A method, system and program product for recommending starting and stopping of a central air-conditioning refrigeration unit

Abstract

The present invention belongs to the field of energy-saving control technology, and specifically discloses a method, system and program product for recommending the start and stop of a central air-conditioning refrigeration unit. The method collects the operation monitoring data of the central air-conditioning in the current period and substitutes it into the training refrigeration capacity prediction model for prediction, determines the predicted refrigeration capacity of the next period, and then selects the recommended refrigeration unit combination based on the predicted refrigeration capacity of the next period and the determined maximum refrigeration capacity, energy efficiency ratio and current load rate of each single refrigeration unit, so as to start each refrigeration unit included in the recommended refrigeration unit combination in the next period. The present invention can realize real-time monitoring and dynamic adjustment of the central air-conditioning refrigeration system, ensure that the refrigeration system always operates in the optimal state, and can effectively improve the refrigeration efficiency and the energy efficiency ratio of the whole station of the central air-conditioning refrigeration system, reduce the energy waste caused by more or less opening, and achieve the purpose of energy saving and emission reduction.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy-saving control, and in particular relates to a method, system and program product for recommending starting and stopping of a central air-conditioning refrigeration unit. Background Art

[0002] As global climate change and energy consumption become increasingly serious, energy conservation and emission reduction have become important goals for all walks of life. Central air conditioning has always been a major energy consumer for enterprises. The refrigeration system of central air conditioning is widely used in industry and commerce, and is the main part of its energy consumption. Optimizing the energy consumption of central air conditioning refrigeration system has become an important part of energy conservation and emission reduction.

[0003] The traditional central air-conditioning intelligent control system controls the refrigeration unit through the automatic control program, and the start and stop of the refrigeration unit includes transition mode and summer mode, etc. The existing refrigeration unit start and stop intelligent control mode has a simple start and stop control logic and a single mode, which is prone to over-start or under-start, resulting in energy waste. At the same time, it will also lead to a low EER (energy efficiency ratio, that is, the ratio of cooling capacity to cooling power consumption) of the central air-conditioning substation. Summary of the invention

[0004] The purpose of the present invention is to provide a method, system and program product for recommending the start and stop of a central air-conditioning refrigeration unit, so as to solve the above-mentioned problems existing in the prior art.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, a method for recommending starting and stopping a central air-conditioning refrigeration unit is provided, comprising:

[0007] Collect historical refrigeration capacity data of each single refrigeration unit of the central air-conditioning in each historical time period under actual working conditions;

[0008] Determine the actual maximum cooling capacity data of each refrigeration unit according to the historical cooling capacity data of each refrigeration unit in each historical time period;

[0009] Collecting in real time the comprehensive monitoring data set of all refrigeration units of the central air conditioner in the current period, the comprehensive monitoring data set includes monitoring temperature data, monitoring humidity data, monitoring cooling capacity data, monitoring power data and monitoring power consumption data;

[0010] The comprehensive monitoring data set is input into the trained cooling capacity prediction model to predict the cooling capacity and obtain the predicted cooling capacity of the central air conditioner in the next period;

[0011] Traversing and determining all possible refrigeration unit combinations of the central air conditioner, wherein the refrigeration unit combination includes at least one refrigeration unit, and determining the total energy efficiency ratio, total current load rate and total maximum cooling capacity of each refrigeration unit combination;

[0012] The refrigeration unit combination whose total maximum refrigeration capacity is greater than or equal to the predicted refrigeration capacity in the next period is taken as the candidate refrigeration unit combination;

[0013] Determine the energy efficiency ratio score of each candidate refrigeration unit combination according to the total energy efficiency ratio of each candidate refrigeration unit combination, determine the current load rate score of each candidate refrigeration unit combination according to the total current load rate of each candidate refrigeration unit combination, and determine the cooling capacity score of each candidate refrigeration unit combination according to the total maximum cooling capacity of each candidate refrigeration unit combination;

[0014] The energy efficiency ratio score, current load rate score and cooling capacity score of each candidate refrigeration unit combination are added together to obtain the total score of each candidate refrigeration unit combination;

[0015] The candidate refrigeration unit combination with the highest total score is used as the recommended refrigeration unit combination for the central air conditioner in the next time period, so that the refrigeration units included in the recommended refrigeration unit combination will be turned on in the next time period of the current time period, and the refrigeration units not included in the recommended refrigeration unit combination will be turned off.

[0016] In a possible design, determining the actual maximum refrigeration capacity data of each refrigeration unit according to the historical refrigeration capacity data of each refrigeration unit in each historical time period includes:

[0017] Summarize the historical refrigeration capacity data of the refrigeration unit in each historical time period in ascending order to obtain the corresponding refrigeration capacity data sequence;

[0018] Map the cooling capacity data sequence to the interval range of [0, 1], so that the minimum value in the cooling capacity data sequence is mapped to 0 and the maximum value is mapped to 1;

[0019] The interval range of [0, 1] is divided into several sub-interval segments according to the set step size, and each sub-interval segment is mapped to a corresponding cooling capacity data sequence segment;

[0020] The cooling capacity data sequence segment corresponding to the set sub-interval segment is taken as the target cooling capacity data sequence segment, and the minimum historical cooling capacity data in the target cooling capacity data sequence segment is taken as the actual maximum cooling capacity data of the corresponding refrigeration unit.

[0021] In a possible design, before inputting the comprehensive monitoring data set into the trained refrigeration capacity prediction model to perform refrigeration capacity prediction, the method further includes:

[0022] Construct a recurrent neural network model, and configure the objective function and constraints of the recurrent neural network model to obtain an initialized recurrent neural network model;

[0023] Collecting historical comprehensive monitoring data sets of all refrigeration units of the central air conditioner in each historical time period, wherein the historical comprehensive monitoring data sets include historical monitoring temperature data, historical monitoring humidity data, historical monitoring cooling capacity data, historical monitoring power data, and historical monitoring power consumption data;

[0024] A training set is constructed based on each historical comprehensive monitoring data set, and the initialized recurrent neural network model is trained using the training set to obtain a trained refrigeration capacity prediction model.

[0025] In a possible design, when the next time period is within the designated morning time period, the training set is constructed based on each historical comprehensive monitoring data set, including:

[0026] The historical comprehensive monitoring data sets corresponding to each historical time period in the morning period are selected as the first type of comprehensive monitoring data sets, and the historical monitoring cooling capacity data are extracted from the historical comprehensive monitoring data of the next historical time period of each historical time period as the label of the first type of comprehensive monitoring data set corresponding to each historical time period;

[0027] Labeling each first-category comprehensive monitoring data set using a label corresponding to each first-category comprehensive monitoring data set to obtain each labeled first-category comprehensive monitoring data set;

[0028] The training set is composed of the labeled first-category comprehensive monitoring data sets.

[0029] In a possible design, when the next time period is within the designated afternoon time period, the training set is constructed based on each historical comprehensive monitoring data set, including:

[0030] The historical comprehensive monitoring data sets corresponding to each historical time period in the afternoon are selected as the second type of comprehensive monitoring data sets, and the historical monitoring cooling capacity data are extracted from the historical comprehensive monitoring data of the next historical time period of each historical time period as the label of the second type of comprehensive monitoring data set corresponding to each historical time period;

[0031] Labeling each second-category comprehensive monitoring data set using a label corresponding to each second-category comprehensive monitoring data set to obtain each labeled second-category comprehensive monitoring data set;

[0032] The training set is composed of the labeled second-category comprehensive monitoring data sets.

[0033] In a possible design, the determination of the total energy efficiency ratio, total current load rate and total maximum refrigeration capacity of each refrigeration unit combination includes:

[0034] Collect the average cooling capacity data and average power consumption data of each refrigeration unit in the refrigeration unit combination on the previous day, divide the average power consumption data of the previous day by the average cooling capacity data of the previous day to obtain the energy efficiency ratio of the corresponding refrigeration unit, and add the energy efficiency ratios of each refrigeration unit in the refrigeration unit combination to obtain the total energy efficiency ratio of the refrigeration unit combination;

[0035] The rated current of each refrigeration unit in the refrigeration unit combination and the average actual working current of the previous day are collected, and the current load rate of the corresponding refrigeration unit is obtained by dividing the average actual working current of the previous day by the rated current. The current load rate of each refrigeration unit in the refrigeration unit combination is added to obtain the total current load rate of the refrigeration unit combination;

[0036] The actual maximum cooling capacity data of each refrigeration unit in the refrigeration unit combination are added together to obtain the total maximum cooling capacity of the refrigeration unit combination.

[0037] In a possible design, the energy efficiency ratio score of each candidate refrigeration unit combination is determined according to the total energy efficiency ratio of each candidate refrigeration unit combination, the current load rate score of each candidate refrigeration unit combination is determined according to the total current load rate of each candidate refrigeration unit combination, and the cooling capacity score of each candidate refrigeration unit combination is determined according to the total maximum cooling capacity of each candidate refrigeration unit combination, including:

[0038] Rank the energy efficiency ratios of the candidate refrigeration unit combinations in descending order of total energy efficiency ratio, and determine the energy efficiency ratio score of each candidate refrigeration unit combination according to the energy efficiency ratio ranking;

[0039] The current load rate of each candidate refrigeration unit combination is ranked in descending order according to the total current load rate, and the current load rate score of each candidate refrigeration unit combination is determined according to the current load rate ranking;

[0040] The cooling capacity of each candidate refrigeration unit combination is ranked in descending order according to the total maximum cooling capacity, and the cooling capacity score of each candidate refrigeration unit combination is determined according to the cooling capacity ranking.

[0041] In a second aspect, a central air-conditioning refrigeration unit start-stop recommendation system is provided, comprising a first acquisition unit, a cooling capacity determination unit, a second acquisition unit, a cooling capacity prediction unit, a combination determination unit, a combination screening unit, a scoring determination unit, a total score calculation unit and a combination recommendation unit, wherein:

[0042] The first collection unit is used to collect historical refrigeration capacity data of each single refrigeration unit of the central air conditioner in each historical time period under actual working conditions;

[0043] A cooling capacity determination unit, used to determine the actual maximum cooling capacity data of each refrigeration unit according to the historical cooling capacity data of each refrigeration unit in each historical time period;

[0044] The second collection unit is used to collect in real time the comprehensive monitoring data set of all refrigeration units of the central air conditioner in the current period, wherein the comprehensive monitoring data set includes monitoring temperature data, monitoring humidity data, monitoring cooling capacity data, monitoring power data and monitoring power consumption data;

[0045] A cooling capacity prediction unit is used to input the comprehensive monitoring data set into the trained cooling capacity prediction model to perform cooling capacity prediction and obtain the predicted cooling capacity of the central air conditioner in the next period;

[0046] A combination determination unit, used for traversing and determining all possible refrigeration unit combinations of the central air conditioner, wherein the refrigeration unit combination includes at least one refrigeration unit, and determining the total energy efficiency ratio, total current load rate and total maximum cooling capacity of each refrigeration unit combination;

[0047] A combination screening unit, used for selecting a refrigeration unit combination whose total maximum refrigeration capacity is greater than or equal to the predicted refrigeration capacity in the next period as a candidate refrigeration unit combination;

[0048] A scoring determination unit, used to determine the energy efficiency ratio score of each candidate refrigeration unit combination according to the total energy efficiency ratio of each candidate refrigeration unit combination, determine the current load rate score of each candidate refrigeration unit combination according to the total current load rate of each candidate refrigeration unit combination, and determine the cooling capacity score of each candidate refrigeration unit combination according to the total maximum cooling capacity of each candidate refrigeration unit combination;

[0049] A total score calculation unit, used for adding the energy efficiency ratio score, current load rate score and cooling capacity score of each candidate refrigeration unit combination to obtain a total score of each candidate refrigeration unit combination;

[0050] The combination recommendation unit is used to use the candidate refrigeration unit combination with the highest total score as the recommended refrigeration unit combination for the central air conditioner in the next time period, so as to turn on the refrigeration units included in the recommended refrigeration unit combination in the next time period of the current time period, and shut down the refrigeration units not included in the recommended refrigeration unit combination.

[0051] In a third aspect, a central air-conditioning refrigeration unit start-stop recommendation system is provided, comprising:

[0052] A memory for storing instructions;

[0053] A processor is used to read the instructions stored in the memory and execute any one of the methods described in the first aspect according to the instructions.

[0054] In a fourth aspect, a computer-readable storage medium is provided, wherein instructions are stored on the computer-readable storage medium, and when the instructions are executed on a computer, the computer executes any one of the methods described in the first aspect. In addition, a computer program product is provided, and when the computer program product is executed on a computer, the computer executes any one of the methods described in the first aspect.

[0055] Beneficial effects: The present invention can realize real-time monitoring and dynamic adjustment of the central air-conditioning refrigeration system, ensuring that the refrigeration system always operates in the optimal state, and can effectively improve the refrigeration efficiency and the energy efficiency ratio of the whole station of the central air-conditioning refrigeration system, reduce the energy waste caused by more or less opening, and achieve the purpose of energy saving and emission reduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 is a flowchart of the steps of the method in Example 1 of the present invention;

[0058] Figure 2 This is a schematic diagram of the structure of the system in Example 2 of the present invention;

[0059] Figure 3 Schematic diagram of the system structure in Example 3 of the present invention. DETAILED DESCRIPTION

[0060] It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. The specific structures and functional details disclosed herein are only used to describe the exemplary embodiments of the present invention. However, the present invention can be embodied in many alternative forms, and it should not be understood that the present invention is limited to the embodiments set forth herein.

[0061] It should be understood that unless otherwise clearly specified and limited, the corresponding terms should be understood in a broad sense, for example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments can be understood according to specific circumstances.

[0062] In the following description, certain details are provided to facilitate a complete understanding of the example embodiments. However, it will be appreciated by those of ordinary skill in the art that the example embodiments may be implemented without these certain details. For example, devices may be shown in block diagrams to avoid obscuring the examples with unnecessary details. In other embodiments, well-known processes, structures, and techniques may not be shown in unnecessary detail to avoid obscuring the embodiments.

[0063] Embodiment 1:

[0064] This embodiment provides a method for recommending starting and stopping a refrigeration unit of a central air conditioner, which can be applied to a main controller of a central air conditioner, such as Figure 1 As shown, the method comprises the following steps:

[0065] S1. Collect historical cooling capacity data of each single refrigeration unit of the central air-conditioning unit in each historical time period under actual working conditions.

[0066] In specific implementation, the operating environment of central air-conditioning refrigeration units is usually more complex, and the maximum cooling capacity on the nameplate under the design conditions cannot be used as a direct reference. It is necessary to determine the actual maximum cooling capacity data of a single refrigeration unit based on a large amount of data trend analysis under actual conditions. Therefore, it is necessary to collect historical cooling capacity data of each single refrigeration unit of the central air-conditioning under actual conditions in various historical time periods. During the data collection process, it is necessary to remove abnormal data generated during downtime or non-production periods, and use the cleaned and integrated historical cooling capacity data for trend analysis.

[0067] S2. Determine the actual maximum cooling capacity data of each refrigeration unit according to the historical cooling capacity data of each refrigeration unit in each historical time period.

[0068] In specific implementation, the historical refrigeration capacity data of the refrigeration unit in each historical time period can be summarized in ascending order to obtain the corresponding refrigeration capacity data sequence; then the refrigeration capacity data sequence is mapped to the interval range of [0, 1], so that the minimum value in the refrigeration capacity data sequence is mapped to 0 and the maximum value is mapped to 1; then the interval range of [0, 1] is divided into several sub-interval segments according to the set step size, and each sub-interval segment is mapped to the corresponding refrigeration capacity data sequence segment. For example, if the step size is set to 0.025, the interval range of [0, 1] can be Divide into 40 sub-intervals (0-0.025, 0.025-0.05, ..., 0.95-0.975, 0.975-1); finally, take the cooling capacity data sequence segment corresponding to the set sub-interval as the target cooling capacity data sequence segment. For example, the cooling capacity data sequence segment corresponding to the 0.95-0.975 sub-interval segment can be taken as the target cooling capacity data sequence segment, and the minimum historical cooling capacity data in the target cooling capacity data sequence segment is taken as the actual maximum cooling capacity data of the corresponding refrigeration unit.

[0069] S3. Real-time collection of a comprehensive monitoring data set of all refrigeration units of the central air conditioner in the current period, wherein the comprehensive monitoring data set includes monitoring temperature data, monitoring humidity data, monitoring cooling capacity data, monitoring power data and monitoring power consumption data.

[0070] In the specific implementation, it is necessary to collect the comprehensive monitoring data set of all refrigeration units of the central air-conditioning in the current period in real time, and the comprehensive monitoring data set includes monitoring temperature data, monitoring humidity data, monitoring cooling capacity data, monitoring power data and monitoring power consumption data.

[0071] S4. Input the comprehensive monitoring data set into the trained cooling capacity prediction model to perform cooling capacity prediction, and obtain the predicted cooling capacity of the central air conditioner in the next period.

[0072] In the specific implementation, before the refrigeration capacity prediction is performed through the refrigeration capacity prediction model, it is necessary to first obtain the refrigeration capacity prediction model, the refrigeration capacity prediction model adopts the existing recurrent neural network (recurrent neural network (RNN) is a type of recurrent neural network that takes sequence data as input, recursively in the evolution direction of the sequence, and all nodes (recurrent units) are connected in a chain), and after the objective function and constraint conditions of the recurrent neural network are configured, the initialized recurrent neural network model is obtained; illustratively, the objective function is Q 预测 =Q 实际 , that is, the cooling capacity predicted by the model is equal to the actual cooling capacity; the constraints may include: the indoor temperature is within the set temperature range, the motor frequency f of the refrigeration unit is within the set frequency range, and the relationship between the power p(f) of the refrigeration unit and the frequency f is p(f)=kf 2 , where k is the set conventional coefficient, the power consumption of the refrigeration unit E = p (f) × t, t is the length of the corresponding time period, and the energy efficiency ratio of the refrigeration unit = Q 预测 / E, etc. Then, the historical comprehensive monitoring data set of all refrigeration units of the central air conditioner in each historical time period is collected, and the historical comprehensive monitoring data set includes historical monitoring temperature data, historical monitoring humidity data, historical monitoring refrigeration capacity data, historical monitoring power data and historical monitoring power consumption data; then, a training set is constructed based on each historical comprehensive monitoring data set, and the initialized recurrent neural network model is trained using the training set to obtain a trained refrigeration capacity prediction model. In the process of model training, corresponding optimization algorithms, such as the gradient descent method, can be used to optimize the prediction results to reduce the prediction deviation of the model.

[0073] The training of the model can be divided into morning period training and afternoon period training. When the next period to be predicted is within the designated morning period, the process of constructing the corresponding training set for model training includes: selecting the historical comprehensive monitoring data sets corresponding to each historical time period within the morning period as the first type of comprehensive monitoring data sets, and extracting the historical monitoring cooling capacity data from the historical comprehensive monitoring data of the next historical time period of each historical time period as the label of the first type of comprehensive monitoring data set corresponding to each historical time period. Then, each first type of comprehensive monitoring data set is labeled using the label corresponding to each first type of comprehensive monitoring data set to obtain each labeled first type of comprehensive monitoring data set. Finally, the labeled first type of comprehensive monitoring data sets are used to form a training set, and the initialized recurrent neural network model is trained using the training set to obtain a trained cooling capacity prediction model.

[0074] When the next time period to be predicted is within the designated afternoon time period, the process of constructing the corresponding training set for model training includes: selecting the historical comprehensive monitoring data sets corresponding to each historical time period within the afternoon time period as the second type of comprehensive monitoring data sets, and extracting the historical monitoring refrigeration capacity data from the historical comprehensive monitoring data of the next historical time period of each historical time period as the label of the second type of comprehensive monitoring data set corresponding to each historical time period. Then, each second type of comprehensive monitoring data set is labeled using the label corresponding to each second type of comprehensive monitoring data set to obtain each labeled second type of comprehensive monitoring data set. Finally, each labeled second type of comprehensive monitoring data set is used to form a training set, and the training set is used to train the initialized recurrent neural network model to obtain a trained refrigeration capacity prediction model.

[0075] S5. Traverse and determine all possible refrigeration unit combinations of the central air conditioner, wherein the refrigeration unit combination includes at least one refrigeration unit, and determine the total energy efficiency ratio, total current load rate and total maximum cooling capacity of each refrigeration unit combination.

[0076] In the specific implementation, all possible refrigeration unit combinations of the central air conditioner are first traversed and determined, and each refrigeration unit combination contains at least one refrigeration unit. Then the total energy efficiency ratio, total current load rate and total maximum cooling capacity of each refrigeration unit combination are determined. The process includes:

[0077] Collect the average cooling capacity data and average power consumption data of each refrigeration unit in the refrigeration unit combination on the previous day, divide the average cooling capacity data of the previous day by the average power consumption data of the previous day to obtain the COP value (Coefficient of Performance, i.e., energy efficiency ratio, which is a key indicator for measuring the efficiency of refrigeration equipment and is defined as the ratio of cooling capacity to power consumption) of the corresponding refrigeration unit, and add the energy efficiency ratios of each refrigeration unit in the refrigeration unit combination to obtain the total energy efficiency ratio of the refrigeration unit combination. Collect the rated current of each refrigeration unit in the refrigeration unit combination and the average actual working current of the previous day, divide the average actual working current of the previous day by the rated current to obtain the current load rate of the corresponding refrigeration unit, and add the current load rates of each refrigeration unit in the refrigeration unit combination to obtain the total current load rate of the refrigeration unit combination. Add the actual maximum cooling capacity data of each refrigeration unit in the refrigeration unit combination to obtain the total maximum cooling capacity of the refrigeration unit combination.

[0078] S6. The refrigeration unit combination whose total maximum cooling capacity is greater than or equal to the predicted cooling capacity for the next period is selected as a candidate refrigeration unit combination.

[0079] In specific implementation, the refrigeration unit combinations whose total maximum cooling capacity is greater than or equal to the predicted cooling capacity for the next period are first selected as candidate refrigeration unit combinations, and the refrigeration unit combinations whose total maximum cooling capacity does not meet the predicted cooling capacity for the next period are all removed.

[0080] S7. Determine the energy efficiency ratio score of each candidate refrigeration unit combination based on the total energy efficiency ratio of each candidate refrigeration unit combination, determine the current load rate score of each candidate refrigeration unit combination based on the total current load rate of each candidate refrigeration unit combination, and determine the cooling capacity score of each candidate refrigeration unit combination based on the total maximum cooling capacity of each candidate refrigeration unit combination.

[0081] In specific implementation, the energy efficiency ratio of each candidate refrigeration unit combination can be ranked in order of total energy efficiency ratio from high to low, and the energy efficiency ratio score of each candidate refrigeration unit combination can be determined according to the energy efficiency ratio ranking. For example, the energy efficiency ratio ranks first, and the corresponding energy efficiency ratio score is 5 points, the energy efficiency ratio ranks second, and the corresponding energy efficiency ratio score is 4 points, and so on.

[0082] The current load rate of each candidate refrigeration unit combination can be ranked in order from high to low according to the total current load rate, and the current load rate score of each candidate refrigeration unit combination can be determined according to the current load rate ranking. For example, if the current load rate ranking is first, the corresponding current load rate score is 5 points, if the current load rate ranking is second, the corresponding current load rate score is 4 points, and so on.

[0083] The cooling capacity of each candidate refrigeration unit combination is ranked in descending order according to the total maximum cooling capacity, and the cooling capacity score of each candidate refrigeration unit combination is determined according to the cooling capacity ranking. For example, the cooling capacity ranking first corresponds to a cooling capacity score of 5 points, the cooling capacity ranking second corresponds to a cooling capacity score of 4 points, and so on.

[0084] S8. Add the energy efficiency ratio score, current load rate score and cooling capacity score of each candidate refrigeration unit combination to obtain the total score of each candidate refrigeration unit combination.

[0085] In specific implementation, the energy efficiency ratio score, current load rate score and cooling capacity score of each candidate refrigeration unit combination are added together by summing the scores to obtain the total score of each candidate refrigeration unit combination.

[0086] S9. The candidate refrigeration unit combination with the highest total score is used as the recommended refrigeration unit combination for the central air conditioner in the next time period, so that each refrigeration unit included in the recommended refrigeration unit combination is turned on in the next time period of the current time period, and each refrigeration unit not included in the recommended refrigeration unit combination is turned off.

[0087] In specific implementation, the candidate refrigeration unit combination with the highest total score can be used as the recommended refrigeration unit combination for the central air conditioner in the next period, and then the refrigeration units included in the recommended refrigeration unit combination will be turned on in the next period of the current period, and the refrigeration units not included in the recommended refrigeration unit combination will be turned off. This can achieve the optimal state control of the central air conditioning refrigeration system while meeting the predicted cooling capacity demand in the next period.

[0088] The method of this embodiment can realize real-time monitoring and dynamic adjustment of the central air-conditioning refrigeration system, ensuring that the refrigeration system always operates in the optimal state, and can effectively improve the refrigeration efficiency of the central air-conditioning refrigeration system and the EER of the entire station, reduce the energy waste caused by over-starting or under-starting, and achieve the purpose of energy saving and emission reduction.

[0089] Embodiment 2:

[0090] This embodiment provides a central air-conditioning refrigeration unit start-stop recommendation system. Figure 2 As shown, it includes a first acquisition unit, a cooling capacity determination unit, a second acquisition unit, a cooling capacity prediction unit, a combination determination unit, a combination screening unit, a scoring determination unit, a total score calculation unit and a combination recommendation unit, wherein:

[0091] The first collection unit is used to collect historical refrigeration capacity data of each single refrigeration unit of the central air conditioner in each historical time period under actual working conditions;

[0092] A cooling capacity determination unit, used to determine the actual maximum cooling capacity data of each refrigeration unit according to the historical cooling capacity data of each refrigeration unit in each historical time period;

[0093] The second collection unit is used to collect in real time the comprehensive monitoring data set of all refrigeration units of the central air conditioner in the current period, wherein the comprehensive monitoring data set includes monitoring temperature data, monitoring humidity data, monitoring cooling capacity data, monitoring power data and monitoring power consumption data;

[0094] A cooling capacity prediction unit is used to input the comprehensive monitoring data set into the trained cooling capacity prediction model to perform cooling capacity prediction and obtain the predicted cooling capacity of the central air conditioner in the next period;

[0095] A combination determination unit, used for traversing and determining all possible refrigeration unit combinations of the central air conditioner, wherein the refrigeration unit combination includes at least one refrigeration unit, and determining the total energy efficiency ratio, total current load rate and total maximum cooling capacity of each refrigeration unit combination;

[0096] A combination screening unit, used for selecting a refrigeration unit combination whose total maximum refrigeration capacity is greater than or equal to the predicted refrigeration capacity in the next period as a candidate refrigeration unit combination;

[0097] A scoring determination unit, used to determine the energy efficiency ratio score of each candidate refrigeration unit combination according to the total energy efficiency ratio of each candidate refrigeration unit combination, determine the current load rate score of each candidate refrigeration unit combination according to the total current load rate of each candidate refrigeration unit combination, and determine the cooling capacity score of each candidate refrigeration unit combination according to the total maximum cooling capacity of each candidate refrigeration unit combination;

[0098] A total score calculation unit, used for adding the energy efficiency ratio score, current load rate score and cooling capacity score of each candidate refrigeration unit combination to obtain a total score of each candidate refrigeration unit combination;

[0099] The combination recommendation unit is used to use the candidate refrigeration unit combination with the highest total score as the recommended refrigeration unit combination for the central air conditioner in the next time period, so as to turn on the refrigeration units included in the recommended refrigeration unit combination in the next time period of the current time period, and shut down the refrigeration units not included in the recommended refrigeration unit combination.

[0100] Embodiment 3:

[0101] This embodiment provides a central air-conditioning refrigeration unit start-stop recommendation system. Figure 3 As shown, at the hardware level, it includes:

[0102] Data interface, used to establish data connection between the processor and the external data terminal;

[0103] A memory for storing instructions;

[0104] The processor is used to read the instructions stored in the memory and execute the central air-conditioning refrigeration unit start-stop recommendation method in Example 1 according to the instructions.

[0105] Optionally, the system further includes an internal bus, through which the processor, the memory and the data interface can be interconnected, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0106] The memory may include, but is not limited to, random access memory (RAM), read only memory (ROM), flash memory, first input first output (FIFO) and / or first in last out (FILO), etc. The processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0107] Embodiment 4:

[0108] This embodiment provides a computer-readable storage medium, on which instructions are stored, and when the instructions are executed on a computer, the computer executes the method for recommending the start and stop of a central air-conditioning refrigeration unit in Embodiment 1. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0109] This embodiment also provides a computer program product, which, when executed on a computer, executes the method for recommending the start and stop of a central air-conditioning refrigeration unit in Embodiment 1. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device.

[0110] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for recommending starting and stopping a central air-conditioning refrigeration unit, characterized in that: include: Collect historical refrigeration capacity data of each single refrigeration unit of the central air-conditioning in each historical time period under actual working conditions; Determine the actual maximum cooling capacity data of each refrigeration unit according to the historical cooling capacity data of each refrigeration unit in each historical time period; Collecting in real time the comprehensive monitoring data set of all refrigeration units of the central air conditioner in the current period, the comprehensive monitoring data set includes monitoring temperature data, monitoring humidity data, monitoring cooling capacity data, monitoring power data and monitoring power consumption data; The comprehensive monitoring data set is input into the trained cooling capacity prediction model to predict the cooling capacity and obtain the predicted cooling capacity of the central air conditioner in the next period; Traverse and determine all possible refrigeration unit combinations of the central air conditioner, wherein the refrigeration unit combination contains at least one refrigeration unit, and determine the total energy efficiency ratio, total current load rate and total maximum cooling capacity of each refrigeration unit combination, including: collecting the average cooling capacity data and average power consumption data of each refrigeration unit in the refrigeration unit combination on the previous day, dividing the average cooling capacity data of the previous day by the average power consumption data of the previous day to obtain the energy efficiency ratio of the corresponding refrigeration unit, adding the energy efficiency ratios of each refrigeration unit in the refrigeration unit combination to obtain the total energy efficiency ratio of the refrigeration unit combination; collecting the rated current of each refrigeration unit in the refrigeration unit combination and the average actual working current of the previous day, dividing the average actual working current of the previous day by the rated current to obtain the current load rate of the corresponding refrigeration unit, adding the current load rates of each refrigeration unit in the refrigeration unit combination to obtain the total current load rate of the refrigeration unit combination; adding the actual maximum cooling capacity data of each refrigeration unit in the refrigeration unit combination to obtain the total maximum cooling capacity of the refrigeration unit combination; The refrigeration unit combination whose total maximum refrigeration capacity is greater than or equal to the predicted refrigeration capacity in the next period is taken as the candidate refrigeration unit combination; Determine the energy efficiency ratio score of each candidate refrigeration unit combination according to the total energy efficiency ratio of each candidate refrigeration unit combination, determine the current load rate score of each candidate refrigeration unit combination according to the total current load rate of each candidate refrigeration unit combination, and determine the cooling capacity score of each candidate refrigeration unit combination according to the total maximum cooling capacity of each candidate refrigeration unit combination; The energy efficiency ratio score, current load rate score and cooling capacity score of each candidate refrigeration unit combination are added together to obtain the total score of each candidate refrigeration unit combination; The candidate refrigeration unit combination with the highest total score is used as the recommended refrigeration unit combination for the central air conditioner in the next time period, so that the refrigeration units included in the recommended refrigeration unit combination will be turned on in the next time period of the current time period, and the refrigeration units not included in the recommended refrigeration unit combination will be turned off.

2. A method for recommending starting and stopping a central air-conditioning refrigeration unit according to claim 1, characterized in that: Determining the actual maximum refrigeration capacity data of each refrigeration unit according to the historical refrigeration capacity data of each refrigeration unit in each historical time period includes: Summarize the historical refrigeration capacity data of the refrigeration unit in each historical time period in ascending order to obtain the corresponding refrigeration capacity data sequence; Map the cooling capacity data sequence to the interval range of [0, 1], so that the minimum value in the cooling capacity data sequence is mapped to 0 and the maximum value is mapped to 1; The interval range of [0, 1] is divided into several sub-interval segments according to the set step size, and each sub-interval segment is mapped to a corresponding cooling capacity data sequence segment; The cooling capacity data sequence segment corresponding to the set sub-interval segment is taken as the target cooling capacity data sequence segment, and the minimum historical cooling capacity data in the target cooling capacity data sequence segment is taken as the actual maximum cooling capacity data of the corresponding refrigeration unit.

3. A method for recommending starting and stopping a central air-conditioning refrigeration unit according to claim 1, characterized in that: Before inputting the comprehensive monitoring data set into the trained refrigeration capacity prediction model to perform refrigeration capacity prediction, the method further includes: Construct a recurrent neural network model, and configure the objective function and constraints of the recurrent neural network model to obtain an initialized recurrent neural network model; Collecting historical comprehensive monitoring data sets of all refrigeration units of the central air conditioner in each historical time period, wherein the historical comprehensive monitoring data sets include historical monitoring temperature data, historical monitoring humidity data, historical monitoring cooling capacity data, historical monitoring power data, and historical monitoring power consumption data; A training set is constructed based on each historical comprehensive monitoring data set, and the initialized recurrent neural network model is trained using the training set to obtain a trained refrigeration capacity prediction model.

4. A method for recommending starting and stopping a central air-conditioning refrigeration unit according to claim 3, characterized in that: When the next time period is within the designated morning time period, the training set is constructed based on each historical comprehensive monitoring data set, including: The historical comprehensive monitoring data sets corresponding to each historical time period in the morning period are selected as the first type of comprehensive monitoring data sets, and the historical monitoring cooling capacity data are extracted from the historical comprehensive monitoring data of the next historical time period of each historical time period as the label of the first type of comprehensive monitoring data set corresponding to each historical time period; Labeling each first-category comprehensive monitoring data set using a label corresponding to each first-category comprehensive monitoring data set to obtain each labeled first-category comprehensive monitoring data set; The training set is composed of the labeled first-category comprehensive monitoring data sets.

5. A method for recommending starting and stopping a central air-conditioning refrigeration unit according to claim 3, characterized in that: When the next time period is within the designated afternoon time period, the training set is constructed based on each historical comprehensive monitoring data set, including: The historical comprehensive monitoring data sets corresponding to each historical time period in the afternoon are selected as the second type of comprehensive monitoring data sets, and the historical monitoring cooling capacity data are extracted from the historical comprehensive monitoring data of the next historical time period of each historical time period as the label of the second type of comprehensive monitoring data set corresponding to each historical time period; Labeling each second-category comprehensive monitoring data set using a label corresponding to each second-category comprehensive monitoring data set to obtain each labeled second-category comprehensive monitoring data set; The training set is composed of the labeled second-category comprehensive monitoring data sets.

6. A method for recommending starting and stopping a central air-conditioning refrigeration unit according to claim 1, characterized in that: The step of determining the energy efficiency ratio score of each candidate refrigeration unit combination according to the total energy efficiency ratio of each candidate refrigeration unit combination, determining the current load rate score of each candidate refrigeration unit combination according to the total current load rate of each candidate refrigeration unit combination, and determining the cooling capacity score of each candidate refrigeration unit combination according to the total maximum cooling capacity of each candidate refrigeration unit combination includes: Rank the energy efficiency ratios of the candidate refrigeration unit combinations in descending order of total energy efficiency ratio, and determine the energy efficiency ratio score of each candidate refrigeration unit combination according to the energy efficiency ratio ranking; The current load rate of each candidate refrigeration unit combination is ranked in descending order according to the total current load rate, and the current load rate score of each candidate refrigeration unit combination is determined according to the current load rate ranking; The cooling capacity of each candidate refrigeration unit combination is ranked in descending order according to the total maximum cooling capacity, and the cooling capacity score of each candidate refrigeration unit combination is determined according to the cooling capacity ranking.

7. A central air conditioning refrigeration unit start-stop recommendation system, characterized in that: It includes a first collection unit, a cooling capacity determination unit, a second collection unit, a cooling capacity prediction unit, a combination determination unit, a combination screening unit, a scoring determination unit, a total score calculation unit and a combination recommendation unit, wherein: The first collection unit is used to collect historical refrigeration capacity data of each single refrigeration unit of the central air conditioner in each historical time period under actual working conditions; A cooling capacity determination unit, used to determine the actual maximum cooling capacity data of each refrigeration unit according to the historical cooling capacity data of each refrigeration unit in each historical time period; The second collection unit is used to collect in real time the comprehensive monitoring data set of all refrigeration units of the central air conditioner in the current period, wherein the comprehensive monitoring data set includes monitoring temperature data, monitoring humidity data, monitoring cooling capacity data, monitoring power data and monitoring power consumption data; A cooling capacity prediction unit is used to input the comprehensive monitoring data set into the trained cooling capacity prediction model to perform cooling capacity prediction and obtain the predicted cooling capacity of the central air conditioner in the next period; A combination determination unit is used to traverse and determine all possible refrigeration unit combinations of the central air conditioner, wherein the refrigeration unit combination contains at least one refrigeration unit, and determine the total energy efficiency ratio, total current load rate and total maximum cooling capacity of each refrigeration unit combination, including: collecting the average cooling capacity data and average power consumption data of each refrigeration unit in the refrigeration unit combination on the previous day, dividing the average cooling capacity data of the previous day by the average power consumption data of the previous day to obtain the energy efficiency ratio of the corresponding refrigeration unit, adding the energy efficiency ratios of each refrigeration unit in the refrigeration unit combination to obtain the total energy efficiency ratio of the refrigeration unit combination; collecting the rated current of each refrigeration unit in the refrigeration unit combination and the average actual working current of the previous day, dividing the average actual working current of the previous day by the rated current to obtain the current load rate of the corresponding refrigeration unit, adding the current load rates of each refrigeration unit in the refrigeration unit combination to obtain the total current load rate of the refrigeration unit combination; adding the actual maximum cooling capacity data of each refrigeration unit in the refrigeration unit combination to obtain the total maximum cooling capacity of the refrigeration unit combination; A combination screening unit, used for selecting a refrigeration unit combination whose total maximum refrigeration capacity is greater than or equal to the predicted refrigeration capacity in the next period as a candidate refrigeration unit combination; A scoring determination unit, used to determine the energy efficiency ratio score of each candidate refrigeration unit combination according to the total energy efficiency ratio of each candidate refrigeration unit combination, determine the current load rate score of each candidate refrigeration unit combination according to the total current load rate of each candidate refrigeration unit combination, and determine the cooling capacity score of each candidate refrigeration unit combination according to the total maximum cooling capacity of each candidate refrigeration unit combination; A total score calculation unit, used for adding the energy efficiency ratio score, current load rate score and cooling capacity score of each candidate refrigeration unit combination to obtain a total score of each candidate refrigeration unit combination; The combination recommendation unit is used to use the candidate refrigeration unit combination with the highest total score as the recommended refrigeration unit combination for the central air conditioner in the next time period, so as to turn on the refrigeration units included in the recommended refrigeration unit combination in the next time period of the current time period, and shut down the refrigeration units not included in the recommended refrigeration unit combination.

8. A central air conditioning refrigeration unit start-stop recommendation system, characterized in that: include: A memory for storing instructions; A processor is used to read the instructions stored in the memory and execute the method for recommending starting and stopping a central air-conditioning refrigeration unit according to any one of claims 1 to 6.

9. A computer program product, characterized in that When the computer program product is run on a computer, the method for recommending starting and stopping a central air-conditioning refrigeration unit according to any one of claims 1 to 6 is executed.

Images