimization target;

[0031] Adjust the index weights in the water supply scheduling control model according to the water supply optimization target to generate an optimal water supply scheduling strategy.

[0032] In the above solution, the predicted water supply demand includes not only the required water supply volume but also the operation requirements to be met during the water supply process, such as saving water resources, electrical energy resources, and supplying water more quickly. Therefore, it is also necessary to determine the water supply optimization target to achieve these additional requirements. Adjust the corresponding index weights according to the water supply optimization target, assign more weight values to the index weights corresponding to the water supply optimization target, and thus obtain an optimal water supply scheduling strategy that meets the water supply optimization target. The water supply system can have good performance under different operating conditions to adapt to different operating environments and requirements.

[0033] In a possible implementation method of the first aspect, adjust the index weights in the water supply scheduling control model according to the water supply optimization target. Specifically:

[0034] Integrate the preset water supply evaluation indexes through the corresponding index weights to construct the water supply scheduling control model;

[0035] According to the water supply optimization target, determine the importance of each water supply evaluation index;

[0036] According to the importance, numerically adjust the index weights of the water supply scheduling control model to generate an optimal water supply scheduling strategy that meets the water supply optimization target;

[0037] Among them, the water supply evaluation indexes include: water level safety, water use satisfaction rate, number of water supply interruptions, energy consumption per unit water volume, electrical energy efficiency ratio, continuous operation time of the water pump, pressure fluctuation range, user satisfaction index, emergency water use response time, and recovery time after emergency water use.

[0038] In a possible implementation method of the first aspect, integrate the preset water supply evaluation indexes through the corresponding index weights to construct the water supply scheduling control model. Specifically:

[0039] The water supply scheduling control model, the specific expression is:

[0040]

[0041] In the formula, CPI is the water supply scheduling control model, WS is the water level safety, SR is the water use satisfaction rate, EUE is the energy consumption per unit of water volume, and EUE max is the maximum value of the energy consumption per unit of water volume, PF is the pressure fluctuation range, and PF max is the maximum value of the pressure fluctuation range, USI is the user satisfaction index, RT is the emergency water use response time, and RT max is the maximum value of the emergency water use response time, RRT is the recovery time after emergency water use, and RRT max is the maximum value of the recovery time after emergency water use, and w1, w2, w3, w4, w5, w6, w7 are the index weights.

[0042] The second aspect of the present application provides a mountain water supply device based on an intelligent module electric meter, and the device includes: a data acquisition module, a demand prediction module, a power adjustment range module, a water supply scheduling strategy generation module, and a water pump power adjustment module;

[0043] Among them, the data acquisition module is used to collect the water storage tank water level data, meteorological change data, and water pump operation data through the intelligent module electric meter;

[0044] The demand prediction module is used to predict the predicted water supply demand within the first time period according to the water storage tank water level data and meteorological change data;

[0045] The power adjustment range module is used to input the water pump operation data into a preset power - flow model according to the predicted water supply demand to obtain the water pump power adjustment range that meets the predicted water supply demand;

[0046] The water supply scheduling strategy generation module is used to adjust a preset water supply scheduling control model according to the predicted water supply demand and the water pump power adjustment range to obtain an optimal water supply scheduling strategy;

[0047] The water pump power adjustment module is used to adjust the output power of the water pump motor through the intelligent module electric meter according to the optimal water supply scheduling strategy.

[0048] The third aspect of the present application provides a mountain water supply system based on an intelligent module electric meter, and the system includes: a mountain water supply device based on an intelligent module electric meter and an intelligent module electric meter;

[0049] Among them, the mountain water supply device based on the intelligent module electric meter is used to implement the mountain water supply method based on the intelligent module electric meter described in any one of the embodiments of the present application;

[0050] The intelligent module electric meter is used to collect the water storage tank water level data, meteorological change data, and water pump operation data, and transmit the data to the mountain water supply device based on the intelligent module electric meter. Description of the Drawings

[0051] To more clearly illustrate the technical solutions of this application, the accompanying drawings required for the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0052] Figure 1 is a specific flowchart showing a mountain water supply method based on an intelligent module electric meter provided by an embodiment of this application;

[0053] Figure 2 is a design diagram of an intelligent module electric meter for a mountain water supply method based on an intelligent module electric meter provided by an embodiment of this application;

[0054] Figure 3 is a communication flowchart of a mountain water supply method based on an intelligent module electric meter provided by an embodiment of this application;

[0055] Figure 4 is an implementation flowchart of a mountain water supply method based on an intelligent module electric meter provided by an embodiment of this application;

[0056] Figure 5 is a specific structural diagram of a mountain water supply device based on an intelligent module electric meter provided by an embodiment of this application;

[0057] Figure 6 is a specific structural diagram of a mountain water supply system based on an intelligent module electric meter provided by an embodiment of this application. Specific Embodiments

[0058] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only some, rather than all, of the embodiments of this application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of this application without creative efforts fall within the scope of protection of this application.

[0059] It should be understood that the step numbers used in the text are only for convenience of description and are not intended to limit the order of execution of the steps.

[0060] First Embodiment

[0061] To solve the problem of difficult automatic water supply in remote villages, the embodiment of this application uses a new generation of intelligent module meters to expand water services. Water level data of the water storage tank and the water intake pool are obtained through a wireless water level meter, and the water level data is analyzed. At the same time, the water tank water level information is also monitored in real time to achieve the allocation of water resources without manual visual inspection. In addition, a model for predicting the water level of the reservoir is established to reasonably plan the water use of the village, make a deployment plan for pumping water, and improve the efficiency of water resource allocation.

[0062] As Figure 1 shown, Figure 1 FIG. is a schematic flow chart of a mountainous area water supply method based on an intelligent module meter provided by an embodiment of this application. The mountainous area water supply method based on an intelligent module meter in this embodiment includes steps S1 to S5, which are described in detail as follows:

[0063] Step S1, collect the water level data of the reservoir, meteorological change data, and pump operation data through the intelligent module meter.

[0064] In the embodiment of this application, the realization of data collection mainly depends on a new generation of intelligent module meters. The intelligent module meter includes a water level meter, a 4G communication device, an electric water pump control device, and a water service sensing input module. Among them, the water level meters are respectively deployed at the reservoir and the water intake pool. The water level meter at the reservoir is connected to the 4G communication module, and a solar power supply device is deployed to provide electrical energy. There is already electrical energy supply at the water intake pool, and the water level meter and the electric water pump control device are connected to the water service sensing access module. Among them, the water service sensing access module is mainly used to collect the water level data of the water level meter and transmit control signals to the electric water pump control device to realize the functions of accessing water service data into the metering system and comprehensively determining the working conditions of the water pump.

[0065] The intelligent module meter is designed to meet the R46 standard of the International Organization of Legal Metrology, adopts the separation method of the management unit and the legal metrology unit, and can realize the up and down transmission of data through the communication unit. There are various methods for separating the management unit and the legal metrology unit, which can mainly be separated from two directions. One is through the physical layer separation method, and the other is to realize the separation of the management unit and the metrology unit through modular design.

[0066] Furthermore, the overall design idea of the intelligent module meter is to independently design the management part (management MCU) and the metering part (metering SoC) of the meter. An isolation area is divided in the intelligent module meter, and the metering function is realized through an independent metering core (metering SoC), and the remaining management-related extended functions are handed over to the management core to realize management and information interaction.

[0067] To better display the architecture of the intelligent module meter, Figure 2The design diagram of the intelligent module electric meter is provided. As shown in the figure, the design structure of the intelligent module electric meter is mainly divided into three major parts: the system power supply part, the management part, and the metering part. The metering part, as the basic meter part of the intelligent module electric meter, mainly undertakes tasks such as voltage and current analog quantity information acquisition, AD data processing (including harmonics), and electric energy metering task processing.

[0068] As an improvement to the above solution, in the embodiment of the present application, a downlink module is newly added to the intelligent module electric meter to realize remote reading of multi-meter data, quickly and accurately collect the user's water consumption, and greatly improve the efficiency and accuracy of meter reading.

[0069] It can be seen from Figure 3 that the intelligent module electric meter transmits the collected water service data to the cloud master station. The cloud master station provides a water service data monitoring platform. The monitoring platform displays the water service data sent by the electric meter in real time and can respond according to the water service warning information. At the same time, the monitoring platform can directly send control instructions to the electric meter, and the electric meter then controls the electric water pump control device through the water service sensing access module. In the embodiment of the present application, mainly through the model constructed by the cloud master station, the future water consumption is predicted and the corresponding optimal water supply scheduling strategy is formulated.

[0070] Among them, the water service data includes the collected water level data of the water storage tank and the water intake pool, water pump operation data, pipeline flow, meteorological change data, etc. These data are uploaded to the cloud master station in real time through the 4G communication module for operation and maintenance personnel to supervise and analyze.

[0071] Step S2, according to the water storage tank water level data and meteorological change data, predict the predicted water supply demand within the first time period.

[0072] In the embodiment of the present application, based on the constructed water consumption prediction model, through the water storage tank water level data and meteorological change data, the water consumption in different time periods of a day is estimated, the water consumption demands in the peak period and the trough period are identified, and the fluctuation of the water consumption is accurately predicted.

[0073] Specifically, first, through the collected water storage tank water level data, meteorological change data (such as ambient temperature and weather conditions, etc.) and historical water consumption data, the Pearson correlation coefficient method is used to select several core features highly correlated with the water consumption as inputs, denoted as water consumption-related features, including: water level, water consumption history record, and air temperature. By selecting water consumption-related features, it can be ensured that the input feature variables are highly correlated with the actual water consumption demand, thereby improving the prediction accuracy of the model.

[0074] Among them, for the collected data, first perform cleaning and preprocessing, such as filling in missing values through interpolation method, removing outliers, and then inputting it into the model.

[0075] Exemplarily, in the embodiments of the present application, an LSTM model based on multiple spatial dimensions is used to construct a water consumption prediction model.

[0076] Among them, the specific expression of the Pearson correlation coefficient method is:

[0077]

[0078] In the formula, x i and y i are respectively the data values of a certain variable X and a certain variable Y in the i-th sample. and are respectively the average values of X and Y, and n is the total number of samples. r is the Pearson correlation coefficient, which is used to compare the correlation between features, and its value range is [-1, 1][-1, 1]; when r is 1, it indicates a perfect positive correlation, when r is -1, it indicates a perfect negative correlation, and when r is 0, it indicates no correlation.

[0079] Then, the water consumption-related features in different time dimensions and spatial dimensions are jointly input into the water consumption prediction model, enabling the model to simultaneously learn the dependencies in the time series and the interaction of spatial information. It can not only capture the time changes during peak and trough water consumption periods, but also combine environmental factors such as weather to optimize the water demand prediction of the entire water supply system. In order to improve the prediction accuracy of the water consumption prediction model, the embodiments of the present application also introduce a multi-dimensional feature fusion method to fuse the water consumption-related features, realizing not only considering the features in the time series, but also introducing the data in the spatial dimension.

[0080] Among them, the multi-dimensional feature fusion method is specifically as follows:

[0081] Assume that the input data dimension is: X = [x1, x2,..., x n ;

[0082] In the formula, each x i is the data of a spatial dimension. By fusing these multi-dimensional features, the input data X t of the LSTM model is obtained:

[0083]

[0084] Based on the above multi-dimensional feature fusion method, the obtained water consumption prediction model enables more refined allocation of water demand.

[0085] As an improvement to the above solution, a Temporal Convolutional Network (TCN) is also introduced in the embodiments of the present application. By combining the TCN with the LSTM model to construct a water consumption prediction model, the water supply system can predict water volume changes from both the temporal and spatial dimensions and formulate refined water supply plans. The model captures the global temporal relationships in the water supply system through the temporal convolutional network and further improves the model's perception ability of water volume demand changes by combining data from multiple spatial dimensions. The basic idea of the temporal convolutional network is to extract local features h in the time series through one-dimensional convolutional operations t . Its core formula is:

[0086]

[0087] In the formula, w i is the weight of the convolutional kernel, and x t-i is the input feature at time t - i.

[0088] Through the TCN, convolutional operations can be performed on the input at each time step, thereby generating features with more global information. This process ensures that the model only relies on past information through causal convolution, which is suitable for the scenario of water volume prediction.

[0089] To ensure the robustness of the model in long-term prediction, the embodiments of the present application also introduce a fusion method for residual sequences to further enhance the performance of the water consumption prediction model. A mechanism for fusing residuals is adopted in the model. The prediction accuracy of the model is improved through the residual sequence. By comparing the deviation between the historical data and the current model prediction value, the residuals are corrected through models such as GRU, and the corrected data is fed back to the original model. This can effectively improve the stability of the model, avoid overfitting problems, and ensure that the model can still maintain high-precision prediction ability in the case of less data or more noise. Residual connections are also added between different layers of the network to alleviate the problems of vanishing gradients and exploding gradients in model prediction.

[0090] Among them, the specific expression of the residual connection is:

[0091] h out = h in + F(h in );

[0092] In the formula, h in is the input feature, F is a certain non-linear transformation, and h out is the output feature.

[0093] In addition, an attention mechanism is also introduced in the water consumption prediction model, which can dynamically adjust the attention of the model to different input features. The formula of the attention mechanism is:

[0094]

[0095] where, e t is the score of the input feature at time step t, and α t is the normalized attention weight, and e k is the feature score at time step t.

[0096] The introduction of the attention mechanism can help the model pay more attention to key time points and important features when predicting water consumption, thereby improving the interpretability and prediction accuracy of the model.

[0097] The water consumption prediction model constructed based on the above method can statistically analyze the water consumption in different periods of a day in the time dimension. The model can identify the water consumption demands during peak and trough periods, and accurately predict the fluctuations in water consumption. It can also conduct climate change predictions, comprehensively considering the changes in climate and seasons, and predict the impact of climate on water consumption demands and the maximum available water volume. Additionally, for specific events such as sudden increases in water consumption during holidays or special activities, it can predict in advance through the analysis of historical data and adjust the water supply plan.

[0098] After inputting the water-related features after input fusion, they are processed in the form of a time series through the water consumption prediction model. According to the forward and backward dependence information of the time series, the model understands the change rules of water consumption at different time points, captures the global dependence relationship in the long time series through TCN, extracts features from the time series, ensures that the data at each time point can be associated with multiple past time steps, further enhances the model's understanding of complex water use behaviors, and constructs the first change relationship among historical water consumption, environmental temperature, and water level.

[0099] Determine the predicted water consumption within the first time period according to the first change relationship. Then, according to the predicted water consumption within the first time period, obtain the predicted water supply demand from the typical water use periods. Among them, the typical water use periods include peak water use periods, trough water use periods, and emergency water use periods.

[0100] Exemplarily, the peak water use period can be set from 6 to 9 in the morning and from 6 to 9 in the evening. During this period, the water consumption is large, and it is necessary to continuously monitor the water level and water consumption to make the water level in the reservoir reach the peak required level. The trough water use period can be set from 12 o'clock at night to 5 o'clock in the early morning. During this time period, the water consumption is small, and it is only necessary to ensure that the water level in the water storage tank is not lower than the minimum reserve level to cope with sudden demands. The emergency water use periods include holidays and extreme weather, etc., and it is necessary to monitor the data in real time, detect sudden water use demands, and ensure the continuity of water supply.

[0101] Step S3, input the pump operation data into a preset power-flow model according to the predicted water supply demand, and obtain the pump power adjustment range that meets the predicted water supply demand.

[0102] In the embodiment of the present application, first, the water flow rate within the first time period is determined according to the obtained predicted water supply demand.

[0103] The water flow rate and the pump operation data are input into a preset power-flow model, and a second variation relationship between the water flow rate and the output power of the pump motor constructed by the power-flow model is used to obtain the pump power adjustment range that meets the water flow rate within the first time period.

[0104] Specifically, according to the water level rising speed measured by the water level gauge, the actual water flow rate can be calculated. Assuming that the water level rises by h meters within 5 minutes and the bottom area of the reservoir is S square meters, the actual water flow rate Q can be expressed as:

[0105]

[0106] The pump motor is used to drive the pump to transport water from the water intake pool to the reservoir. The relationship between power and flow rate can be expressed by the following formula:

[0107]

[0108] In the formula, P is the output power of the pump motor, ρ is the density of water, g is the acceleration due to gravity, H is the pump head, that is, the height difference between the water intake pool and the reservoir, and η is the efficiency of the pump.

[0109] Based on the above formula, according to the water level change data and the output power of the pump motor, the power of the motor is adjusted in real time by the pump control device to determine the water flow velocity at different powers. Specifically: starting from the minimum output power, the output power of the motor is gradually increased at preset time intervals. When the cumulative time is greater than the set adjustment period, the pump control device is controlled to increase the output power, and the current flow rate is measured again by the water level gauge, and then this process continues. As the output power increases, the water flow rate data at different powers are recorded successively. When the output power reaches the highest preset power, a complete power-flow data set is obtained. According to this data set and the above formula, the power-flow model constructs a second variation relationship between the water flow rate and the output power of the pump motor, and further obtains the pump power adjustment range that meets the water flow rate within the first time period.

[0110] Since the pump working conditions may change at any time during the actual operation process, it is necessary to update the power-flow model regularly. The model update process is mainly adjusted in real time through the communication status between the reservoir and the pump, and the power-flow model is updated according to the real-time measured data. However, when the communication between the reservoir and the pump is interrupted, the pump control device will enter the theoretical calculation mode and perform theoretical updates based on the previously recorded power-flow model.

[0111] Step S4: Adjust the preset water supply scheduling control model according to the predicted water supply demand and the adjustable range of the water pump power to obtain the optimal water supply scheduling strategy.

[0112] In an embodiment of the present application, a water supply scheduling control model is provided, which is obtained by standardizing and weighting preset water supply evaluation indicators. It can integrate multiple key indicators for evaluating the performance of the water supply system into a comprehensive scoring indicator and use this comprehensive scoring indicator to evaluate the overall performance of the water supply system.

[0113] Exemplarily, in an embodiment of the present application, the water supply evaluation indicators include: water level safety, water use satisfaction rate, number of water supply interruptions, energy consumption per unit of water volume, electrical energy efficiency ratio, continuous operation time of the water pump, pressure fluctuation range, user satisfaction index, emergency water use response time, and recovery time after emergency water use.

[0114] Among them, the water level safety WS is specifically:

[0115]

[0116] In the formula, L is the current water level, L min and L max are the lowest water level and the highest water level respectively.

[0117] The water use satisfaction rate SR is specifically:

[0118]

[0119] In the formula, T met is the time when the water supply system meets the water use demand, and T total is the total peak time.

[0120] The number of water supply interruptions is the total number of water supply interruptions occurring within a certain period of time.

[0121] The energy consumption per unit of water volume EUE is specifically:

[0122]

[0123] In the formula, E total is the total electrical energy consumption, with the unit of kWh; V total is the total water supply volume.

[0124] The electrical energy efficiency ratio COP is specifically:

[0125]

[0126] In the formula, W output is the output water flow work, and E input is the input electrical energy.

[0127] The continuous operation time of the water pump is the time when the water pump operates continuously, ensuring that it does not exceed the set maximum continuous operation time.

[0128] The pressure fluctuation range PF is specifically:

[0129] PF = P max - P min ;

[0130] In the formula, P max , P min are the maximum pressure and the minimum pressure recorded within a certain time period, respectively.

[0131] The user satisfaction index USI is specifically:

[0132]

[0133] In the formula, S positive is the number of positive feedbacks, and S total is the total number of feedbacks.

[0134] The emergency water use response time RT is specifically:

[0135] RT = t action - t detection ;

[0136] In the formula, t action is the time to take action, and t detection is the time when the emergency water use is detected.

[0137] The recovery time RRT after the emergency water use is specifically:

[0138] RRT = t normal - t cnd ;

[0139] In the formula, t normal is the time when the water supply system resumes normal operation, and t cnd is the time when the emergency event ends.

[0140] By standardizing and assigning weights to the above water supply evaluation indicators, the water supply scheduling control model is constructed, and the specific expression is:

[0141]

[0142] In the formula, CPI is the water supply scheduling control model, WS is the water level security, which is a binary indicator with a value of 0 or 1; SR is the water use satisfaction rate, EUE is the energy consumption per unit of water volume, and EUE maxis the maximum value of the energy consumption per unit of water volume, PF is the pressure fluctuation range, and PF max is the maximum value of the pressure fluctuation range, USI is the user satisfaction index, RT is the emergency water supply response time, and RT max is the maximum value of the emergency water supply response time, RRT is the recovery time after emergency water use, and RRT max is the maximum value of the recovery time after emergency water use, and w1, w2, w3, w4, w5, w6, w7 are the weights of the above indicators. Some of the indicators in the above formula are standardized by dividing by the maximum value.

[0143] Among them, CPI is actually an indicator for evaluating the overall performance of the water supply system by the water supply scheduling control model. The closer the value of CPI is to 1, the better the overall performance of the system.

[0144] In the embodiments of the present application, according to the predicted water supply demand and the pump power adjustment range, a water supply optimization target is determined.

[0145] Optionally, the water supply optimization target may be to save water resources, save electric energy during the water supply process, or improve the water supply efficiency.

[0146] According to the water supply optimization target, the importance of each water supply evaluation indicator is determined. Then, based on the importance, the weights of the indicators in the water supply scheduling control model are numerically adjusted, and the weights corresponding to the indicators that the water supply optimization target needs to meet are increased to generate an optimal water supply scheduling strategy that meets the water supply optimization target.

[0147] Step S5, according to the optimal water supply scheduling strategy, adjust the output power of the pump motor through the intelligent module electric meter.

[0148] Exemplarily, if the optimal water supply scheduling strategy is used during the peak period, the output power of the pump motor is gradually increased in the first hour of the first time period to make the water level in the reservoir reach the level required during the peak period. The system continuously monitors the water level and water consumption during the peak period. If the actual water consumption is higher than the predicted value and the water level is close to the lowest safety threshold, the system will automatically further increase the output power. After the peak period ends, the output power is gradually restored to the normal level to ensure that the water level in the reservoir is within the safe range while optimizing the energy consumption efficiency.

[0149] If the optimal water supply scheduling strategy is used during the off-peak period, at the beginning of the off-peak period, the output power is gradually reduced to the lowest safety level to reduce energy consumption, while ensuring that the water level in the reservoir is not lower than the lowest reserve level to cope with sudden demands. One hour before the end of the off-peak period, the output power is gradually restored to prepare for possible increased water use demands.

[0150] If the optimal water supply scheduling strategy is used for emergencies, in order to ensure the continuity of water supply, monitor the data as needed, detect sudden water demands, and immediately increase the output power to maintain water supply when the demand surges. After the event, analyze the water supply data, evaluate the effectiveness of the emergency strategy, and adjust the plan.

[0151] Furthermore, the water level, water consumption, and pump status data can be displayed in real time on the cloud platform. The water supply system sets alarm thresholds, and when the water level is too low or the communication is interrupted, an alarm is automatically sent to the operation and maintenance personnel.

[0152] Figure 4 The implementation flowchart of the embodiment of the present application is provided. As shown in the figure, first determine the locations of the reservoir and the intake pool, evaluate the power supply and signal coverage at these two places, and prepare all necessary tools and equipment. Then install an intelligent module electric meter at the intake pool and connect it to the power supply. Install a water level gauge at the intake pool and connect it to the water service sensing access module. Install an electric water pump control device near the intake pool and connect it to the water service sensing access module. Install a solar power supply device at the water storage tank, connect the solar panel to the battery, the water level gauge, and the 4G communication module. Install a water service sensing access module on the electric meter and connect it to the electric water pump control device. After the equipment installation is completed, conduct system joint debugging and testing, check the power supply and communication connections of all equipment, calibrate the water level gauge and the electric water pump, and test the data transmission function of the electric meter. Finally, conduct a preliminary operation test, start the system for operation testing, and start the prediction of water supply after the test is successful.

[0153] Implementing the embodiment of the present application has the following beneficial effects:

[0154] In the embodiment of the present application, first, according to the reservoir water level data and meteorological change data, study the relationship between the water level change and the weather state through the water consumption prediction model, and achieve accurate prediction of future water consumption through weather changes to obtain the predicted water supply demand within the first time period. Then, according to the predicted water supply demand, study the change relationship between the water level, water flow rate of the reservoir, and the output power of the water pump motor through the power-flow model to obtain the output power range corresponding to the water flow rate that can meet the predicted water supply demand within the first time period, providing data support for the subsequent adjustment of the operation of the water pump motor. Then, based on the predicted water supply demand and the water pump power adjustment range, give more attention to the key points of water supply operation through the water supply scheduling control model, so that the generated optimal water supply scheduling strategy can not only meet the predicted water supply demand, but also achieve the key points of water supply operation, such as reducing water resource waste or saving electricity consumption, etc., to ensure the continuity and efficiency of water supply.

[0155] Second Embodiment

[0156] Furthermore, in order to implement the mountain water supply device based on the smart module electric meter corresponding to the above method embodiment to achieve the corresponding functions and technical effects, Figure 5 A structural diagram of a mountain water supply device based on a smart module electric meter is provided. For ease of description, only the parts related to this embodiment are shown. The mountain water supply device based on a smart module electric meter provided in the embodiment of the present application includes:

[0157] The data acquisition module 201 is used to collect reservoir water level data, meteorological change data and water pump operation data through the smart module electric meter.

[0158] In the embodiment of the present application, the realization of data collection mainly relies on a new generation of smart module electric meters, which include a water level meter, a 4G communication device, an electric water pump control device, and a water affairs sensor input module. The water level meter is deployed at the water reservoir and the water intake pool, respectively. The water level meter at the water reservoir is connected to the 4G communication module, and a solar power supply device is deployed to provide electricity. There is already electricity supply at the water intake pool, and the water level meter and the electric water pump control device are connected to the water affairs sensor access module. The water affairs sensor access module is mainly used to collect water level data from the water level meter and transmit control signals to the electric water pump control device, so as to realize the function of accessing water affairs data to the metering system and making comprehensive decisions on the working conditions of the water pump.

[0159] The design of the smart module meter meets the R46 standard of the International Measurement Organization, adopts a method of separating the management unit from the legal measurement unit, and can achieve data uplink and downlink transmission through the communication unit. There are many ways to separate the management unit from the legal measurement unit, which can be separated from two directions, one is through physical layer separation, and the other is to separate the management unit from the measurement unit through modular design.

[0160] Furthermore, the overall design idea of ​​the smart module meter is to independently design the management part (management MCU) and the metering part (metering SoC) of the meter, divide the isolation area in the smart module meter, implement the metering function through an independent metering core (metering SoC), and leave the remaining management-related extended functions to the management core to realize management and information interaction.

[0161] The demand prediction module 202 is used to predict the water supply demand in a first time period based on the water level data of the reservoir and the meteorological change data.

[0162] In the embodiment of the present application, several water use related features are selected from the water level data of the reservoir, the meteorological change data and the historical water use data by using the Pearson correlation coefficient method;

[0163] Input the water - related features into a preset water consumption prediction model, and predict the predicted water supply demand within a first time period based on the preset typical water - using periods;

[0164] Among them, the typical water - using periods include peak water - using periods, low - valley water - using periods, and emergency water - using periods.

[0165] The power adjustment range module 203 is configured to input the pump operation data into a preset power - flow model according to the predicted water supply demand, and obtain the pump power adjustment range that meets the predicted water supply demand.

[0166] In the embodiment of the present application, determine the water flow rate within the first time period according to the predicted water supply demand;

[0167] Input the water flow rate and pump operation data into a preset power - flow model, and combine the bottom area of the reservoir and historical water level data to calculate the pump power adjustment range that meets the water flow rate within the first time period.

[0168] The water supply scheduling strategy generation module 204 is configured to adjust a preset water supply scheduling control model according to the predicted water supply demand and the pump power adjustment range to obtain an optimal water supply scheduling strategy.

[0169] In the embodiment of the present application, determine the water supply optimization goal according to the predicted water supply demand and the pump power adjustment range;

[0170] Adjust the index weights in the water supply scheduling control model according to the water supply optimization goal to generate an optimal water supply scheduling strategy.

[0171] Specifically: Integrate the preset water supply evaluation indexes through the corresponding index weights to construct the water supply scheduling control model;

[0172] Determine the importance of each water supply evaluation index according to the water supply optimization goal;

[0173] Adjust the numerical values of the index weights in the water supply scheduling control model according to the importance to generate an optimal water supply scheduling strategy that meets the water supply optimization goal;

[0174] Among them, the water supply evaluation indexes include: water level safety, water - using satisfaction rate, number of water supply interruptions, energy consumption per unit of water, electric energy efficiency ratio, continuous operation time of the pump, pressure fluctuation range, user satisfaction index, emergency water - using response time, and recovery time after emergency water - using.

[0175] The pump power adjustment module 205 is configured to adjust the output power of the pump motor through an intelligent module electric meter according to the optimal water supply scheduling strategy.

[0176] In the embodiments of the present application, if the optimal water supply scheduling strategy is used during the peak period, the output power of the pump motor is gradually increased in the first hour of the first time period to make the water level in the reservoir reach the level required during the peak period. The system continuously monitors the water level and water consumption during the peak period. If the actual water consumption is higher than the predicted value and the water level is close to the lowest safety threshold, the system will automatically further increase the output power. After the peak period ends, the output power is gradually restored to the normal level to ensure that the water level in the reservoir is within the safe range while optimizing the energy consumption efficiency.

[0177] If the optimal water supply scheduling strategy is used during the low period, at the beginning of the low period, the output power is gradually reduced to the lowest safety level to reduce energy consumption, while ensuring that the water level in the reservoir is not lower than the lowest reserve level to cope with sudden demands. One hour before the end of the low period, the output power is gradually restored to prepare for possible increased water demand.

[0178] If the optimal water supply scheduling strategy is used for emergencies, to ensure the continuity of water supply, monitor the data when needed, detect sudden water demands, and immediately increase the output power to maintain water supply when the demand surges. After the event ends, analyze the water supply data, evaluate the effectiveness of the emergency strategy, and adjust the plan.

[0179] Furthermore, the water level, water consumption, and pump status data can be displayed in real time on the cloud platform. The water supply system sets alarm thresholds, and when the water level is too low or the communication is interrupted, an alarm is automatically sent to the operation and maintenance personnel.

[0180] In some embodiments, the demand prediction module 202 further includes:

[0181] Based on the constructed water consumption prediction model, estimate the water consumption in different time periods of a day through the water level data of the reservoir and meteorological change data, identify the water demands during the peak and low periods, and accurately predict the fluctuations in water consumption.

[0182] Specifically, first, through the collected water level data of the reservoir, meteorological change data (such as ambient temperature and weather conditions, etc.) and historical water consumption data, use the Pearson correlation coefficient method to select several core features highly correlated with water consumption as inputs, denoted as water consumption-related features, including: water level, water consumption history records, and temperature. By selecting water consumption-related features, it can be ensured that the input feature variables are highly correlated with the actual water demand, thereby improving the prediction accuracy of the model.

[0183] Among them, for the collected data, first perform cleaning and preprocessing, such as filling missing values by interpolation method, removing outliers, and then inputting them into the model.

[0184] Exemplarily, in the embodiments of the present application, an LSTM model based on multiple spatial dimensions is used to construct the water consumption prediction model.

[0185] Among them, the specific expression of the Pearson correlation coefficient method is as follows:

[0186]

[0187] In the formula, x i and y i are respectively the data values of a certain variable X and a certain variable Y in the i-th sample. and are respectively the average values of X and Y, and n is the total number of samples. r is the Pearson correlation coefficient, which is used to compare the correlation between features, and its value range is [-1, 1][-1, 1]; when r is 1, it represents a perfect positive correlation, when r is -1, it represents a perfect negative correlation, and when r is 0, it represents no correlation.

[0188] Then, the water use-related features in different time dimensions and space dimensions are jointly input into the water consumption prediction model, enabling the model to simultaneously learn the dependencies in the time series and the interactions of spatial information. It can not only capture the time variations during peak and trough water use periods, but also combine environmental factors such as weather to optimize the water demand prediction of the entire water supply system. To improve the prediction accuracy of the water consumption prediction model, the embodiments of this application also introduce a multi-dimensional feature fusion method to fuse the water use-related features, realizing not only considering the features in the time series, but also introducing the data in the spatial dimension.

[0189] Among them, the multi-dimensional feature fusion method is specifically as follows:

[0190] Assume that the dimension of the input data is: X = [x1, x2,..., x n ;

[0191] In the formula, each x i is the data of a spatial dimension. By fusing these multi-dimensional features, the input data X t for the LSTM model is obtained:

[0192]

[0193] Based on the above multi-dimensional feature fusion method, the obtained water consumption prediction model enables more refined allocation of water demand.

[0194] As an improvement to the above solution, a Temporal Convolutional Network (TCN) is also introduced in the embodiments of the present application. The TCN is combined with the LSTM model to construct a water consumption prediction model, enabling the water supply system to predict water volume changes from both temporal and spatial dimensions and formulate refined water supply plans. The model captures the global temporal relationships in the water supply system through the temporal convolutional network and further improves the model's perception ability of water volume demand changes by integrating data from multiple spatial dimensions. The basic idea of the temporal convolutional network is to extract local features h in the time series through one-dimensional convolutional operations t . Its core formula is:

[0195]

[0196] In the formula, w i is the weight of the convolutional kernel, and x t-i is the input feature at time t - i

[0197] Through the TCN, convolutional operations can be performed on the input at each time step, thereby generating features with more global information. This process ensures that the model only relies on past information through causal convolution, which is suitable for the scenario of water volume prediction

[0198] To ensure the robustness of the model in long-term prediction, the embodiments of the present application also introduce a fusion method for residual sequences to further enhance the performance of the water consumption prediction model. A mechanism for fusing residuals is adopted in the model to improve the prediction accuracy of the model through residual sequences. By comparing the deviation between historical data and the current model prediction value, the residuals are corrected through models such as GRU, and the corrected data is fed back to the original model. This can effectively improve the stability of the model, avoid overfitting problems, and ensure that the model can still maintain high-precision prediction ability in the case of less data or more noise. Residual connections are also added between different layers of the network to alleviate the problems of gradient disappearance and gradient explosion in model prediction

[0199] Among them, the specific expression of the residual connection is:

[0200] h out = h in + F(h in );

[0201] In the formula, h in is the input feature, F is a certain non-linear transformation, and h out is the output feature

[0202] In addition, an attention mechanism is also introduced in the water consumption prediction model, which can dynamically adjust the attention of the model to different input features. The formula of the attention mechanism is:

[0203]

[0204] In the formula, e t is the score of the input feature at time step t, and α t is the normalized attention weight, and e k is the feature score at time step t.

[0205] The introduction of the attention mechanism can help the model pay more attention to key time points and important features when predicting water consumption, thereby improving the interpretability and prediction accuracy of the model.

[0206] The water consumption prediction model constructed based on the above method can statistically analyze the water consumption situation at different times of the day in the time dimension. The model can identify the water consumption demands during peak and trough periods and accurately predict the fluctuations in water consumption. It can also conduct climate change predictions, comprehensively considering the changes in climate and seasons, and predict the impact of climate on water consumption demands and the maximum available water volume. Additionally, for specific events such as sudden increases in water consumption during holidays or special activities, it can predict in advance through the analysis of historical data and adjust the water supply plan.

[0207] After inputting the water-related features after fusion, they are processed in the form of a time series through the water consumption prediction model. Based on the forward and backward dependency information of the time series, the model understands the variation law of water consumption at different time points, captures the global dependencies in the long time series through TCN, extracts features from the time series, ensures that the data at each time point can be associated with multiple past time steps, further enhances the model's understanding of complex water consumption behaviors, and constructs the first variation relationship among historical water consumption, environmental temperature, and water level.

[0208] Determine the predicted water consumption within the first time period according to the first variation relationship. Then, based on the predicted water consumption within the first time period, obtain the predicted water supply demand from the typical water consumption periods. Among them, the typical water consumption periods include peak water consumption periods, trough water consumption periods, and emergency water consumption periods.

[0209] Exemplarily, the peak water consumption period can be set from 6 to 9 in the morning and from 6 to 9 in the evening. During this period, the water consumption is large, and it is necessary to continuously monitor the water level and water consumption to make the water level in the reservoir reach the peak level. The trough water consumption period can be set from 12 o'clock at night to 5 o'clock in the early morning. During this time period, the water consumption is small, and it is only necessary to ensure that the water level in the water storage tank is not lower than the minimum reserve level to cope with sudden demands. The emergency water consumption period includes holidays and extreme weather, etc., and it is necessary to monitor the data in real time, detect sudden water consumption demands, and ensure the continuity of water supply.

[0210] In some embodiments, the power adjustment range module 203 further includes:

[0211] First, determine the water flow rate within the first time period according to the obtained predicted water supply demand.

[0212] Input the water flow rate and the water pump operation data into a preset power-flow model, and obtain the pump power adjustment range that meets the water flow rate within the first time period through the second variation relationship between the water flow rate and the output power of the water pump motor constructed by the power-flow model.

[0213] Specifically, according to the water level rising speed measured by the water level gauge, the actual water flow rate can be calculated. Assume that the water level has risen by h meters within 5 minutes, and the bottom area of the reservoir is S square meters, then the actual water flow rate Q can be expressed as:

[0214]

[0215] The water pump motor is used to drive the water pump to transport water from the water intake pool to the reservoir. The relationship between power and flow rate can be expressed by the following formula:

[0216]

[0217] In the formula, P is the output power of the water pump motor, ρ is the density of water, g is the acceleration due to gravity, H is the head of the water pump, that is, the height difference from the water intake pool to the reservoir, and η is the efficiency of the water pump.

[0218] Based on the above formula, according to the water level change data and the output power of the water pump motor, the power of the motor is adjusted in real time through the water pump control device to determine the water flow velocity at different powers. Specifically: starting from the minimum output power, the output power of the motor is gradually increased at preset time intervals. When the cumulative time is greater than the set adjustment period, control the water pump control device to increase the output power, and measure the current flow rate through the water level gauge again, then continue according to this process. As the output power increases, record the water flow rate data at different powers successively. When the output power reaches the highest preset power, a complete power-flow data set will be obtained. According to this data set and the above formula, the power-flow model constructs the second variation relationship between the water flow rate and the output power of the water pump motor, and further obtains the pump power adjustment range that meets the water flow rate within the first time period.

[0219] Since the working conditions of the water pump will change at any time during the actual operation process, it is necessary to update the power-flow model regularly. Mainly, the model update process is adjusted in real time through the communication status between the reservoir and the water pump, and the power-flow model is updated according to the real-time measured data. However, when the communication between the reservoir and the water pump is interrupted, the water pump control device will enter the theoretical calculation mode and perform theoretical updates based on the previously recorded power-flow model.

[0220] In some embodiments, the water supply scheduling strategy generation module 204 is specifically:

[0221] In an embodiment of the present application, a water supply scheduling control model is provided, which is obtained by standardizing and weighting preset water supply evaluation indicators. It can integrate multiple key indicators for evaluating the performance of the water supply system into a comprehensive score indicator, and use this comprehensive score indicator to evaluate the overall performance of the water supply system.

[0222] Exemplarily, in an embodiment of the present application, the water supply evaluation indicators include: water level safety, water use satisfaction rate, number of water supply interruptions, energy consumption per unit of water volume, electrical energy efficiency ratio, continuous operation time of the water pump, pressure fluctuation range, user satisfaction index, emergency water use response time, and recovery time after emergency water use.

[0223] Among them, the water level safety WS is specifically:

[0224]

[0225] In the formula, L is the current water level, L min and L max are the lowest water level and the highest water level respectively.

[0226] The water use satisfaction rate SR is specifically:

[0227]

[0228] In the formula, T met is the time when the water supply system meets the water use demand, and T total is the total peak time.

[0229] The number of water supply interruptions is the total number of water supply interruptions occurring within a certain period of time.

[0230] The energy consumption per unit of water volume EUE is specifically:

[0231]

[0232] In the formula, E total is the total electrical energy consumption, with the unit of kWh; V total is the total water supply volume.

[0233] The electrical energy efficiency ratio COP is specifically:

[0234]

[0235] In the formula, W output is the output water flow work, and E input is the input electrical energy.

[0236] The continuous operation time of the water pump is the time when the water pump operates continuously, ensuring that it does not exceed the set maximum continuous operation time.

[0237] The pressure fluctuation range PF is specifically:

[0238] PF = P max - P min ;

[0239] In the formula, P max and P min are respectively the maximum pressure and the minimum pressure recorded within a certain time period.

[0240] The user satisfaction index USI is specifically:

[0241]

[0242] In the formula, S positive is the number of positive feedbacks, and S total is the total number of feedbacks.

[0243] The emergency water use response time RT is specifically:

[0244] RT = t action - t detection ;

[0245] In the formula, t action is the time to take action, and t detection is the time to detect the emergency water use.

[0246] The recovery time RRT after the emergency water use is specifically:

[0247] RRT = t normal - t cnd ;

[0248] In the formula, t normal is the time for the water supply system to resume normal operation, and t cnd is the time when the emergency event ends.

[0249] By standardizing and assigning weights to the above water supply evaluation indicators, the water supply scheduling control model is constructed, and the specific expression is:

[0250]

[0251] In the formula, CPI is the water supply scheduling control model, WS is the water level safety, which is a binary indicator with a value of 0 or 1; SR is the water use satisfaction rate, EUE is the energy consumption per unit of water volume, and EUE max is the maximum value of the energy consumption per unit of water volume, PF is the pressure fluctuation range, and PF max is the maximum value of the pressure fluctuation range, USI is the user satisfaction index, RT is the emergency water use response time, and RT maxis the maximum value of the emergency water use response time, RRT is the recovery time after emergency water use, RRT max is the maximum value of the recovery time after emergency water use, and w1, w2, w3, w4, w5, w6, and w7 are the weights of the above indicators. Some of the indicators in the above formula are standardized by dividing by the maximum value.

[0252] Among them, CPI is actually an indicator for evaluating the overall performance of the water supply system by the water supply scheduling control model. The closer the value of CPI is to 1, the better the overall performance of the system.

[0253] In the embodiment of the present application, according to the predicted water supply demand and the adjustable range of the pump power, the water supply optimization target is determined.

[0254] Optionally, the water supply optimization target may be to save water resources, save electric energy during the water supply process, or improve the water supply efficiency.

[0255] According to the water supply optimization target, the importance of each water supply evaluation indicator is determined. Then, based on the importance, the numerical weights of the indicators in the water supply scheduling control model are adjusted, and the weights corresponding to the indicators that need to be satisfied by the water supply optimization target are increased to generate an optimal water supply scheduling strategy that meets the water supply optimization target.

[0256] Implementing the embodiment of the present application has the following beneficial effects:

[0257] In the embodiment of the present application, first, according to the reservoir water level data and meteorological change data, the relationship between the water level change and the weather state is studied through the water consumption prediction model, and the future water consumption is accurately predicted by the weather change to obtain the predicted water supply demand in the first time period. Then, according to the predicted water supply demand, the change relationship between the water level, water flow rate of the reservoir and the output power of the pump motor is studied through the power-flow model to obtain the output power range corresponding to the water flow rate that can meet the predicted water supply demand in the first time period, providing data support for the subsequent adjustment of the operation of the pump motor. Then, based on the predicted water supply demand and the adjustable range of the pump power, more attention is paid to the key points of the water supply operation through the water supply scheduling control model, so that the generated optimal water supply scheduling strategy can not only meet the predicted water supply demand, but also achieve the key points of the water supply operation, such as reducing the waste of water resources or saving the use of electric energy, etc., to ensure the continuity and high efficiency of the water supply.

[0258] The third embodiment

[0259] Furthermore, in order to execute the mountainous area water supply method based on the intelligent module electric meter corresponding to the above method embodiment to achieve the corresponding functions and technical effects, Figure 5A structural diagram of a mountain water supply system based on an intelligent module electric meter is provided. For ease of description, only parts related to this embodiment are shown. The mountain water supply system based on the intelligent module electric meter provided by the embodiments of the present application includes:

[0260] A mountain water supply device M1 based on an intelligent module electric meter, which is used for the method embodiments described above.

[0261] The intelligent module electric meter M2 is used to collect the water level data of the reservoir, meteorological change data, and pump operation data, and transmit the data to the mountain water supply device based on the intelligent module electric meter.

[0262] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present application. It should be understood that the above are only specific embodiments of the present application and are not used to limit the protection scope of the present application. In particular, it is pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A water supply method in mountainous areas based on smart module electric meters, characterized in that: include: Collect reservoir water level data, meteorological change data and water pump operation data through smart module meters; Predicting the water supply demand in a first time period based on the water level data of the reservoir and the meteorological change data; According to the predicted water supply demand, the water pump operation data is input into a preset power-flow model to obtain a water pump power adjustment range that meets the predicted water supply demand; According to the predicted water supply demand and the water pump power adjustment range, the preset water supply scheduling control model is adjusted to obtain the optimal water supply scheduling strategy; According to the optimal water supply scheduling strategy, the output power of the water pump motor is adjusted through the smart module meter.

2. The method for supplying water in mountainous areas based on a smart module electric meter according to claim 1, characterized in that: The water supply demand in the first time period is predicted based on the water level data of the reservoir and the meteorological change data, specifically: Selecting a number of water use related features from the water level data of the reservoir, the meteorological change data and the historical water use data by using the Pearson correlation coefficient method; Inputting the water use related characteristics into a preset water consumption prediction model, and predicting the water supply demand in a first time period based on a preset typical water use period; Among them, the typical water use periods include peak water use period, trough water use period and emergency water use period.

3. The method for supplying water in mountainous areas based on smart module electric meters according to claim 2 is characterized in that: The water consumption related features are input into the water consumption prediction model to predict the water supply demand in the first time period from the preset typical water consumption period, specifically: According to the water use related characteristics, construct a first change relationship between historical water use, ambient temperature and water level; Determining predicted water consumption in a first time period through the first change relationship; The predicted water supply demand is obtained from the typical water use period according to the predicted water consumption in the first time period.

4. The method for supplying water in mountainous areas based on a smart module electric meter according to claim 1, characterized in that: According to the predicted water supply demand, the water pump operation data is input into a preset power-flow model to obtain a water pump power adjustment range that meets the predicted water supply demand, specifically: Determining a water flow rate within a first time period based on the predicted water supply demand; The water flow and water pump operation data are input into a preset power-flow model, and combined with the bottom area of ​​the reservoir and the historical water level data, the water pump power adjustment range that meets the water flow in the first time period is calculated.

5. The method for supplying water in mountainous areas based on smart module electric meters according to claim 4 is characterized in that: The pump power adjustment range that satisfies the water flow rate in the first time period is obtained by combining the bottom area of ​​the water reservoir and the historical water level data, specifically: Determine the water flow velocity under different output powers of the water pump motor in combination with the bottom area of ​​the water reservoir and the historical water level data, and construct a second variation relationship between the water flow rate and the output power of the water pump motor based on the water flow velocity; According to the second change relationship, a water pump power adjustment range that satisfies the water flow rate within the first time period is determined.

6. The method for supplying water in mountainous areas based on a smart module electric meter according to any one of claims 1 to 5, characterized in that: According to the predicted water supply demand and the water pump power adjustment range, the preset water supply scheduling control model is adjusted to obtain the optimal water supply scheduling strategy, which is specifically: Determining a water supply optimization target according to the predicted water supply demand and the water pump power adjustment range; The indicator weights in the water supply scheduling control model are adjusted according to the water supply optimization target to generate an optimal water supply scheduling strategy.

7. The method for supplying water in mountainous areas based on a smart module electric meter according to claim 6, characterized in that: The weights of the indicators in the water supply scheduling control model are adjusted according to the water supply optimization target, specifically: Integrate the preset water supply evaluation indicators through the corresponding indicator weights to construct the water supply scheduling control model; Determining the importance of each of the water supply evaluation indicators according to the water supply optimization goal; According to the importance, numerically adjusting the indicator weights of the water supply scheduling control model to generate an optimal water supply scheduling strategy that meets the water supply optimization goal; Among them, the water supply evaluation indicators include: water level safety, water use satisfaction rate, number of water supply interruptions, energy consumption per unit of water volume, electricity energy efficiency ratio, continuous operation time of water pumps, pressure fluctuation range, user satisfaction index, emergency water use response time, and recovery time after emergency water use.

8. The method for supplying water in mountainous areas based on smart module electric meters according to claim 7 is characterized in that: The preset water supply evaluation indexes are integrated through the corresponding index weights to construct the water supply scheduling control model, specifically: The water supply scheduling control model is specifically expressed as follows: In the formula, CPI is the water supply scheduling control model, WS is the water level security, SR is the water satisfaction rate, EUE is the energy consumption per unit water volume, and EUE max is the maximum energy consumption per unit water volume, PF is the pressure fluctuation range, PF max is the maximum value of the pressure fluctuation range, USI is the user satisfaction index, RT is the emergency water response time, and RT max is the maximum value of the emergency water response time, RRT is the recovery time after emergency water use, RRT max is the maximum value of the recovery time after emergency water use, and w1, w2, w3, w4, w5, w6, and w7 are the indicator weights.

9. A mountain water supply device based on a smart module electric meter, characterized in that: include: Data acquisition module, demand forecasting module, power adjustment range module, water supply scheduling strategy generation module and water pump power adjustment module; Among them, the data acquisition module is used to collect reservoir water level data, meteorological change data and water pump operation data through the smart module meter; The demand forecasting module is used to forecast the water supply demand within a first time period based on the water level data of the reservoir and the meteorological change data; The power adjustment range module is used to input the water pump operation data into a preset power-flow model according to the predicted water supply demand, so as to obtain the water pump power adjustment range that meets the predicted water supply demand; The water supply scheduling strategy generation module is used to adjust the preset water supply scheduling control model according to the predicted water supply demand and the water pump power adjustment range to obtain the optimal water supply scheduling strategy; The water pump power regulation module is used to adjust the output power of the water pump motor through the smart module meter according to the optimal water supply scheduling strategy.

10. A mountain water supply system based on a smart module electric meter, characterized in that: include: Mountain water supply device and smart module meter based on smart module meter; Wherein, the mountain water supply device based on the smart module electric meter is used to execute the mountain water supply method based on the smart module electric meter as described in any one of claims 1 to 8; The smart module electric meter is used to collect reservoir water level data, meteorological change data and water pump operation data, and transmit the data to the mountain water supply device based on the smart module electric meter.

Images