Intelligent energy consumption control system and method and application of intelligent energy consumption control system and method in sluice energy consumption control

Abstract

The invention relates to the technical field of energy consumption control, in particular to an intelligent energy consumption control system and method and application of the intelligent energy consumption control system and method to sluice energy consumption control, a target sluice is accurately locked through collected position data of a target farmland irrigation area, the opening height of the target sluice is scientifically set according to farmland irrigation requirements, and sluice opening operation is executed; constructing an irrigation water volume prediction model through the historical farmland irrigation operation feature data, and performing water volume prediction on the irrigation water volume prediction model and the collected target farmland irrigation area feature data to generate target farmland irrigation predicted water volume data; the target water gate water yield is monitored in real time through the water gate energy consumption control platform, and if the target water gate water yield reaches the target farmland irrigation predicted water yield data, water gate closing operation is executed; otherwise, continuously monitoring the real-time water yield of the target water gate through the water gate energy consumption control platform; through reasonable planning of the opening height of the water gate and accurate monitoring of the closing time of the water gate, intelligent control of the energy consumption of the water gate is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption control, and specifically to an intelligent energy consumption control system, method and its application in the energy consumption control of sluice gates. Background Art

[0002] In the field of water conservancy projects, as an important water conservancy facility, the sluice gate undertakes various functions such as flood control and irrigation. With the continuous development of Internet technology, the control of sluice gate has gradually become intelligent. However, the traditional sluice gate control technology often fails to accurately control the sluice gate, resulting in additional resource consumption.

[0003] The Chinese patent application with the publication number CN118732512A introduces a sluice gate control system for a reservoir. By calculating the data obtained by normalizing the gate opening, the water level in front of the gate and the water level behind the gate in the historical data respectively through the genetic program carried, and the measured flow rate through the gate, the optimal objective function is obtained. The real-time collected data is input into the optimal objective function to generate the real-time flow rate through the gate for flood discharge of the reservoir. When the real-time flow rate through the gate exceeds the upper limit value, the integrated measurement and control gate is controlled to reduce the opening, and a warning is issued, realizing the accurate adjustment of the gate opening, enhancing the timeliness and accuracy of the flood discharge warning of the reservoir. However, it cannot accurately control the opening height and the opening and closing time of the sluice gate, resulting in unnecessary energy waste and high energy consumption during the process of performing sluice gate control operations. Summary of the Invention

[0004] (I) Technical Problems to be Solved

[0005] To solve the deficiencies in the background art, the present invention provides an intelligent energy consumption control system, method and its application in the energy consumption control of sluice gates, realizing the intelligent control of sluice gate energy consumption through the reasonable planning of the opening height of the sluice gate and the accurate monitoring of the closing time of the sluice gate.

[0006] (II) Technical Solutions

[0007] An intelligent energy consumption control method includes the following steps:

[0008] S1. Collect the position data of the target farmland irrigation area, and determine the target sluice gate according to the position data of the target farmland irrigation area;

[0009] S2. Set the opening height of the target sluice gate according to the farmland irrigation demand, and control the target sluice gate to perform the sluice gate opening operation according to the opening height of the target sluice gate;

[0010] S3. Collect the characteristic data of historical farmland irrigation operations;

[0011] S4. Construct an irrigation water volume prediction model according to the characteristic data of historical farmland irrigation operations;

[0012] S5. Collect the characteristic data of the target farmland irrigation area, and predict the irrigation water volume of the target farmland according to the characteristic data of the target farmland irrigation area and the irrigation water volume prediction model, and generate the predicted irrigation water volume data of the target farmland.

[0013] S6. Monitor the real-time water output of the target sluice through the sluice energy consumption control platform. If the real-time water output of the target sluice reaches the predicted irrigation water volume data of the target farmland, perform the sluice closing operation; otherwise, continue to monitor the real-time water output of the target sluice through the sluice energy consumption control platform.

[0014] Precisely lock the target sluice through the collected position data of the target farmland irrigation area, scientifically set the opening height of the target sluice according to the farmland irrigation requirements, and perform the sluice opening operation; construct an irrigation water volume prediction model through the historical farmland irrigation operation characteristic data, and perform water volume prediction with the collected characteristic data of the target farmland irrigation area to generate the predicted irrigation water volume data of the target farmland; monitor the water output of the target sluice in real time through the sluice energy consumption control platform. If the water output of the target sluice reaches the predicted irrigation water volume data of the target farmland, perform the sluice closing operation; otherwise, continue to monitor the real-time water output of the target sluice through the sluice energy consumption control platform; realize the intelligent control of the sluice energy consumption through the reasonable planning of the sluice opening height and the precise monitoring of the sluice closing time.

[0015] Preferably, the specific steps of collecting the position data of the target farmland irrigation area and determining the target sluice according to the position data of the target farmland irrigation area are as follows:

[0016] S11. Online collect the position data of the target farmland irrigation area through the sluice energy consumption control platform to generate the position data A of the target farmland irrigation area.

[0017] S12. Establish an irrigation area sluice characteristic data set B = {b 1 , b 2 , …, b i , …, b k}, where b i represents the sluice characteristic data corresponding to the i-th farmland irrigation area, k represents the total number of farmland irrigation areas, and the sluice characteristic data includes sluice position data and sluice number data.

[0018] S13. Use a two-way search algorithm to traverse all the irrigation area sluice characteristic data in the irrigation area sluice characteristic data set, search for the irrigation area sluice characteristic data that matches the position data A of the target farmland irrigation area, and use the sluice corresponding to the irrigation area sluice characteristic data that matches the position data A of the target farmland irrigation area as the target sluice.

[0019] Preferably, the target sluice opening height is set according to the farmland irrigation demand, and the specific steps for controlling the target sluice to perform the sluice opening operation according to the target sluice opening height are as follows:

[0020] S21. Online obtain the demand for this farmland irrigation operation through the farmland irrigation demand selection interface to generate farmland irrigation demand data. If the farmland irrigation demand data is urgent, set the target sluice opening height h to the maximum sluice opening height h max ; if the farmland irrigation demand data is not urgent, set the optimal sluice opening height h best through the Snow Goose optimization algorithm, and set the target sluice opening height h to the optimal sluice opening height h best ; the maximum sluice opening height represents the maximum lifting height of the target sluice;

[0021] The specific steps for setting the optimal sluice opening height through the Snow Goose optimization algorithm are as follows:

[0022] S211. Construct a sluice opening height search Snow Goose population, set the population size to N, the current iteration number to t, the maximum iteration number to t max and the dimension of the optimal sluice opening height search space to P;

[0023] Set the interval (0, h max ) as the optimal sluice opening height search space. Randomly generate N sluice opening heights in the optimal sluice opening height search space, and each sluice opening height corresponds to a sluice opening height search Snow Goose individual in the sluice opening height search Snow Goose population;

[0024] S212. Calculate the fitness value of each sluice opening height search Snow Goose individual in the sluice opening height search Snow Goose population, sort the sluice opening height search Snow Goose individuals in the sluice opening height search Snow Goose population from largest to smallest according to the fitness value, and take the sluice opening height search Snow Goose individual with the largest fitness value as the current optimal individual; the fitness value calculation formula is as follows:

[0025]

[0026] Among them, Fit i represents the fitness value of the i-th sluice opening height search Snow Goose individual in the sluice opening height search Snow Goose population, Q i1 , Q i2 and Q i3 respectively represent the power consumption, sluice loss value, and water output per unit time of the sluice opening height corresponding to the i-th sluice opening height search Snow Goose individual in the sluice opening height search Snow Goose population, ε, φ, and respectively represent the power consumption weight factor, the sluice loss value weight factor, and the water discharge weight factor, and γ represents the correction value;

[0027] S213. If the angle when each individual snow goose searching for the sluice opening height in the snow goose population of sluice opening height searches for migration behavior is greater than π, then go to S214; if the angle when each individual snow goose searching for the sluice opening height in the snow goose population of sluice opening height searches for migration behavior is less than or equal to π, then go to S215;

[0028] S214. Update the speed of each individual snow goose searching for the sluice opening height in the snow goose population of sluice opening height; the speed update formula is as follows:

[0029]

[0030] Among them, and respectively represent the speed after position update and the current speed of the i-th individual snow goose searching for the sluice opening height in the snow goose population of sluice opening height, β represents the acceleration, α represents the weight factor for controlling the speed of the snow goose, and

[0031] Each individual snow goose searching for the sluice opening height in the snow goose population of sluice opening height updates its position by adopting a V-shaped flight strategy in the search space of the optimal sluice opening height according to the updated speed, and enters S216 after position update; the position update formula is as follows:

[0032]

[0033] Among them, and represent the position after position update and the current position of the i-th individual snow goose searching for the sluice opening height in the snow goose population of sluice opening height, X best represents the position of the current optimal individual, represents the current position of the z-th individual snow goose randomly selected from the snow goose population of sluice opening height, and λ and η represent two parameters for controlling the flight of the snow goose;

[0034] S215. Each individual snow goose searching for the sluice opening height in the snow goose population of sluice opening height updates its position by adopting a straight-line flight strategy in the search space of the optimal sluice opening height, and enters S216 after position update; the position update formula is as follows:

[0035]

[0036] Among them, The operation symbol representing element-wise multiplication, and ω represents the Brownian motion function;

[0037] S216. Calculate the fitness value of each snow goose individual for the sluice opening height search in the snow goose population for the sluice opening height search after position update. If the fitness value of a snow goose individual for the sluice opening height search after position update is greater than the original fitness value, replace the original position with the new position of this snow goose individual for the sluice opening height search; otherwise, retain the original position of this snow goose individual for the sluice opening height search;

[0038] Re-sort each snow goose individual in the snow goose population for the sluice opening height search in descending order according to the fitness value, and take the snow goose individual with the largest fitness value as the new current optimal individual;

[0039] S217. Determine whether the current iteration number t is less than the maximum iteration number t max , if the current iteration number t is less than the maximum iteration number t max , then increment the current iteration number t by 1 and return to S213; otherwise, take the current optimal individual as the global optimal solution, and output the sluice opening height corresponding to the global optimal solution as the optimal sluice opening height h best ;

[0040] S22. Control the target sluice to perform the sluice opening operation through the sluice energy consumption control platform, and adjust the lifting height of the target sluice to the set target sluice opening height h.

[0041] Quickly lock the target sluice by obtaining the position data of the target farmland irrigation area, and adaptively adjust the sluice opening height according to the farmland irrigation demand. While meeting the irrigation demand, it effectively avoids additional energy consumption; set the optimal sluice opening height through the snow goose optimization algorithm, quickly and accurately find the optimal sluice opening height under the influence of multiple factors, accelerate the convergence speed of the optimization process, and at the same time, the snow goose optimization algorithm has good robustness, ensuring the stability of the optimization process.

[0042] Preferably, the specific steps for collecting historical farmland irrigation operation characteristic data are as follows:

[0043] S31. Collect the characteristic data during the execution of historical farmland irrigation operations through the sluice energy consumption control platform to generate a historical farmland irrigation operation characteristic data set C = {c 1 , c 2 , …, c i , …, c l}, where c iDenote the characteristic data when the i-th historical farmland irrigation operation is executed, and l denote the total number of collected historical farmland irrigation operations. The characteristic data represents the farmland irrigation area characteristic data and the corresponding water gate water output data when the historical farmland irrigation operation is executed. The farmland irrigation area characteristic data includes, but is not limited to, farmland irrigation area area data, farmland irrigation area weather data, farmland irrigation area soil type data, and farmland irrigation area crop type data.

[0044] Preferably, the specific steps for constructing an irrigation water volume prediction model according to the historical farmland irrigation operation characteristic data are as follows:

[0045] S41. Set the training data ratio and the test data ratio, and divide the historical farmland irrigation operation characteristic data set according to the training data ratio and the test data ratio to obtain a historical farmland irrigation operation characteristic training data set and a historical farmland irrigation operation characteristic test data set;

[0046] S42. Construct an initial SVM model, set the penalty factor as and the radial basis kernel parameter as θ, and at the same time set the kernel function of the initial SVM model as the Sigmoid radial basis kernel function; the formula of the Sigmoid radial basis kernel function is as follows:

[0047] q(x,y) = tanh(θx T y + θ),

[0048] where q(x,y) represents the Sigmoid radial basis kernel function, x and y represent two input feature vectors, θ represents the offset, and x T represents the transpose of the vector x;

[0049] S43. Set the training error threshold and the maximum number of training times, and input the historical farmland irrigation operation characteristic training data set into the initial SVM model for training until the training error is less than the training error threshold or the number of training times is greater than the maximum number of training times to obtain a trained SVM model;

[0050] S44. Set the accuracy threshold, input the historical farmland irrigation operation characteristic test data set into the trained SVM model for testing and calculate the accuracy of the test result. If the accuracy of the test result is greater than or equal to the accuracy threshold, an irrigation water volume prediction model is obtained; otherwise, adjust the SVM model parameters through the grid search algorithm until the accuracy of the test result is greater than or equal to the accuracy threshold.

[0051] Preferably, the specific steps for collecting the characteristic data of the target farmland irrigation area, predicting the irrigation water volume of the target farmland according to the characteristic data of the target farmland irrigation area and the irrigation water volume prediction model, and generating the predicted irrigation water volume data of the target farmland are as follows:

[0052] S51. Online collect the characteristic data of the target farmland irrigation area through the water gate energy consumption control platform to generate the characteristic data C of the target farmland irrigation area shishi , and the characteristic data of the target farmland irrigation area includes but is not limited to the area data of the target farmland irrigation area, the weather data of the target farmland irrigation area, the soil type data of the target farmland irrigation area, and the crop type data of the target farmland irrigation area;

[0053] S52. Input the characteristic data C of the target farmland irrigation area shishi into the irrigation water volume prediction model to predict the irrigation water volume of the target farmland, and output the predicted irrigation water volume data D of the target farmland yuce .

[0054] Scientifically construct an irrigation water volume prediction model through the historical characteristic data of farmland irrigation operations, and input the characteristic data of the target farmland irrigation area collected online into the irrigation water volume prediction model to accurately predict the predicted irrigation water volume data of the target farmland, providing a data basis for subsequent reasonable monitoring of the water output of the target water gate.

[0055] Preferably, monitor the real-time water output of the target water gate through the water gate energy consumption control platform. If the real-time water output of the target water gate reaches the predicted irrigation water volume data of the target farmland, perform the water gate closing operation; otherwise, continue to monitor the real-time water output of the target water gate through the water gate energy consumption control platform. The specific steps are as follows:

[0056] S61. Real-time collect the water output of the target water gate through the flow sensor installed on the target water gate to generate the real-time water output data D of the target water gate shishi , and push the real-time water output data D of the target water gate shishi to the water gate energy consumption control platform through the Internet of Things communication network. The flow sensor represents any one of an electromagnetic flowmeter, an ultrasonic flowmeter, a vortex street flowmeter, and a positive displacement flowmeter;

[0057] S62. Numerically compare the real-time water output data D of the target water gate shishi with the predicted irrigation water volume data D of the target farmland yuce to generate the execution instruction data E for the water gate closing operation according to the numerical comparison result;

[0058] If the real-time water output data D of the target water gate shishi is less than the predicted irrigation water volume data D of the target farmlandyuce It means that the real-time water discharge of the sluice does not meet the water demand for target farmland irrigation. The execution instruction data E for closing the sluice is output as not closing, and the real-time water discharge of the target sluice is continuously collected through the flow sensor installed on the target sluice until the real-time water discharge data D of the target sluice shishi is greater than or equal to the predicted water volume data D for target farmland irrigation yuce ;

[0059] If the real-time water discharge data D of the target sluice shishi is greater than or equal to the predicted water volume data D for target farmland irrigation yuce It means that the real-time water discharge of the sluice has met the water demand for target farmland irrigation. The execution instruction data E for closing the sluice is output as closing, and the execution instruction data E for closing the sluice is pushed to the sluice energy consumption control platform through the Internet of Things communication network. After receiving the execution instruction data E for closing the sluice, the sluice energy consumption control platform executes the sluice closing operation.

[0060] The real-time water discharge of the target sluice is collected through the flow sensor and numerically compared with the predicted water volume data for target farmland irrigation output by the irrigation water volume prediction model. According to the numerical comparison result, it is monitored in real time whether the water discharge of the target sluice meets the water demand for farmland irrigation, effectively avoiding the waste of electric energy and water resources caused by untimely closing of the sluice, and improving the accuracy of the sluice energy control operation.

[0061] The present invention further includes an energy consumption intelligent control system, including a target sluice locking module, a sluice opening operation execution module, a historical farmland irrigation operation characteristic data acquisition module, an irrigation water volume prediction model construction module, a target farmland irrigation water volume prediction module, and a sluice closing operation execution module;

[0062] The target sluice locking module online collects the position data of the target farmland irrigation area through the sluice energy consumption control platform, traverses the sluice characteristic data set of the irrigation area by using the bidirectional search algorithm, searches out the sluice characteristic data of the irrigation area that matches the collected position data, and takes the sluice corresponding to the sluice characteristic data of the irrigation area that matches the collected position data as the target sluice;

[0063] The sluice opening operation execution module online obtains the requirements of this farmland irrigation operation through the farmland irrigation demand selection interface. If it is urgent, the opening height of the target sluice is set to the maximum sluice opening height; otherwise, the optimal sluice opening height is set through the Snow Goose optimization algorithm, and the opening height of the target sluice is set to the optimal sluice opening height;

[0064] The historical farmland irrigation operation feature data collection module collects the feature data during the execution of historical farmland irrigation operations through the sluice energy consumption control platform, and generates historical farmland irrigation operation feature data;

[0065] The irrigation water volume prediction model construction module divides the historical farmland irrigation operation feature data set, and trains and tests the initial SVM model based on the historical farmland irrigation operation feature training data set and the historical farmland irrigation operation feature test data set obtained after data division, to obtain an irrigation water volume prediction model;

[0066] The target farmland irrigation water volume prediction module online collects the feature data of the target farmland irrigation area through the sluice energy consumption control platform, generates the target farmland irrigation area feature data and inputs it into the irrigation water volume prediction model to predict the target farmland irrigation water volume, and outputs the target farmland irrigation predicted water volume data;

[0067] The sluice closing operation execution module real-time collects the water discharge of the target sluice through the flow sensor installed on the target sluice, generates the target sluice real-time water discharge data. If the target sluice real-time water discharge data is less than the target farmland irrigation predicted water volume data, it outputs that the sluice closing operation execution instruction data is not to close, and continues to monitor the water discharge of the target sluice; otherwise, it outputs that the sluice closing operation execution instruction data is to close, pushes the sluice closing operation execution instruction data to the sluice energy consumption control platform through the Internet of Things communication network, and executes the sluice closing operation.

[0068] (III) Beneficial effects

[0069] 1. The present invention accurately locks the target sluice through the collected target farmland irrigation area location data, scientifically sets the opening height of the target sluice according to the farmland irrigation demand, and executes the sluice opening operation; constructs an irrigation water volume prediction model through the historical farmland irrigation operation feature data, and conducts water volume prediction with the collected target farmland irrigation area feature data to generate the target farmland irrigation predicted water volume data; real-time monitors the water discharge of the target sluice through the sluice energy consumption control platform. If the water discharge of the target sluice reaches the target farmland irrigation predicted water volume data, it executes the sluice closing operation; otherwise, it continues to monitor the real-time water discharge of the target sluice through the sluice energy consumption control platform; realizes the intelligent control of sluice energy consumption through the reasonable planning of the sluice opening height and the accurate monitoring of the sluice closing time.

[0070] 2. Quickly lock the target sluice by obtaining the location data of the target farmland irrigation area, and adaptively adjust the opening height of the sluice according to the farmland irrigation requirements. While meeting the irrigation requirements, it effectively avoids additional energy consumption; set the optimal sluice opening height through the Snow Goose optimization algorithm, quickly and accurately find the optimal sluice opening height under the influence of multiple factors, accelerate the convergence speed of the optimization process, and at the same time, the Snow Goose optimization algorithm has good robustness, ensuring the stability of the optimization process;

[0071] 3. Scientifically construct an irrigation water volume prediction model through the historical farmland irrigation operation characteristic data, and input the characteristic data of the target farmland irrigation area collected online into the irrigation water volume prediction model to accurately predict the target farmland irrigation predicted water volume data, providing a data basis for subsequent reasonable monitoring of the water output of the target sluice;

[0072] 4. Real-time collect the water output of the target sluice through a flow sensor, and compare it numerically with the target farmland irrigation predicted water volume data output by the irrigation water volume prediction model. According to the numerical comparison result, monitor in real time whether the water output of the target sluice meets the farmland irrigation water volume requirements, effectively avoiding the waste of electric energy and water resources caused by untimely closing of the sluice, and improving the accuracy of the sluice energy control operation. Brief Description of the Drawings

[0073] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0074] Figure 1 It is a flowchart of an intelligent energy consumption control method provided by the present invention;

[0075] Figure 2 It is a schematic diagram of the modules of an intelligent energy consumption control system provided by the present invention. Detailed Embodiments

[0076] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0077] In the description of the present invention, it should be understood that the terms "open hole", "upper", "lower", "top", "middle", "inner", etc. indicating orientation or positional relationship are only for the convenience of describing the invention and simplifying the description, rather than indicating or implying that the components or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the invention.

[0078] The first embodiment is as follows:

[0079] Please refer to Figure 1 , an intelligent energy consumption control method, including the following steps:

[0080] S1. Collect the position data of the target farmland irrigation area, and determine the target sluice according to the position data of the target farmland irrigation area;

[0081] S11. Online collect the position data of the target farmland irrigation area through the sluice energy consumption control platform to generate the position data A of the target farmland irrigation area;

[0082] S12. Establish an irrigation area sluice feature data set B = {b 1 , b 2 , …, b i , …, b k}, where b i represents the sluice feature data corresponding to the i-th farmland irrigation area, k represents the total number of farmland irrigation areas, and the sluice feature data includes sluice position data and sluice number data;

[0083] S13. Use the bidirectional search algorithm to traverse all the irrigation area sluice feature data in the irrigation area sluice feature data set, search out the irrigation area sluice feature data that matches the position data A of the target farmland irrigation area, and use the sluice corresponding to the irrigation area sluice feature data that matches the position data A of the target farmland irrigation area as the target sluice.

[0084] S2. Set the opening height of the target sluice according to the farmland irrigation demand, and control the target sluice to perform the sluice opening operation according to the opening height of the target sluice;

[0085] S21. Online obtain the demand for this farmland irrigation operation through the farmland irrigation demand selection interface to generate farmland irrigation demand data. If the farmland irrigation demand data is urgent, set the opening height h of the target sluice to the maximum sluice opening height h max ; if the farmland irrigation demand data is not urgent, set the optimal sluice opening height h best through the Snow Goose optimization algorithm, and set the opening height h of the target sluice to the optimal sluice opening height h best ; the maximum sluice opening height represents the maximum lifting height of the target sluice;

[0086] The specific steps for setting the optimal sluice opening height through the snow goose optimization algorithm are as follows:

[0087] S211. Construct a snow goose population for searching the sluice opening height, set the population size as N, the current iteration number as t, the maximum iteration number as t max and the dimension of the search space for the optimal sluice opening height as P;

[0088] Set the interval (0, h max ) as the search space for the optimal sluice opening height, and randomly generate N sluice opening heights in the search space for the optimal sluice opening height. Each sluice opening height corresponds to a snow goose individual for searching the sluice opening height in the snow goose population for searching the sluice opening height;

[0089] S212. Calculate the fitness values of the snow goose individuals for searching the sluice opening height in the snow goose population for searching the sluice opening height, sort the snow goose individuals for searching the sluice opening height in the snow goose population for searching the sluice opening height in descending order according to the fitness values, and take the snow goose individual for searching the sluice opening height with the largest fitness value as the current optimal individual; the fitness value calculation formula is as follows:

[0090]

[0091] Among them, Fit i represents the fitness value of the i-th snow goose individual for searching the sluice opening height in the snow goose population for searching the sluice opening height, Q i1 , Q i2 and Q i3 respectively represent the power consumption, sluice loss value, and water output per unit time of the sluice opening height corresponding to the i-th snow goose individual for searching the sluice opening height in the snow goose population for searching the sluice opening height, ε, φ, and respectively represent the power consumption weight factor, sluice loss value weight factor, and water output weight factor, and γ represents the correction value;

[0092] S213. If the included angle when the snow goose individuals for searching the sluice opening height in the snow goose population for searching the sluice opening height perform migration behavior is greater than π, then enter S214; if the included angle when the snow goose individuals for searching the sluice opening height in the snow goose population for searching the sluice opening height perform migration behavior is less than or equal to π, then enter S215;

[0093] S214. Update the speeds of the snow goose individuals for searching the sluice opening height in the snow goose population for searching the sluice opening height; the speed update formula is as follows:

[0094]

[0095] Among them, and respectively represent the velocity and the current velocity of the i-th snow goose individual in the water gate opening height search snow goose population after position update. β represents the acceleration, α represents the weight factor controlling the velocity of the snow goose, and

[0096] each snow goose individual in the water gate opening height search snow goose population updates its position by adopting a V-shaped flight strategy in the optimal water gate opening height search space according to the updated velocity, and enters S216 after position update; the position update formula is as follows:

[0097]

[0098] Among them, and represent the position and the current position of the i-th snow goose individual in the water gate opening height search snow goose population after position update, X best represents the position of the current optimal individual, represents the current position of the z-th snow goose individual randomly selected from the water gate opening height search snow goose population, and λ and η represent two parameters controlling the flight of the snow goose;

[0099] In S215, each snow goose individual in the water gate opening height search snow goose population updates its position by adopting a straight-line flight strategy in the optimal water gate opening height search space, and enters S216 after position update; the position update formula is as follows:

[0100]

[0101] Among them, represents the operation symbol of element-wise multiplication, and ω represents the Brownian motion function;

[0102] In S216, calculate the fitness value of each snow goose individual in the water gate opening height search snow goose population after position update. If the fitness value of a snow goose individual after position update is greater than the original fitness value, replace the original position with the new position of this snow goose individual; otherwise, retain the original position of this snow goose individual;

[0103] Re-sort each snow goose individual in the water gate opening height search snow goose population from largest to smallest according to the fitness value, and take the snow goose individual with the largest fitness value as the new current optimal individual;

[0104] S217. Determine whether the current iteration number t is less than the maximum iteration number t max , if the current iteration number t is less than the maximum iteration number t max , then increment the current iteration number t by 1 and return to S213; otherwise, take the current optimal individual as the global optimal solution and output the water gate opening height corresponding to the global optimal solution as the optimal water gate opening height h best ;

[0105] S22. Control the target water gate to perform the water gate opening operation through the water gate energy consumption control platform, and adjust the lifting height of the target water gate to the set target water gate opening height h.

[0106] S3. Collect historical farmland irrigation operation characteristic data;

[0107] S31. Collect the characteristic data during the execution of historical farmland irrigation operations through the water gate energy consumption control platform, and generate a historical farmland irrigation operation characteristic data set C = {c 1 , c 2 , …, c i , …, c l}, where c i represents the characteristic data during the execution of the i-th historical farmland irrigation operation, l represents the total number of historical farmland irrigation operations collected, and the characteristic data represents the farmland irrigation area characteristic data and the corresponding water gate water output data during the execution of historical farmland irrigation operations. The farmland irrigation area characteristic data includes, but is not limited to, farmland irrigation area area data, farmland irrigation area weather data, farmland irrigation area soil type data, and farmland irrigation area crop type data.

[0108] S4. Construct an irrigation water volume prediction model based on the historical farmland irrigation operation characteristic data;

[0109] S41. Set the training data ratio and the test data ratio, and divide the historical farmland irrigation operation characteristic data set according to the training data ratio and the test data ratio to obtain a historical farmland irrigation operation characteristic training data set and a historical farmland irrigation operation characteristic test data set;

[0110] S42. Construct an initial SVM model, set the penalty factor to and the radial basis kernel parameter to θ, and at the same time set the kernel function of the initial SVM model to the Sigmoid radial basis kernel function; The formula of the Sigmoid radial basis kernel function is as follows:

[0111]

[0112] where q(x, y) represents the Sigmoid radial basis kernel function, and x and y represent two input feature vectors, Indicates the offset, x T Indicates the transpose of the vector x;

[0113] S43. Set the training error threshold and the maximum number of training times, and input the historical farmland irrigation operation feature training data set into the initial SVM model for training until the training error is less than the training error threshold or the number of training times is greater than the maximum number of training times, so as to obtain a trained SVM model;

[0114] S44. Set the accuracy threshold, input the historical farmland irrigation operation feature test data set into the trained SVM model for testing and calculate the accuracy of the test result. If the accuracy of the test result is greater than or equal to the accuracy threshold, an irrigation water volume prediction model is obtained; otherwise, adjust the SVM model parameters through the grid search algorithm until the accuracy of the test result is greater than or equal to the accuracy threshold.

[0115] S5. Collect the feature data of the target farmland irrigation area, and predict the irrigation water volume of the target farmland according to the feature data of the target farmland irrigation area and the irrigation water volume prediction model, so as to generate the predicted irrigation water volume data of the target farmland;

[0116] S51. Online collect the feature data of the target farmland irrigation area through the sluice energy consumption control platform to generate the feature data C of the target farmland irrigation area shishi , and the feature data of the target farmland irrigation area includes but is not limited to the area data of the target farmland irrigation area, the weather data of the target farmland irrigation area, the soil type data of the target farmland irrigation area, and the crop type data of the target farmland irrigation area;

[0117] S52. Input the feature data C of the target farmland irrigation area shishi into the irrigation water volume prediction model to predict the irrigation water volume of the target farmland, and output the predicted irrigation water volume data D of the target farmland yuce .

[0118] S6. Monitor the real-time water output of the target sluice through the sluice energy consumption control platform. If the real-time water output of the target sluice reaches the predicted irrigation water volume data of the target farmland, perform the sluice closing operation; otherwise, continue to monitor the real-time water output of the target sluice through the sluice energy consumption control platform;

[0119] S61. Real-time collect the water output of the target sluice through the flow sensor installed on the target sluice to generate the real-time water output data D of the target sluice shishi , and transmit the real-time water output data D of the target sluice through the Internet of Things communication network shishiPush it to the water gate energy consumption control platform, where the flow sensor represents any one of an electromagnetic flowmeter, an ultrasonic flowmeter, a vortex street flowmeter, and a positive displacement flowmeter;

[0120] S62. Through the water gate energy consumption control platform, the real-time water output data D of the target water gate shishi and the predicted water volume data D for target farmland irrigation yuce are numerically compared, and an execution instruction data E for the water gate closing operation is generated according to the numerical comparison result;

[0121] If the real-time water output data D of the target water gate shishi is less than the predicted water volume data D for target farmland irrigation yuce , it means that the real-time water output of the water gate does not meet the water volume requirement for target farmland irrigation. Output the execution instruction data E for the water gate closing operation as not to close, and continue to collect the real-time water output of the target water gate through the flow sensor installed on the target water gate until the real-time water output data D of the target water gate shishi is greater than or equal to the predicted water volume data D for target farmland irrigation yuce ;

[0122] If the real-time water output data D of the target water gate shishi is greater than or equal to the predicted water volume data D for target farmland irrigation yuce , it means that the real-time water output of the water gate has met the water volume requirement for target farmland irrigation. Output the execution instruction data E for the water gate closing operation as close, and push the execution instruction data E for the water gate closing operation to the water gate energy consumption control platform through the Internet of Things communication network. After receiving the execution instruction data E for the water gate closing operation, the water gate energy consumption control platform executes the water gate closing operation.

[0123] Embodiment 2 is as follows:

[0124] Please refer to Figure 2 , an energy consumption intelligent control system, including a target water gate locking module, a water gate opening operation execution module, a historical farmland irrigation operation feature data acquisition module, an irrigation water volume prediction model construction module, a target farmland irrigation water volume prediction module, and a water gate closing operation execution module;

[0125] The target water gate locking module online collects the position data of the target farmland irrigation area through the water gate energy consumption control platform, traverses the irrigation area water gate feature data set by using a bidirectional search algorithm, searches out the irrigation area water gate feature data matching the collected position data, and takes the water gate corresponding to the irrigation area water gate feature data matching the collected position data as the target water gate;

[0126] The sluice opening operation execution module obtains the requirements of the current farmland irrigation operation online through the farmland irrigation demand selection interface. If it is an emergency, the target sluice opening height is set to the maximum sluice opening height; otherwise, the optimal sluice opening height is set through the Snow Goose optimization algorithm, and the target sluice opening height is set to the optimal sluice opening height.

[0127] The historical farmland irrigation operation feature data acquisition module collects the feature data during the execution of historical farmland irrigation operations through the sluice energy consumption control platform to generate historical farmland irrigation operation feature data.

[0128] The irrigation water volume prediction model construction module divides the historical farmland irrigation operation feature data set, and trains and tests the initial SVM model based on the historical farmland irrigation operation feature training data set and the historical farmland irrigation operation feature test data set obtained after data division to obtain the irrigation water volume prediction model.

[0129] The target farmland irrigation water volume prediction module online collects the feature data of the target farmland irrigation area through the sluice energy consumption control platform, generates the target farmland irrigation area feature data and inputs it into the irrigation water volume prediction model for predicting the target farmland irrigation water volume, and outputs the target farmland irrigation predicted water volume data.

[0130] The sluice closing operation execution module real-time collects the water output of the target sluice through the flow sensor installed on the target sluice to generate the target sluice real-time water output data. If the target sluice real-time water output data is less than the target farmland irrigation predicted water volume data, the sluice closing operation execution instruction data output is not to close, and continue to monitor the water output of the target sluice; otherwise, the sluice closing operation execution instruction data output is to close, and the sluice closing operation execution instruction data is pushed to the sluice energy consumption control platform through the Internet of Things communication network, and the sluice closing operation is executed.

[0131] In the description of this specification, the description with reference to terms such as "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0132] The preferred embodiments of the invention disclosed above are only used to help illustrate the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the invention, so that those skilled in the art can well understand and utilize the invention.

Claims

1. An intelligent energy consumption control method, characterized in that: The steps include: S1. Collecting the location data of the target farmland irrigation area, and determining the target sluice gate according to the location data of the target farmland irrigation area; S2. Setting a target sluice gate opening height according to farmland irrigation demand, and controlling the target sluice gate to perform sluice gate opening operation according to the target sluice gate opening height; S3. Collect historical farmland irrigation operation characteristic data; S4, constructing an irrigation water volume prediction model based on the historical farmland irrigation operation characteristic data; S5, collecting characteristic data of the target farmland irrigation area, predicting the target farmland irrigation water volume according to the characteristic data of the target farmland irrigation area and the irrigation water volume prediction model, and generating target farmland irrigation prediction water volume data; S6. Monitor the real-time water output of the target sluice through the sluice energy consumption control platform. If the real-time water output of the target sluice reaches the target farmland irrigation predicted water volume data, execute the sluice closing operation; otherwise, continue to monitor the real-time water output of the target sluice through the sluice energy consumption control platform.

2. The energy consumption intelligent control method according to claim 1, characterized in that: The S1 comprises the following steps: S11, collecting the location data of the target farmland irrigation area online through the sluice energy consumption control platform to generate the location data A of the target farmland irrigation area; S12. Establish the irrigation area sluice feature data set B = {b1, b2, ..., b i ,…,b k }, where b i represents the sluice characteristic data corresponding to the i-th farmland irrigation area, k represents the total number of farmland irrigation areas, and the sluice characteristic data includes sluice location data and sluice number data; S13. Use a bidirectional search algorithm to traverse all the irrigation area sluice feature data in the irrigation area sluice feature data set, search for the irrigation area sluice feature data that matches A, and use the sluice corresponding to the irrigation area sluice feature data that matches A as the target sluice.

3. The energy consumption intelligent control method according to claim 2 is characterized in that: The S21 comprises the following steps: S21. Obtain the demand for the current farmland irrigation operation online through the farmland irrigation demand selection interface, generate farmland irrigation demand data, and if the farmland irrigation demand data is urgent, set the target sluice opening height h as the maximum sluice opening height h. max If the farmland irrigation demand data is not urgent, the optimal sluice opening height h is set by the Snow Goose Optimization Algorithm best , and set the target sluice opening height h as the optimal sluice opening height h best ; The maximum sluice gate opening height represents the maximum lifting height of the target sluice gate; S22. Control the target sluice gate to perform sluice gate opening operation through the sluice gate energy consumption control platform, and adjust the lifting height of the target sluice gate to the set target sluice gate opening height h.

4. The energy consumption intelligent control method according to claim 3 is characterized in that: Setting the optimal sluice opening height by the Snow Goose optimization algorithm in S21 includes the following steps: S211. Construct a sluice gate opening height to search for snow goose populations, set the population size to N, the current number of iterations to t, and the maximum number of iterations to t max And the dimension of the search space for the optimal sluice opening height is P; Set the interval (0,h max ) is an optimal sluice opening height search space, N sluice opening heights are randomly generated in the optimal sluice opening height search space, and each sluice opening height corresponds to a sluice opening height search snow goose individual; S212, calculating the fitness values ​​of the snow goose individuals searched at each sluice gate opening height, sorting the snow goose individuals searched at each sluice gate opening height from large to small according to the fitness values, and taking the snow goose individual searched at the sluice gate opening height with the largest fitness value as the current optimal individual; S213, if the angle between the opening heights of each sluice gate and the snow goose individuals performing migration behavior is greater than π, then enter S214; if the angle between the opening heights of each sluice gate and the snow goose individuals performing migration behavior in the snow goose population is less than or equal to π, then enter S215; S214, updating the speed of searching for individual snow geese at each sluice gate opening height; Each snow goose individual searching for the sluice gate opening height adopts a herringbone flight strategy to update its position in the optimal sluice gate opening height search space according to the updated speed, and enters S216 after the position is updated; S215, each sluice gate opening height searches for snow geese individuals in the optimal sluice gate opening height search space using a straight-line flight strategy to update their positions, and enter S216 after the positions are updated; S216, calculating the fitness value of each sluice gate opening height search snow goose individual after the position is updated, if the fitness value of the sluice gate opening height search snow goose individual after the position is updated is greater than the original fitness value, then the new position of the sluice gate opening height search snow goose individual is used to replace the original position; otherwise, the original position of the sluice gate opening height search snow goose individual is retained; Re-sort the snow goose individuals at each sluice opening height according to their fitness values ​​from large to small, and take the snow goose individual at the sluice opening height with the largest fitness value as the new current optimal individual; S217, determine whether t is less than t max , if t is less than t max , then t is increased by 1, and the process returns to S213; otherwise, the current optimal individual is taken as the global optimal solution, and the sluice opening height corresponding to the global optimal solution is output as the optimal sluice opening height h best .

5. The energy consumption intelligent control method according to claim 4 is characterized in that: The S3 comprises the following steps: S31, collect the characteristic data of the historical farmland irrigation operation through the sluice energy consumption control platform, and generate the historical farmland irrigation operation characteristic data set C = {c1, c2, ..., c i ,…,c l }, where c i represents the characteristic data when the i-th historical farmland irrigation operation is executed, l represents the total number of historical farmland irrigation operations collected, and the characteristic data represents the characteristic data of the farmland irrigation area when the historical farmland irrigation operation is executed and the corresponding sluice water discharge data, and the farmland irrigation area characteristic data includes but is not limited to farmland irrigation area area data, farmland irrigation area weather data, farmland irrigation area soil type data and farmland irrigation area crop type data.

6. The energy consumption intelligent control method according to claim 5, characterized in that: The S4 comprises the following steps: S41, setting a training data ratio and a test data ratio, dividing the historical farmland irrigation operation feature data set according to the training data ratio and the test data ratio to obtain a historical farmland irrigation operation feature training data set and a historical farmland irrigation operation feature test data set; S42, build the initial SVM model and set the penalty factor to And the radial basis kernel parameter is θ, and the kernel function of the initial SVM model is set to the Sigmoid radial basis kernel function; the formula of the Sigmoid radial basis kernel function is as follows: Among them, q(x,y) represents the Sigmoid radial basis kernel function, x and y represent the feature vectors of the two inputs, Indicates the offset, x T represents the transpose of vector x; S43, setting a training error threshold and a maximum number of training times, inputting the historical farmland irrigation operation feature training data set into the initial SVM model for training until the training error is less than the training error threshold or the number of training times is greater than the maximum number of training times, thereby obtaining a trained SVM model; S44. Set an accuracy threshold, input the historical farmland irrigation operation characteristic test data set into the trained SVM model for testing and calculate the accuracy of the test results. If the accuracy of the test results is greater than or equal to the accuracy threshold, an irrigation water volume prediction model is obtained; otherwise, the SVM model parameters are adjusted through a grid search algorithm until the accuracy of the test results is greater than or equal to the accuracy threshold.

7. The energy consumption intelligent control method according to claim 6, characterized in that: The S5 comprises the following steps: S51, collecting characteristic data of the target farmland irrigation area online through the sluice energy consumption control platform, generating characteristic data C of the target farmland irrigation area shishi , the target farmland irrigation area characteristic data includes but is not limited to target farmland irrigation area area data, target farmland irrigation area weather data, target farmland irrigation area soil type data and target farmland irrigation area crop type data; S52, the C shishi Input the irrigation water volume prediction model to predict the target farmland irrigation water volume, and output the target farmland irrigation prediction water volume data D yuce .

8. The energy consumption intelligent control method according to claim 7, characterized in that: The S6 comprises the following steps: S61, collecting the water output of the target sluice in real time by means of a flow sensor installed on the target sluice, and generating real-time water output data D of the target sluice shishi , through the Internet of Things communication network, the D shishi Push to the sluice energy consumption control platform; S62, through the sluice energy consumption control platform, the D shishi and the D yuce Performing numerical comparison, and generating sluice gate closing operation execution instruction data E according to the numerical comparison result; If the D shishi Smaller than D yuce , it means that the real-time water output of the sluice gate does not meet the irrigation water demand of the target farmland, and the output E is not closed. The real-time water output of the target sluice gate is continuously collected by the flow sensor installed on the target sluice gate until the D shishi Greater than or equal to the D yuce ; If the D shishi Greater than or equal to the D yuce , it means that the real-time water discharge of the sluice has met the target farmland irrigation water demand, and the output E is closed. The E is pushed to the sluice energy consumption control platform through the Internet of Things communication network. After receiving the E, the sluice energy consumption control platform executes the sluice closing operation.

9. A system for implementing the energy consumption intelligent control method according to any one of claims 1 to 8, characterized in that: It includes a target sluice locking module, a sluice opening operation execution module, a historical farmland irrigation operation characteristic data collection module, an irrigation water volume prediction model construction module, a target farmland irrigation water volume prediction module, and a sluice closing operation execution module.

10. Application of the intelligent energy consumption control method according to any one of claims 1 to 8 in energy consumption control of a sluice.

Images