Intelligent digital variable frequency three-effect unit energy consumption management method and system

Abstract

The application provides a kind of intelligent digital frequency conversion three-effect unit energy consumption management method and system, related to energy consumption management technical field, the method includes: obtaining the efficient, medium and low efficient demand information of current user;Obtain the historical efficient, medium and low efficient energy supply parameters in the history time of user, distribute and obtain efficient, medium and low efficient weight;Randomly configure the frequency conversion parameter of three-effect unit variable frequency control, configure energy efficiency control prediction resource, carry out three-effect control prediction, obtain efficient, medium and low efficient control parameter;According to efficient, medium and low efficient weight, and efficient, medium and low efficient demand information, the control deviation of efficient, medium and low efficient control parameter is weighted calculation, process obtains frequency conversion adaptive parameter, and iteration optimization obtains optimal frequency conversion parameter, carries out variable frequency energy consumption management.The technical problem that frequency conversion three-effect unit cannot dynamically adjust frequency conversion parameter according to the demand of user in prior art, and then influence the technical problem of frequency conversion control effect.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of energy consumption management, and in particular to an intelligent digital variable frequency three-effect unit energy consumption management method and system. BACKGROUND

[0002] The variable frequency three-effect unit is a high-efficiency energy-saving device that combines energy cascade utilization and variable frequency speed regulation technology. The core is to realize the maximum utilization of energy through the coordinated operation and dynamic adjustment of three-effect efficiency. The variable frequency three-effect unit can be divided into high-efficiency, medium-efficiency, and low-efficiency levels according to temperature. Specifically, high-efficiency (first effect): using high-temperature energy to complete core functions such as refrigeration; medium-efficiency (second effect): recovering the remaining medium-temperature energy from the high-efficiency link to meet secondary demand, such as preheating domestic water to 45℃ through a secondary heat exchanger; low-efficiency (third effect): recovering the remaining low-temperature energy from the medium-efficiency link to achieve ultimate waste heat recovery to meet the minimum demand, such as using the last remaining low-temperature heat for pool heating or greenhouse insulation. In this way, the energy waste of traditional single-effect or double-effect energy supply is broken, and the cascade utilization logic of high-temperature high-use and low-temperature low-use is realized through three levels in series, achieving the maximum utilization of energy.

[0003] However, the traditional control method usually uses fixed parameters to manage the variable frequency three-effect unit, without considering the user's demand for energy distribution, and cannot dynamically adjust the variable frequency parameters according to the user's demand for energy distribution. For example, when the user focuses on high-efficiency refrigeration at a certain time, the energy is still allocated according to the preset proportion, which may cause temperature fluctuations due to insufficient resource supply, thereby affecting the variable frequency control effect. SUMMARY

[0004] The present application provides an intelligent digital variable frequency three-effect unit energy consumption management method and system to solve the technical problem that the variable frequency three-effect unit cannot dynamically adjust the variable frequency parameters according to the user's demand for energy distribution, thereby affecting the variable frequency control effect.

[0005] The technical solution of the present application to solve the above technical problem is as follows:

[0006] In a first aspect, the present application provides an intelligent digital variable frequency three-effect unit energy consumption management method, comprising:

[0007] obtaining high-efficiency demand information, medium-efficiency demand information, and low-efficiency demand information of a current user;

[0008] obtaining historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters, and historical low-efficiency energy supply parameters within a historical time of the user, and obtaining high-efficiency weights, medium-efficiency weights, and low-efficiency weights, wherein each energy supply parameter includes a stable energy supply time;

[0009] Randomly configure the variable frequency parameters for variable frequency control of the three-effect unit, configure energy efficiency control prediction resources according to the historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters, perform three-effect control prediction, and obtain high-efficiency control parameters, medium-efficiency control parameters and low-efficiency control parameters;

[0010] According to the high-efficiency weight, medium-efficiency weight and low-efficiency weight, and high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information, the control deviation of the high-efficiency control parameters, medium-efficiency control parameters and low-efficiency control parameters is weighted and calculated, the variable frequency adaptive parameters are processed and obtained, the optimal variable frequency parameters are iteratively optimized and obtained, and variable frequency energy consumption management is performed.

[0011] In a second aspect, the present application provides an intelligent digital variable frequency three-effect unit energy consumption management system, comprising:

[0012] A data acquisition module is configured to obtain high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information of a current user;

[0013] A weight allocation module is configured to obtain historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters of a user in a historical time, and allocate high-efficiency weight, medium-efficiency weight and low-efficiency weight, wherein each energy supply parameter comprises a stable energy supply time.

[0014] A parameter configuration module is configured to randomly configure variable frequency parameters for variable frequency control of the three-effect unit, configure energy efficiency control prediction resources according to the historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters, perform three-effect control prediction, and obtain high-efficiency control parameters, medium-efficiency control parameters and low-efficiency control parameters.

[0015] An optimization output module is configured to perform weighted calculation on the control deviation of the high-efficiency control parameters, medium-efficiency control parameters and low-efficiency control parameters according to the high-efficiency weight, medium-efficiency weight and low-efficiency weight, and high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information, process and obtain variable frequency adaptive parameters, iteratively optimize and obtain optimal variable frequency parameters, and perform variable frequency energy consumption management.

[0016] The present application has the following beneficial effects:

[0017] Compared with the prior art, the application first acquires high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information of the current user, acquires the three-efficiency demand information of the user, converts the energy demand of the user into quantifiable and executable technical indicators, and provides a necessary data basis for subsequent weight allocation, prediction control, parameter optimization and the like. Secondly, historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters in a historical time of the user are acquired, and high-efficiency weight, medium-efficiency weight and low-efficiency weight are allocated, wherein each energy supply parameter comprises stable energy supply time. By acquiring the historical high-efficiency energy supply parameters, the historical medium-efficiency energy supply parameters and the historical low-efficiency energy supply parameters in the historical time of the user, the dependence degree of the user on the three levels of energy efficiency is quantified, and weight allocation is performed accordingly, solving the defect that the traditional fixed weight cannot adapt to the dynamic demand of the user. Thirdly, variable frequency parameters for variable frequency control of the three-effect unit are randomly configured, the energy efficiency control prediction resources are configured according to the historical high-efficiency energy supply parameters, the historical medium-efficiency energy supply parameters and the historical low-efficiency energy supply parameters, the three-effect control prediction is performed, the high-efficiency control parameters, the medium-efficiency control parameters and the low-efficiency control parameters are acquired, the energy efficiency control prediction resources are allocated according to the historical stable energy supply condition, the three-effect control prediction is performed by the variable frequency three-effect controller, and a necessary data basis is provided for subsequent iteration optimization of the variable frequency parameters. Finally, the control bias of the high-efficiency control parameters, the medium-efficiency control parameters and the low-efficiency control parameters is weighted and calculated according to the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, the variable frequency adaptive parameters are obtained by processing, and the optimal variable frequency parameters are obtained by iteration optimization, variable frequency energy consumption management is performed, the split-efficiency demand of the user, the historical data and the real-time control parameters are considered, the variable frequency adaptive parameters are calculated and generated, then the optimal variable frequency parameters are searched by using the random iteration optimization strategy based on the variable frequency adaptive parameters, the optimal variable frequency parameters can make the energy consumption control stability best on the premise of meeting the split-efficiency demand of the user, and then the variable frequency control effect is improved.

[0018] Through the above technical solution, the application fully considers the three-effect demand information of the user, performs three-effect control prediction on different variable frequency parameter combinations by means of the variable frequency three-effect controller cluster, then generates variable frequency adaptive parameters based on the split-efficiency demand of the user, the historical stable energy supply data and the real-time control parameter bias, searches the global optimal variable frequency parameters dynamically based on the variable frequency adaptive parameters by using the random iteration optimization strategy, and finally applies the optimal variable frequency parameters to the variable frequency energy consumption management. In this way, the split-efficiency demand of the user is accurately matched, and the variable frequency control effect is improved by iteration optimization of the variable frequency parameters. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 A flowchart of an intelligent digital variable frequency three-effect unit energy consumption management method provided by the application;

[0020] Figure 2 A structure schematic diagram of an intelligent digital variable frequency three-effect unit energy consumption management system provided by the present application.

[0021] In the drawings, the components represented by the respective reference numerals are as follows:

[0022] The data acquisition module 11, the weight distribution module 12, the parameter configuration module 13, and the optimization output module 14. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0024] In the description of the present application, the terms "first", "second" are used only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "multiple" is two or more, unless otherwise specifically limited.

[0025] In the description of the present application, the term "for example" is used to indicate "as an example, illustration or explanation". Any embodiment described as "for example" in the present application is not necessarily interpreted as more preferred or more advantageous than other embodiments. The following description is given in order to enable any person skilled in the art to implement and use the present application. In the following description, details are listed for the purpose of explanation. It should be understood that those skilled in the art can realize the present application without using these specific details. In other examples, well-known structures and processes will not be described in detail in order to avoid unnecessary details making the description of the present application obscure. Therefore, the present application is not intended to be limited to the shown embodiments, but is consistent with the broadest scope in accordance with the principles and characteristics disclosed.

[0026] Embodiment one, as shown in the present application, provides an intelligent digital variable frequency three-effect unit energy consumption management method, comprising: Figure 1

[0027] S10: obtaining high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information of the current user;

[0028] ​The variable frequency three-effect unit is a high-efficiency energy-saving equipment combining energy cascade utilization and variable frequency speed regulation technology. The core of the variable frequency three-effect unit is to realize the maximum utilization of energy through the synergistic operation and dynamic adjustment of three-effect units. The variable frequency three-effect unit can be divided into three levels of high efficiency, medium efficiency and low efficiency according to temperature. Specifically, high efficiency (first effect): using high-temperature energy to complete core functions such as refrigeration; medium efficiency (second effect): recovering the remaining medium-temperature energy in the high-efficiency link to meet secondary demand, such as preheating domestic water to 45℃ through a secondary heat exchanger; low efficiency (third effect): recovering the remaining low-temperature energy in the medium-efficiency link to achieve ultimate recovery of waste heat to meet the minimum demand, such as using the last remaining low-temperature heat for pool heating or greenhouse insulation.

[0029] Further, the conventional control method usually uses fixed parameters to manage the variable frequency three-effect unit, without considering the user's demand for three-effect units, and cannot dynamically adjust the priority according to the user's demand for three-effect units.

[0030] To solve the above problems, the present application obtains high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information of the current user.

[0031] Specifically, step S10 in the method comprises:

[0032] Obtaining the high-efficiency demand temperature, medium-efficiency demand temperature and low-efficiency demand temperature of the current user;

[0033] The high-efficiency demand temperature, medium-efficiency demand temperature and low-efficiency demand temperature are used as high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information.

[0034] In the embodiment of the present application, the high-efficiency demand temperature, medium-efficiency demand temperature and low-efficiency demand temperature of the current user are obtained first. Specifically, the high-efficiency demand temperature is the target temperature of the first effect using high-temperature energy to complete core functions, the medium-efficiency demand temperature is the target temperature of the second effect recovering the first-effect waste heat for secondary demand, and the low-efficiency demand temperature is the target temperature of the third effect recovering the remaining low-temperature energy of the second effect for meeting the minimum requirement. For example, the user can directly input personalized three-effect demand temperatures through a touch screen, APP or central control system, etc., for example, the high-efficiency demand temperature is 100℃, the medium-efficiency demand temperature is 60℃ (such as for domestic water preheating), and the low-efficiency demand temperature is 25℃.

[0035] Secondly, the high-efficiency demand temperature, the medium-efficiency demand temperature and the low-efficiency demand temperature are taken as high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information. For example, the high-efficiency demand temperature, the medium-efficiency demand temperature and the low-efficiency demand temperature of the current user reflect the demand temperatures of the user for the three efficiencies, and therefore, the high-efficiency demand temperature, the medium-efficiency demand temperature and the low-efficiency demand temperature can be taken as the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information of the user, for example, the high-efficiency demand temperature, the medium-efficiency demand temperature and the low-efficiency demand temperature of 100 ℃, 60 ℃ and 25 ℃ are taken as the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, respectively.

[0036] In summary, compared with the prior art, the application obtains the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information of the current user. In this way, the three-efficiency demand information of the user is obtained, and the energy demand of the user is converted into quantifiable and executable technical indexes, thereby providing a necessary data basis for subsequent weight allocation, prediction control, parameter optimization and the like.

[0037] S20: obtaining historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters of the user in a historical time, and obtaining high-efficiency weights, medium-efficiency weights and low-efficiency weights, wherein each energy supply parameter comprises a stable energy supply time;

[0038] The demand of the user for the three efficiencies can have significant dynamic differences. For example, the user can have a significantly increased demand for high-efficiency energy supply (such as refrigeration) during the day in summer, and can rely more on medium-efficiency preheating (such as preheating of domestic water) or low-efficiency heating (such as pool insulation) at night. Therefore, the conventional fixed-parameter split-efficiency control mode is difficult to adapt to such dynamically changing demand priorities, thereby leading to problems such as insufficient guarantee of core functions or low efficiency of waste heat recovery.

[0039] In view of the above problems, the application obtains historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters of the user in a historical time, and obtains high-efficiency weights, medium-efficiency weights and low-efficiency weights, wherein each energy supply parameter comprises a stable energy supply time.

[0040] Specifically, step S20 in the method comprises:

[0041] obtaining cumulative high-efficiency energy supply time of the user for stable high-efficiency energy supply in a recent historical time as a historical high-efficiency energy supply parameter, wherein the stable high-efficiency energy supply comprises a high-efficiency energy supply temperature fluctuation range that does not exceed a preset high-efficiency temperature fluctuation threshold;

[0042] obtaining cumulative medium-efficiency energy supply time and cumulative low-efficiency energy supply time of the user for stable medium-efficiency energy supply and stable low-efficiency energy supply in the recent historical time as historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters;

[0043] According to the time length of the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter, the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight are allocated and obtained.

[0044] In the embodiment of the application, firstly, the cumulative high-efficiency energy supply time of the user in the recent historical time is obtained as the historical high-efficiency energy supply parameter, wherein the stable high-efficiency energy supply includes that the high-efficiency energy supply temperature fluctuation range does not exceed the preset high-efficiency temperature fluctuation threshold. Specifically, the recent historical time is selected as a time window, and in the time window, the cumulative time of stable high-efficiency energy supply, in which the actual temperature fluctuation range of high-efficiency energy supply is less than or equal to the preset high-efficiency temperature fluctuation threshold, is counted as the historical high-efficiency energy supply parameter. The recent historical time can be determined according to specific climate, location and other factors, for example, the recent historical time is determined as the recent 7 days to improve the timeliness of data, or the recent historical time is determined as the recent 30 days to filter accidental fluctuations and capture the user's normal energy use mode. Those skilled in the art can dynamically adjust according to the actual situation. Further, the preset high-efficiency temperature fluctuation threshold is a preset high-efficiency temperature fluctuation range. The smaller the preset high-efficiency temperature fluctuation threshold is, the higher the stability requirement of the high-efficiency function is. Since the high-efficiency function is the core function, the preset high-efficiency temperature fluctuation threshold should be set smaller, for example, it is set to ±0.5℃. Those skilled in the art can dynamically set it according to the actual situation. For example, according to the actual situation, the recent historical time is determined as the recent 7 days, and the preset high-efficiency temperature fluctuation threshold is 100℃±0.5℃. Then, the recent 7 days are taken as the time window, and all the cumulative high-efficiency energy supply time in the recent 7 days, in which the actual temperature fluctuation range of high-efficiency energy supply does not exceed 100℃±0.5℃, such as 100 hours, is collected from the device historical operation data, and is taken as the historical high-efficiency energy supply parameter. The historical high-efficiency energy supply parameter reflects the demand degree of the user for high-efficiency energy supply. The larger the historical high-efficiency energy supply parameter is, the greater the demand degree of the user for high-efficiency energy supply is.

[0045] Secondly, the cumulative efficient supply energy time and the cumulative inefficient supply energy time of the user in the recent history time for stable efficient supply energy and stable inefficient supply energy are obtained as the historical efficient supply energy parameter and the historical inefficient supply energy parameter. Specifically, the foregoing recent history time is taken as a time window, the cumulative time of stable efficient supply energy with an actual temperature fluctuation range less than or equal to a preset efficient temperature fluctuation threshold in the time window and the cumulative time of stable inefficient supply energy with an actual temperature fluctuation range less than or equal to a preset inefficient temperature fluctuation threshold in the time window are collected as the historical efficient supply energy parameter and the historical inefficient supply energy parameter, wherein, compared with the preset high efficient temperature fluctuation threshold, the preset efficient temperature fluctuation threshold and the preset inefficient temperature fluctuation threshold can be set larger because they are not the core of energy supply. For example, the preset efficient temperature fluctuation threshold is set to ±1℃ and the preset inefficient temperature fluctuation threshold is set to ±3℃, and the person skilled in the art can dynamically set them according to the actual situation. Exemplarily, the recent history time is determined as the recent 7 days according to the actual situation, the preset efficient temperature fluctuation threshold is 60℃±1℃ and the preset inefficient temperature fluctuation threshold is 25±3℃, then the recent 7 days are taken as the time window, and the total cumulative efficient and inefficient supply energy time of the efficient supply energy and the inefficient supply energy in the recent 7 days with an actual temperature fluctuation range not more than 60℃±1℃ and 25±3℃, such as 60 hours and 40 hours, are collected from the device history operation data as the historical efficient supply energy parameter and the historical inefficient supply energy parameter. The historical efficient supply energy parameter can reflect the demand degree of the user for efficient supply energy, and the greater the historical efficient supply energy parameter, the greater the demand degree of the user for efficient supply energy. The historical inefficient supply energy parameter can reflect the demand degree of the user for inefficient supply energy, and the greater the historical inefficient supply energy parameter, the greater the demand degree of the user for inefficient supply energy.

[0046] Finally, according to the time length of the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter, a high-efficiency weight, a medium-efficiency weight and a low-efficiency weight are allocated, wherein the high-efficiency weight = the historical high-efficiency energy supply parameter / (the historical high-efficiency energy supply parameter + the historical medium-efficiency energy supply parameter + the historical low-efficiency energy supply parameter), the medium-efficiency weight = the historical medium-efficiency energy supply parameter / (the historical high-efficiency energy supply parameter + the historical medium-efficiency energy supply parameter + the historical low-efficiency energy supply parameter), and the low-efficiency weight = the historical low-efficiency energy supply parameter / (the historical high-efficiency energy supply parameter + the historical medium-efficiency energy supply parameter + the historical low-efficiency energy supply parameter). The high-efficiency weight, the medium-efficiency weight and the low-efficiency weight are the cumulative energy supply time proportions of the user in the recent historical time for stable high-efficiency, medium-efficiency and low-efficiency energy supply. The greater the time proportion, the more the user depends on the function, and the higher the weight. For example, when the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter are 100 hours, 60 hours and 40 hours respectively, the high-efficiency weight = 100 / (100 + 60 + 40) = 0.5, the medium-efficiency weight = 60 / (100 + 60 + 40) = 0.3, and the low-efficiency weight = 40 / (100 + 60 + 40) = 0.2. Among them, the high-efficiency weight is the largest, indicating that the user depends more on high-efficiency energy supply.

[0047] In summary, compared with the prior art, the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter of the user in the historical time are obtained, and the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight are allocated, wherein each energy supply parameter includes stable energy supply time. In this way, by collecting the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter of the user in the historical time, the dependence degree of the user on the three levels of energy efficiency is quantified, and the weight is allocated accordingly, solving the defect that the traditional fixed weight cannot adapt to the dynamic needs of the user.

[0048] S30: randomly configuring a variable frequency parameter for variable frequency control of the three-effect unit, configuring an energy efficiency control prediction resource according to the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter, performing three-effect control prediction to obtain high-efficiency control parameters, medium-efficiency control parameters and low-efficiency control parameters;

[0049] Different variable frequency parameters, such as compressor frequency and water pump speed, will directly affect the energy supply performance of the three-effect unit, so the control effect of different variable frequency parameters can be predicted, and the optimal variable frequency parameter is quickly determined under the premise of ensuring to meet the three-effect needs of the user.

[0050] To solve the above problems, the application randomly configures a variable frequency parameter for variable frequency control of the three-effect unit, configures an energy efficiency control prediction resource according to the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter, performs three-effect control prediction to obtain high-efficiency control parameters, medium-efficiency control parameters and low-efficiency control parameters.

[0051] Specifically, step S30 in the method comprises:

[0052] randomly configuring a variable frequency parameter for variable frequency control of the three-effect unit;

[0053] calculating the average of the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter to obtain an average stable energy supply time;

[0054] calculating the ratio of the average stable energy supply time to the maximum stable energy supply time to obtain an energy efficiency control prediction resource coefficient;

[0055] obtaining a variable frequency three-effect controller cluster and randomly selecting a variable frequency three-effect controller with a proportion of the energy efficiency control prediction resource coefficient;

[0056] inputting the variable frequency parameter into the randomly selected multiple variable frequency three-effect controllers, calculating the average of three-effect control prediction output results to obtain a high-efficiency control parameter, a medium-efficiency control parameter and a low-efficiency control parameter.

[0057] In the embodiments of the present application, first, a variable frequency parameter for variable frequency control of the three-effect unit is randomly configured. For example, an initial variable frequency parameter of the three-effect unit is randomly generated, such as a compressor frequency of 30-60 Hz and a water pump rotating speed of 1000-2000 rpm.

[0058] Secondly, the average of the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter is calculated to obtain an average stable energy supply time, wherein the average stable energy supply time=(historical high-efficiency energy supply parameter+historical medium-efficiency energy supply parameter+historical low-efficiency energy supply parameter) / 3. For example, when the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter are 100 hours, 60 hours and 40 hours respectively, the average stable energy supply time=(100+60+40) / 3=66.67 hours, which reflects the overall stability of the three-effect energy supply operation in the recent historical time. The greater the average stable energy supply time, the better the overall stability.

[0059] Again, a ratio of the average stable energy supply time and the maximum stable energy supply time is calculated to obtain an energy efficiency control prediction resource coefficient, wherein the energy efficiency control prediction resource coefficient = average stable energy supply time / maximum stable energy supply time, and the maximum stable energy supply time is the maximum value of the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter, and the historical low-efficiency energy supply parameter. For example, when the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter, and the historical low-efficiency energy supply parameter are 100 hours, 60 hours, and 40 hours, respectively, and the average stable energy supply time is 66.67 hours, the maximum stable energy supply time is the historical high-efficiency energy supply parameter 100 hours, and the energy efficiency control prediction resource coefficient = 66.67 / 100 = 0.6667. The larger the energy efficiency control prediction resource coefficient, the smaller the difference between the historical stable energy supply times of high efficiency, medium efficiency, and low efficiency, and the more stable the overall operation. Conversely, if the energy efficiency control prediction resource coefficient is small, it means that the energy supply time of a certain efficiency dominates, and the overall stability is poor.

[0060] Further, a variable frequency three-effect controller cluster is obtained, and a variable frequency three-effect controller with a proportion of the energy efficiency control prediction resource coefficient is randomly selected, wherein the number of variable frequency three-effect controllers randomly selected from the variable frequency three-effect controller cluster = [energy efficiency control prediction resource coefficient * total number of variable frequency three-effect controllers], and [] is the ceiling function. For example, the total number of variable frequency three-effect controllers in the variable frequency three-effect controller cluster is 10, and the energy efficiency control prediction resource coefficient is 0.6667. Therefore, the number of variable frequency three-effect controllers that should be randomly selected at this time = [0.6667 * 10] = 7, that is, 7 variable frequency three-effect controllers need to be randomly selected from the variable frequency three-effect controller cluster. This is because the larger the energy efficiency control prediction resource coefficient, the smaller the difference between the historical stable energy supply times of the three effects, that is, the three-effect unit needs to handle concurrent demands of multiple efficiency segments at the same time. For example, when the energy efficiency control prediction resource coefficient is 0.9, the three-effect unit may alternately perform high-efficiency refrigeration, medium-efficiency constant temperature, and low-efficiency standby control within 1 hour, and the variable frequency parameters of each control method are different. Therefore, more variable frequency three-effect controllers need to be called for prediction to improve prediction accuracy. Conversely, if the energy efficiency control prediction resource coefficient is low, it means that the energy supply time of a certain efficiency dominates, and the variable frequency parameter adjustment is relatively simple. Therefore, the number of variable frequency three-effect controllers can be appropriately reduced to improve efficiency and reduce unnecessary resource waste. In this way, the number of variable frequency three-effect controllers called by the energy efficiency control prediction resource coefficient is dynamically adjusted, balancing prediction accuracy and unnecessary resource waste.

[0061] Finally, the variable frequency parameters are input into a plurality of variable frequency three-effect controllers selected at random, the average of the three-effect control prediction output results is calculated, and the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter are obtained. By calculating the average of the output results of a plurality of controllers, random errors can be effectively reduced, and the prediction accuracy can be improved. For example, randomly configured variable frequency parameters, such as compressor frequency 30-60 Hz and water pump speed 1000-2000 rpm, are input into 7 variable frequency three-effect controllers selected at random, the three-effect control prediction output results are respectively predicted and output, and then the average of the three-effect control prediction output results is calculated. For example, by predicting and calculating the average of the output results of 7 variable frequency three-effect controllers, the high-efficiency control parameter is 99.8℃, the medium-efficiency control parameter is 59.6℃, and the low-efficiency control parameter is 25.3℃.

[0062] Further, the "acquiring a variable frequency three-effect controller cluster" comprises:

[0063] According to the three-effect unit control data in the historical time, a sample variable frequency parameter set is collected, and a sample high-efficiency control parameter set, a sample medium-efficiency control parameter set and a sample low-efficiency control parameter set under different sample variable frequency parameters are collected;

[0064] The data in a plurality of groups of a preset number in the sample variable frequency parameter set, the sample high-efficiency control parameter set, the sample medium-efficiency control parameter set and the sample low-efficiency control parameter set is randomly divided, and a first variable frequency three-effect controller is trained.

[0065] Continue to train a plurality of variable frequency three-effect controllers, and obtain a variable frequency three-effect controller cluster.

[0066] In the embodiments of the present application, first, according to the three-effect unit control data in the historical time, the sample variable frequency parameter set is collected, and the sample high-efficiency control parameter set, the sample medium-efficiency control parameter set and the sample low-efficiency control parameter set under the control of different sample variable frequency parameters are collected. Specifically, in the historical time, different variable frequency parameters such as different frequencies, voltages and currents are collected as the sample variable frequency parameter set, and the high-efficiency energy supply temperature, the medium-efficiency energy supply temperature and the low-efficiency energy supply temperature under the control of different sample variable frequency parameters are collected as the sample high-efficiency control parameter set, the sample medium-efficiency control parameter set and the sample low-efficiency control parameter set. For example, different variable frequency parameters and their corresponding high-efficiency energy supply temperature, medium-efficiency energy supply temperature and low-efficiency energy supply temperature are collected, such as when the frequency is 30 Hz and the water pump speed is 1000 rpm, the high-efficiency energy supply temperature is 99 ℃, the medium-efficiency energy supply temperature is 59.5 ℃, and the low-efficiency energy supply temperature is 25.1 ℃; when the frequency is 35 Hz and the water pump speed is 1050 rpm, the high-efficiency energy supply temperature is 99.6 ℃, the medium-efficiency energy supply temperature is 59.8 ℃, and the low-efficiency energy supply temperature is 25.6 ℃; when the frequency is 40 Hz and the water pump speed is 1100 rpm, the high-efficiency energy supply temperature is 100.1 ℃, the medium-efficiency energy supply temperature is 60.2 ℃, and the low-efficiency energy supply temperature is 25.3 ℃, etc., to obtain the sample variable frequency parameter set, the sample high-efficiency control parameter set, the sample medium-efficiency control parameter set and the sample low-efficiency control parameter set.

[0067] Secondly, the data in the sample variable frequency parameter set, the sample high-efficiency control parameter set, the sample medium-efficiency control parameter set and the sample low-efficiency control parameter set is randomly divided into a preset number of groups, and a first variable frequency three-effect controller is trained. For example, the first variable frequency three-effect controller can adopt a machine learning or deep learning model such as a neural network, a random forest, a gradient boosting tree, etc., learn the mapping relationship between the variable frequency parameters and the three-effect control parameters, input the variable frequency parameters, and predict the three-effect control prediction output results. For example, the first variable frequency three-effect controller can be constructed by a neural network, which can adopt a hybrid architecture combining long short-term memory (LSTM) and multi-layer perceptron (MLP). The input layer receives the variable frequency parameters, which are input into a 64-unit LSTM layer after standardization. The hyperbolic tangent activation function is used to capture the time inertia of temperature changes. The attention mechanism is introduced in the middle layer to automatically weight the key historical data (such as abnormal fluctuation time), and two fully connected layers (128 / 64 units, LeakyReLU activation) are combined to realize nonlinear transformation, effectively fitting the mapping relationship between the variable frequency parameters and the three-effect control parameters (R 2 ≥0.95), and the output layer adopts an independent head structure to output high-efficiency, medium-efficiency and low-efficiency control parameters respectively.

[0068] Exemplarily, the training process of the first variable frequency three-effect controller can be implemented through the following technical path: 1. Data preparation: the sample variable frequency parameter set, the sample high-efficiency control parameter set, the sample medium-efficiency control parameter set and the sample low-efficiency control parameter set can be randomly divided into a training set, a validation set and a test set in a ratio of 7:1.5:1.5. 2. Model training: the divided training set data is input into the model, and the model parameters such as the weights and biases of the neural network are adjusted through iterative calculation to minimize the error between the three-effect control parameters output by the model and the actual sample data. The optimization objective function can select mean square error (MSE) or mean absolute error (MAE) to optimize the prediction accuracy of the three-effect control parameters. The stable energy supply demand can also be used as a regularization constraint to avoid overfitting of the model to non-stable working condition data. Finally, when the prediction error is ≤±1℃ and the prediction accuracy on the test set is more than 95%, it is considered to be converged, and the first variable frequency three-effect controller is obtained.

[0069] Finally, continue to train multiple variable frequency three-effect controllers to obtain a variable frequency three-effect controller cluster. Specifically, according to the same construction and training process of the first variable frequency three-effect controller, continue to train multiple variable frequency three-effect controllers, combine multiple variable frequency three-effect controllers, and obtain a variable frequency three-effect controller cluster.

[0070] In summary, compared with the prior art, the present application randomly configures variable frequency parameters for variable frequency control of the three-effect unit, configures energy efficiency control prediction resources according to the historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters, performs three-effect control prediction, and obtains high-efficiency control parameters, medium-efficiency control parameters and low-efficiency control parameters. In this way, according to the historical stable energy supply situation, the energy efficiency control prediction resources are allocated, the three-effect control prediction is performed through the variable frequency three-effect controller, and the necessary data basis is provided for subsequent variable frequency parameter iterative optimization.

[0071] S40: According to the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, the control bias of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter is weighted and calculated, the variable frequency adaptive parameter is obtained, and the optimal variable frequency parameter is obtained through iterative optimization, and variable frequency energy consumption management is performed.

[0072] The foregoing steps obtain the demand information of the user for high-efficiency, medium-efficiency and low-efficiency, and the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter under variable frequency parameter control, so the variable frequency parameter can be scored accordingly, and the variable frequency parameter with the highest score is output through iterative optimization, and variable frequency energy consumption management is performed.

[0073] In view of the above problems, the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information are used to weight and calculate the control deviation of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter, to obtain the variable frequency adaptation parameter through processing, and to obtain the optimal variable frequency parameter through iterative optimization, so as to perform variable frequency energy consumption management.

[0074] Specifically, the step S40 in the method comprises:

[0075] Average high-efficiency energy supply information, average medium-efficiency energy supply information and average low-efficiency energy supply information of the user in the recent history time are obtained;

[0076] Similarities of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information are calculated respectively, and the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight are used to weight and calculate to obtain the variable frequency accurate adaptation parameter;

[0077] Differences of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information are calculated respectively to obtain the high-efficiency control deviation, the medium-efficiency control deviation and the low-efficiency control deviation;

[0078] The fluctuation amplitudes of the high-efficiency control deviation, the medium-efficiency control deviation and the low-efficiency control deviation and the average high-efficiency energy supply information, the average medium-efficiency energy supply information and the average low-efficiency energy supply information are calculated respectively, the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight are used to weight and calculate to obtain the variable frequency deviation fluctuation parameter, and the variable frequency fluctuation adaptation parameter is calculated and obtained;

[0079] The variable frequency adaptation parameter is calculated and obtained according to the variable frequency accurate adaptation parameter and the variable frequency fluctuation adaptation parameter.

[0080] In the embodiment of the application, first, average high-efficiency energy supply information, average medium-efficiency energy supply information and average low-efficiency energy supply information of the user in the recent history time are obtained, wherein the recent history time can be determined comprehensively according to specific climate, location and other factors, for example, it is determined as the last 7 days or the last 10 days, and the actual situation can be adjusted dynamically by the person skilled in the art. For example, according to the historical operation data, the average high-efficiency energy supply temperature, the average medium-efficiency energy supply temperature and the average low-efficiency energy supply temperature of the user in the last 7 days are collected, for example, 99.6℃, 59.5℃ and 25.1℃ are collected and obtained, which are used as the average high-efficiency energy supply information, the average medium-efficiency energy supply information and the average low-efficiency energy supply information.

[0081] Secondly, the similarity of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information is calculated respectively, and the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight are used for weighted calculation to obtain a variable frequency accurate adaptation parameter, wherein the similarity can be obtained by calculating the Euclidean distance, the cosine similarity and the like of the high-efficiency, the medium-efficiency and the low-efficiency control parameter and the demand information, the similarity reflects the deviation degree between the high-efficiency, the medium-efficiency and the low-efficiency control parameter under the current variable frequency parameter control and the user's ideal high-efficiency, medium-efficiency and low-efficiency demand information, and the variable frequency accurate adaptation parameter = high-efficiency weight * high-efficiency similarity + medium-efficiency weight * medium-efficiency similarity + low-efficiency weight * low-efficiency similarity. Exemplarily, under the current variable frequency parameter control, the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter are 99.8℃, 59.6℃ and 25.3℃ respectively, the user's high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information are 100℃, 60℃ and 25℃ respectively, the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight are 0.5, 0.3 and 0.2 respectively, the Euclidean distance of the high-efficiency, the medium-efficiency and the low-efficiency control parameter and the demand information is calculated, for example, |99.8℃-100℃|=0.2, |59.6℃-60℃|=0.4, |25.3℃-25℃|=0.3, which is the similarity of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, then the variable frequency accurate adaptation parameter is calculated by weighted calculation according to the similarity and the weight, for example, the variable frequency accurate adaptation parameter = 0.5*0.2+0.3*0.4+0.2*0.3=0.28, the variable frequency accurate adaptation parameter can reflect the overall matching precision of the user's target demand under the current variable frequency parameter control, and the greater the variable frequency accurate adaptation parameter is, the more optimal the current variable frequency parameter is.

[0082] Again, the difference between the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information is calculated respectively to obtain the high-efficiency control deviation, the medium-efficiency control deviation and the low-efficiency control deviation. For example, under the current variable frequency parameter control, the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter are 99.8℃, 59.6℃ and 25.3℃ respectively, and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information of the user are 100℃, 60℃ and 25℃ respectively, then the high-efficiency control deviation = |99.8℃-100℃| = 0.2, the medium-efficiency control deviation = |59.6℃-60℃| = 0.4, and the low-efficiency demand information = |25.3℃-25℃| = 0.3. These deviations directly reflect the deviation degree of the three-effect temperatures under the current variable frequency parameter control and the target demand temperature of the user, and also represent the control change degree that may be further generated in order to achieve the target demand temperature of the user, i.e. the variable frequency control fluctuation that may be further generated. The greater the deviation, the greater the deviation degree of the three-effect temperatures under the current variable frequency parameter control and the target demand temperature of the user, and the greater the variable frequency control fluctuation that may be further generated in order to achieve the target demand temperature of the user.

[0083] Further, the fluctuation amplitudes of the high-efficiency control deviation, the medium-efficiency control deviation and the low-efficiency control deviation and the average high-efficiency energy supply information, the average medium-efficiency energy supply information and the average low-efficiency energy supply information are calculated respectively, the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight are used for weighted calculation to obtain a variable frequency deviation fluctuation parameter, and a variable frequency fluctuation adaptation parameter is calculated, wherein the high-efficiency fluctuation amplitude = the high-efficiency control deviation / average high-efficiency energy supply information, the medium-efficiency fluctuation amplitude = the medium-efficiency control deviation / average medium-efficiency energy supply information, the low-efficiency fluctuation amplitude = the low-efficiency control deviation / average low-efficiency energy supply information, the variable frequency deviation fluctuation parameter = the high-efficiency weight*high-efficiency fluctuation amplitude + the medium-efficiency weight*medium-efficiency fluctuation amplitude + the low-efficiency weight*low-efficiency fluctuation amplitude, and the variable frequency fluctuation adaptation parameter = 1-variable frequency deviation fluctuation parameter. For example, the high-efficiency control deviation, the medium-efficiency control deviation and the low-efficiency control deviation are 0.2, 0.4 and 0.3 respectively, the average high-efficiency energy supply information, the average medium-efficiency energy supply information and the average low-efficiency energy supply information are 99.6℃, 59.5℃ and 25.1℃ respectively, the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight are 0.5, 0.3 and 0.2 respectively, then the high-efficiency fluctuation amplitude = 0.2 / 99.6 = 0.002, the medium-efficiency fluctuation amplitude = 0.4 / 59.5 = 0.0067, the low-efficiency fluctuation amplitude = 0.3 / 25.1 = 0.012, the variable frequency deviation fluctuation parameter = 0.5*0.002 + 0.3*0.0067 + 0.2*0.012 = 0.0054, and the variable frequency fluctuation adaptation parameter = 1-0.0054 = 0.9946. Thus, the variable frequency fluctuation adaptation parameter can reflect the control fluctuation that may occur in the future to achieve the user target demand temperature, the smaller the variable frequency fluctuation adaptation parameter, the smaller the future control fluctuation, that is, the more stable the control, and the user experience can be avoided from being affected by the dramatic fluctuation of the variable frequency parameter.

[0084] Finally, the variable frequency adaptation parameter is calculated according to the variable frequency accurate adaptation parameter and the variable frequency fluctuation adaptation parameter, wherein the variable frequency adaptation parameter = the variable frequency accurate adaptation parameter + the variable frequency fluctuation adaptation parameter. For example, when the variable frequency accurate adaptation parameter is 0.28 and the variable frequency fluctuation adaptation parameter is 0.9946, the variable frequency adaptation parameter = 0.28 + 0.9946 = 1.2746. The variable frequency accurate adaptation parameter can reflect the matching accuracy of the actual three-effect temperature under the current variable frequency parameter control and the user target demand temperature, the variable frequency fluctuation adaptation parameter can reflect the future control stability, and the variable frequency adaptation parameter is finally obtained through fusion calculation. The variable frequency adaptation parameter comprehensively reflects the matching degree of the current variable frequency control parameter to the user demand and the running stability, the larger the variable frequency adaptation parameter, the more optimal the current variable frequency control parameter, the better the variable frequency control parameter meets the user target demand temperature, and the stronger the future running stability.

[0085] Further, the "iterative optimization to obtain the optimal variable frequency parameter and perform variable frequency energy consumption management" includes:

[0086] Continue to randomly configure the variable frequency parameter, process the acquired variable frequency adaptation parameter, and perform iterative optimization.

[0087] After optimization convergence, the optimal variable frequency parameter corresponding to the maximum variable frequency adaptation parameter is obtained, and variable frequency energy consumption management is performed.

[0088] In the embodiments of the present application, the optimal variable frequency parameter can be found by iterative optimization guided by the adaptation parameter, and variable frequency energy consumption management is performed accordingly. Specifically:

[0089] First, continue to randomly configure the variable frequency parameter, process the acquired variable frequency adaptation parameter, and perform iterative optimization. Illustratively, on the basis of the current variable frequency parameter, a new variable frequency parameter is generated in a random manner, then the energy efficiency control prediction resource is configured, three-effect control prediction is performed, the variable frequency accurate adaptation parameter and the variable frequency fluctuation adaptation parameter are calculated respectively, and the variable frequency adaptation parameter is calculated by fusion. In this way, according to the logic of variable frequency parameter→calculation of variable frequency adaptation parameter→adjustment of variable frequency adaptation parameter, iterative optimization is continuously performed, the search range of variable frequency parameter is gradually reduced, and the variable frequency parameter evolves in a more optimal direction.

[0090] Secondly, after optimization convergence, the optimal variable frequency parameter corresponding to the maximum variable frequency adaptation parameter is obtained, and variable frequency energy consumption management is performed. Illustratively, during the iteration process, when the change amplitude of the variable frequency adaptation parameter is less than the preset threshold, i.e. the optimization effect tends to be stable and no longer improves significantly, it is considered that the optimization process converges. At this time, the variable frequency parameter corresponding to the maximum variable frequency adaptation parameter in the iteration process is found, which is the optimal variable frequency parameter. The optimal variable frequency parameter can make the energy consumption control stability reach the best under the premise of meeting the user's target temperature demand. The preset threshold can be set according to the precision of the three-effect unit for temperature control. For example, when the precision requirement is very high, the threshold should be set to a small value, such as 0.01%~0.1%, to ensure that the parameter converges to a high-precision solution. If it is a common civil scene, the precision requirement is not high, and the threshold can be relaxed to 0.5%~1% to improve the optimization efficiency. Further, the optimal variable frequency parameter is applied to variable frequency energy consumption management, the three-effect energy distribution is optimized, the invalid energy consumption loss is reduced, and high-efficiency energy consumption management of the three-effect unit is realized.

[0091] In summary, compared with the prior art, the application calculates the control deviation of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter according to the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, processes to obtain the variable frequency adaptive parameter, and iteratively optimizes to obtain the optimal variable frequency parameter, and performs variable frequency energy consumption management. In this way, the variable frequency adaptive parameter is calculated and generated by considering the user's split-efficiency demand, historical data and real-time control parameter, and then the optimal variable frequency parameter is found by iteratively optimizing the variable frequency parameter guided by the adaptive parameter. The optimal variable frequency parameter can make the energy consumption control stability optimal under the premise of meeting the user's split-efficiency demand, thereby improving the variable frequency control effect.

[0092] In summary, the embodiments of the application have at least the following technical effects:

[0093] Compared with the prior art, the application first obtains the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information of the current user. In this way, the three-efficiency demand information of the user is obtained, and the user's energy demand is converted into quantifiable and executable technical indicators, providing a necessary data basis for subsequent weight allocation, prediction control, parameter optimization and the like.

[0094] Secondly, the application obtains historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters of the user in a historical time, and allocates to obtain high-efficiency weights, medium-efficiency weights and low-efficiency weights, wherein each energy supply parameter includes a stable energy supply time. In this way, by collecting the historical high-efficiency energy supply parameters, the historical medium-efficiency energy supply parameters and the historical low-efficiency energy supply parameters of the user in the historical time, the dependence degree of the user on the three levels of energy efficiency is quantified, and weight allocation is performed accordingly, solving the defect that the traditional fixed weight cannot adapt to the dynamic demand of the user.

[0095] Thirdly, the application randomly configures a variable frequency parameter for variable frequency control of a three-efficiency unit, configures energy efficiency control prediction resources according to the historical high-efficiency energy supply parameters, the historical medium-efficiency energy supply parameters and the historical low-efficiency energy supply parameters, performs three-efficiency control prediction, and obtains high-efficiency control parameters, medium-efficiency control parameters and low-efficiency control parameters. In this way, according to the historical stable energy supply condition, the energy efficiency control prediction resources are allocated, the three-efficiency control prediction is performed by the variable frequency three-efficiency controller, and a necessary data basis is provided for subsequent iterative optimization of the variable frequency parameter.

[0096] Finally, the application calculates the control deviation of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter according to the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, obtains the variable frequency adaptive parameter through processing, and iteratively optimizes the optimal variable frequency parameter, and performs variable frequency energy consumption management. In this way, the variable frequency adaptive parameter is calculated and generated by considering the user's split-efficiency demand, historical data and real-time control parameter, and then the optimal variable frequency parameter is found by iteratively optimizing the variable frequency parameter guided by the adaptive parameter. The optimal variable frequency parameter can make the energy consumption control stability best under the premise of meeting the user's split-efficiency demand, thereby improving the variable frequency control effect.

[0097] Through the above technical solution, the application fully considers the user's demand information for three effects, and the variable frequency three-effect controller cluster carries out three-effect control prediction on different variable frequency parameter combinations. Then, based on the user's split-efficiency demand, historical stable energy supply data and real-time control parameter deviation, a multi-dimensional weighted calculation model is constructed to generate a variable frequency adaptive parameter. Then, through a random iterative optimization strategy, the globally optimal variable frequency parameter is dynamically searched guided by the variable frequency adaptive parameter. Finally, the optimal variable frequency parameter is applied to variable frequency energy consumption management. In this way, the split-efficiency demand of the user is accurately matched, and the variable frequency control effect is improved through iterative optimization of the variable frequency parameter.

[0098] Embodiment two, as shown in Figure 2 based on the same inventive concept of the intelligent digital variable frequency three-effect unit energy consumption management method provided in embodiment one, the application embodiment further provides an intelligent digital variable frequency three-effect unit energy consumption management system, comprising:

[0099] The data acquisition module 11 is used to acquire the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information of the current user;

[0100] The weight distribution module 12 is used to acquire the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter in the historical time of the user, and distribute the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, wherein each energy supply parameter includes a stable energy supply time;

[0101] The parameter configuration module 13 is used to randomly configure the variable frequency parameter for variable frequency control of the three-effect unit, configure the energy efficiency control prediction resource according to the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter, perform three-effect control prediction, and obtain the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter;

[0102] The optimization output module 14 is configured to calculate the control deviation of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter according to the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, obtain the variable frequency adaptation parameter through processing, and obtain the optimal variable frequency parameter through iterative optimization, so as to perform variable frequency energy consumption management.

[0103] The data acquisition module 11 is configured to:

[0104] obtain the high-efficiency demand temperature, the medium-efficiency demand temperature and the low-efficiency demand temperature of the current user;

[0105] use the high-efficiency demand temperature, the medium-efficiency demand temperature and the low-efficiency demand temperature as the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information.

[0106] The weight allocation module 12 is configured to:

[0107] obtain the cumulative high-efficiency energy supply time of the user in the recent historical time as the historical high-efficiency energy supply parameter, wherein the stable high-efficiency energy supply includes that the high-efficiency energy supply temperature fluctuation range does not exceed the preset high-efficiency temperature fluctuation threshold;

[0108] obtain the cumulative medium-efficiency energy supply time and the cumulative low-efficiency energy supply time of the user in the recent historical time as the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter, wherein the stable medium-efficiency energy supply and the stable low-efficiency energy supply include that the medium-efficiency energy supply temperature fluctuation range and the low-efficiency energy supply temperature fluctuation range do not exceed the preset medium-efficiency temperature fluctuation threshold and the preset low-efficiency temperature fluctuation threshold respectively;

[0109] allocate and calculate the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight according to the time length of the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter.

[0110] The parameter configuration module 13 is configured to:

[0111] randomly configure the variable frequency parameter for the variable frequency control of the triple-effect unit;

[0112] calculate the average of the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter to obtain the average stable energy supply time;

[0113] calculate the ratio of the average stable energy supply time to the maximum stable energy supply time to obtain the energy efficiency control prediction resource coefficient;

[0114] obtain a variable frequency triple-effect controller cluster, and randomly select a variable frequency triple-effect controller with a proportion of the energy efficiency control prediction resource coefficient;

[0115] input the variable frequency parameter into the randomly selected multiple variable frequency triple-effect controllers, calculate the average of the triple-effect control prediction output results, and obtain the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter.

[0116] Further, the "acquiring a variable frequency three-effect controller cluster" comprises:

[0117] According to three-effect unit control data in a historical time, a sample variable frequency parameter set is collected, and a sample high-efficiency control parameter set, a sample medium-efficiency control parameter set and a sample low-efficiency control parameter set under different sample variable frequency parameters are collected;

[0118] A preset number of groups of data in the sample variable frequency parameter set, the sample high-efficiency control parameter set, the sample medium-efficiency control parameter set and the sample low-efficiency control parameter set are randomly divided, and a first variable frequency three-effect controller is trained;

[0119] Continue to train multiple variable frequency three-effect controllers to obtain a variable frequency three-effect controller cluster.

[0120] The optimization output module 14 is specifically configured to:

[0121] Obtain average high-efficiency energy supply information, average medium-efficiency energy supply information and average low-efficiency energy supply information of stable energy supply of a user in a recent historical time;

[0122] Calculate the similarity of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter with the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, respectively, and obtain variable frequency accurate adaptation parameters by weighted calculation using the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight;

[0123] Calculate the difference between the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, respectively, to obtain high-efficiency control deviation, medium-efficiency control deviation and low-efficiency control deviation;

[0124] Calculate the fluctuation amplitude of the high-efficiency control deviation, the medium-efficiency control deviation and the low-efficiency control deviation and the average high-efficiency energy supply information, the average medium-efficiency energy supply information and the average low-efficiency energy supply information, respectively, and obtain variable frequency deviation fluctuation parameters by weighted calculation using the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, and calculate variable frequency fluctuation adaptation parameters;

[0125] According to the variable frequency accurate adaptation parameters and the variable frequency fluctuation adaptation parameters, calculate variable frequency adaptation parameters.

[0126] Further, the "iterative optimization to obtain optimal variable frequency parameters for variable frequency energy consumption management" comprises:

[0127] Continue to randomly configure variable frequency parameters, process variable frequency adaptation parameters, and perform iterative optimization;

[0128] After the optimization convergence, the optimal variable frequency parameter corresponding to the maximum variable frequency adaptive parameter is obtained, and variable frequency energy consumption management is performed.

[0129] To sum up, the embodiments of the application have at least the following technical effects:

[0130] Compared with the prior art, first, the data acquisition module is used to obtain the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information of the current user, so that the three-efficiency demand information of the user is obtained, and the energy demand of the user is converted into quantifiable and executable technical indexes, thereby providing a necessary data basis for subsequent weight distribution, prediction control and parameter optimization. Second, the weight distribution module is used to obtain the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter in the historical time of the user, and the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight are obtained, wherein each energy supply parameter includes a stable energy supply time. The historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter in the historical time of the user are collected, the dependence degree of the user on the three levels of energy efficiency is quantified, and the weight distribution is performed accordingly, thereby solving the defect that the traditional fixed weight cannot adapt to the dynamic demand of the user. Third, the parameter configuration module is used to randomly configure the variable frequency parameter for variable frequency control of the three-efficiency unit, configure the energy efficiency control prediction resource according to the historical high-efficiency energy supply parameter, the historical medium-efficiency energy supply parameter and the historical low-efficiency energy supply parameter, perform three-efficiency control prediction to obtain the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter, distribute the energy efficiency control prediction resource according to the historical stable energy supply condition, perform three-efficiency control prediction by the variable frequency three-efficiency controller, and provide a necessary data basis for subsequent variable frequency parameter iterative optimization. Finally, the optimization output module is used to perform weighted calculation on the control deviation of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter according to the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, process the variable frequency adaptive parameter, and iteratively optimize the optimal variable frequency parameter to perform variable frequency energy consumption management. The variable frequency adaptive parameter is calculated and generated by considering the split-efficiency demand of the user, the historical data and the real-time control parameter, and then the optimal variable frequency parameter is found by randomly iteratively optimizing the variable frequency parameter. The optimal variable frequency parameter can make the energy consumption control stability best on the premise of meeting the split-efficiency demand of the user, thereby improving the variable frequency control effect. In this way, the split-efficiency demand of the user is accurately matched, and the variable frequency control effect is improved by iterative optimization of the variable frequency parameter.

[0131] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0132] Those skilled in the art will appreciate that embodiments of the present application can be devised for a variety of applications. It is intended that the present application be limited only by the scope of the appended claims, and it is intended that there be a full range of equivalents. Many embodiments of the application embody one or more of the following features:

[0133] The present application is described in reference to the drawings using a flowchart and / or a block diagram of the method, apparatus (system) and computer program product according to embodiments of the application. It will be understood that each block of the flowchart and / or block diagram, and combinations of blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions of the flowchart and / or the block diagram block or blocks. Figure 1 The flowchart and / or block diagram can include one or more flowcharts and / or one or more block diagrams. Figure 1 The flowchart and / or block diagram can include one or more flowcharts and / or one or more block diagrams.

[0134] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions of the flowchart and / or block diagram block or blocks. Figure 1 The flowchart and / or block diagram can include one or more flowcharts and / or one or more block diagrams. Figure 1 The flowchart and / or block diagram can include one or more flowcharts and / or one or more block diagrams.

[0135] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions of the flowchart and / or block diagram block or blocks. Figure 1 The flowchart and / or block diagram can include one or more flowcharts and / or one or more block diagrams. Figure 1 The flowchart and / or block diagram can include one or more flowcharts and / or one or more block diagrams.

[0136] While the preferred embodiments of the application have been described, additional variations and modifications can be employed by those skilled in the art without departing from the spirit and scope of the application.

[0137] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the application, the application can be practiced otherwise than as specifically described.

Claims

1. A method for energy consumption management of an intelligent digital variable frequency three-effect unit, characterized in that, The method comprises: obtaining high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information of a current user; obtaining historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters in a historical time of the user, and obtaining high-efficiency weight, medium-efficiency weight and low-efficiency weight, wherein each energy supply parameter comprises stable energy supply time; randomly configuring a variable frequency parameter for variable frequency control of a three-effect unit, configuring an energy efficiency control prediction resource according to the historical high-efficiency energy supply parameters, the historical medium-efficiency energy supply parameters and the historical low-efficiency energy supply parameters, performing three-effect control prediction, and obtaining high-efficiency control parameters, medium-efficiency control parameters and low-efficiency control parameters, comprising: randomly configuring a variable frequency parameter for variable frequency control of a three-effect unit; calculating the average of the historical high-efficiency energy supply parameters, the historical medium-efficiency energy supply parameters and the historical low-efficiency energy supply parameters to obtain the average stable energy supply time; calculating the ratio of the average stable energy supply time to the maximum stable energy supply time to obtain an energy efficiency control prediction resource coefficient; obtaining a variable frequency three-effect controller cluster and randomly selecting a variable frequency three-effect controller with a proportion of the energy efficiency control prediction resource coefficient; inputting the variable frequency parameter into the randomly selected multiple variable frequency three-effect controllers, calculating the average of the three-effect control prediction output results, and obtaining high-efficiency control parameters, medium-efficiency control parameters and low-efficiency control parameters; weighting and calculating the control deviation of the high-efficiency control parameters, the medium-efficiency control parameters and the low-efficiency control parameters according to the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, processing to obtain a variable frequency adaptive parameter, and iteratively optimizing to obtain an optimal variable frequency parameter for variable frequency energy consumption management; wherein obtaining a variable frequency three-effect controller cluster comprises: collecting a sample variable frequency parameter set according to three-effect unit control data in a historical time, and collecting a sample high-efficiency control parameter set, a sample medium-efficiency control parameter set and a sample low-efficiency control parameter set under different sample variable frequency parameter control; randomly dividing the data of a preset number of groups in the sample variable frequency parameter set, the sample high-efficiency control parameter set, the sample medium-efficiency control parameter set and the sample low-efficiency control parameter set, and training a first variable frequency three-effect controller; continue to train multiple variable frequency three-effect controllers to obtain a variable frequency three-effect controller cluster.

2. The intelligent digital variable frequency three-effect unit energy consumption management method of claim 1, wherein, Obtaining high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information of a current user comprises: obtaining high-efficiency demand temperature, medium-efficiency demand temperature and low-efficiency demand temperature of the current user; using the high-efficiency demand temperature, the medium-efficiency demand temperature and the low-efficiency demand temperature as high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information.

3. The intelligent digital variable frequency three-effect unit energy consumption management method of claim 1, wherein, Obtaining historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters in a historical time of the user, and obtaining high-efficiency weight, medium-efficiency weight and low-efficiency weight, comprises: obtaining cumulative high-efficiency energy supply time of the user in the recent historical time for stable high-efficiency energy supply as the historical high-efficiency energy supply parameter, wherein stable high-efficiency energy supply comprises that the high-efficiency energy supply temperature fluctuation range does not exceed a preset high-efficiency temperature fluctuation threshold; obtaining cumulative medium-efficiency energy supply time and cumulative low-efficiency energy supply time of stable medium-efficiency energy supply and stable low-efficiency energy supply of the user in the recent history time as historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters; allocating high-efficiency weight, medium-efficiency weight and low-efficiency weight according to time length of the historical high-efficiency energy supply parameters, the historical medium-efficiency energy supply parameters and the historical low-efficiency energy supply parameters.

4. The intelligent digital variable frequency three-effect unit energy consumption management method of claim 1, wherein, According to the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, the control deviation of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter is weighted and calculated to obtain the variable frequency adaptation parameter, including: obtaining average high-efficiency energy supply information, average medium-efficiency energy supply information and average low-efficiency energy supply information of stable energy supply of the user in the recent history time; respectively calculating similarity of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, and obtaining variable frequency accurate adaptation parameters by weighted calculation using the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight; respectively calculating difference of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information to obtain high-efficiency control deviation, medium-efficiency control deviation and low-efficiency control deviation; respectively calculating fluctuation amplitude of the high-efficiency control deviation, the medium-efficiency control deviation and the low-efficiency control deviation and the average high-efficiency energy supply information, the average medium-efficiency energy supply information and the average low-efficiency energy supply information, and obtaining variable frequency deviation fluctuation parameters by weighted calculation using the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, and calculating variable frequency fluctuation adaptation parameters; obtaining variable frequency adaptation parameters according to the variable frequency accurate adaptation parameters and the variable frequency fluctuation adaptation parameters.

5. The intelligent digital variable frequency three-effect chiller energy consumption management method of claim 1, wherein, iteratively optimizing to obtain optimal variable frequency parameters for variable frequency energy consumption management, including: continuing to randomly configure variable frequency parameters to obtain variable frequency adaptation parameters for iterative optimization; after optimization convergence, obtaining optimal variable frequency parameters corresponding to maximum variable frequency adaptation parameters for variable frequency energy consumption management.

6. An intelligent digital variable frequency three-effect unit energy consumption management system, characterized in that, for performing the method of any one of claims 1-5, comprising: a data acquisition module for obtaining high-efficiency demand information, medium-efficiency demand information and low-efficiency demand information of the current user; a weight allocation module for obtaining historical high-efficiency energy supply parameters, historical medium-efficiency energy supply parameters and historical low-efficiency energy supply parameters of the user in the history time, and obtaining high-efficiency weight, medium-efficiency weight and low-efficiency weight, wherein each energy supply parameter includes stable energy supply time; a parameter configuration module for randomly configuring variable frequency parameters for variable frequency control of the triple-effect unit, configuring energy efficiency control prediction resources according to the historical high-efficiency energy supply parameters, the historical medium-efficiency energy supply parameters and the historical low-efficiency energy supply parameters, performing triple-effect control prediction to obtain high-efficiency control parameters, medium-efficiency control parameters and low-efficiency control parameters; An optimization output module is configured to calculate the control deviation of the high-efficiency control parameter, the medium-efficiency control parameter and the low-efficiency control parameter according to the high-efficiency weight, the medium-efficiency weight and the low-efficiency weight, and the high-efficiency demand information, the medium-efficiency demand information and the low-efficiency demand information, to obtain the variable frequency adaptive parameter, and to iteratively optimize the variable frequency adaptive parameter to obtain the optimal variable frequency parameter, and to perform variable frequency energy consumption management.

Images