A method and system for compressor switching control based on big data deep learning

Abstract

The present invention discloses a method and system for compressor switching control based on big data deep learning, which is applied to the technical field of air conditioning energy consumption control. The method includes: periodically acquiring a compression working data set of each air handling unit. For any air handling unit, the data in the compression working data set of the air handling unit is grouped according to the number of compressor starts, and first data sets corresponding to different start numbers are obtained respectively. According to the total power and cooling capacity at different compression frequencies in the first data set corresponding to the start number i and the total power and cooling capacity at different compression frequencies in the first data set corresponding to the start number i+1, the frequency switching point when the start number of the compressor increases from i to i+1 is obtained, and the start state of each compressor is switched based on the frequency switching point. The calculation efficiency of the compressor switching point is improved, the compressor switching point can be continuously optimized, and the impact on the system can be avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of air-conditioning energy consumption control, and in particular to a method and system for compressor switching control based on big data deep learning. Background Art

[0002] In the cooling system of a data center, the compressor in the air handling unit is one of the key components, which is responsible for providing the cooling required. The operating status of the compressor (such as the number of units turned on) needs to be adjusted according to the real-time heat load of the data center to ensure cooling efficiency and reduce energy consumption.

[0003] The compressor switching point refers to the critical point of switching from one compressor operating state to another under different heat load conditions, that is, the critical point of increasing the number of compressors turned on. Optimizing the compressor switching points can significantly improve the energy efficiency of data centers because they determine the operating time and energy consumption of the compressors. Existing solutions include gradually adjusting the switching frequency of the compressors in actual operation, recording changes in energy consumption, and using simulation software to optimize the switching points; it also includes installing an energy consumption monitoring system to monitor the operating status and energy consumption of the air handling units in real time, and manually adjusting and optimizing the compressor switching points based on the monitoring data. However, experimental testing may affect the normal operation of the system, and the cost of using simulation software and manual adjustments and optimizations is high.

[0004] Therefore, how to improve the calculation efficiency of the compressor switching point, continuously optimize the compressor switching point, and avoid the impact on the system is a problem that needs to be solved urgently. Summary of the invention

[0005] The embodiment of the present invention provides a method and system for compressor switching control based on big data deep learning, which is used to periodically obtain data sets for calculation, continuously optimize the switching point, adapt to changes in the system operating state, maintain energy-saving effects, and avoid impacts on the system. By comparing the energy consumption and cooling capacity under different numbers of compressors turned on, it is ensured that the cooling effect and stability of the system will not be sacrificed while saving energy. And improve the calculation efficiency of the compressor switching point.

[0006] In a first aspect, an embodiment of the present invention provides a method for compressor switching control based on big data deep learning, comprising:

[0007] Periodically acquiring a compression work data set of each air handling unit; the air handling unit includes at least one compressor, and the compression work data set of the air handling unit includes the total power, cooling capacity, compression frequency and startup status of each compressor corresponding to each time point of the air handling unit in a compressor mixed mode, and the compression frequency represents the frequency of the compressor in the air handling unit;

[0008] For any air handling unit, based on the startup status of each compressor corresponding to each time point in the compression work data set of the air handling unit, the data in the compression work data set of the air handling unit are grouped according to the startup number of the compressors, and first data sets corresponding to different startup numbers are obtained respectively;

[0009] According to the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i and the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i+1, the frequency switching point when the startup number of the compressor increases from i to i+1 is obtained, and the startup state of each compressor is switched based on the frequency switching point, i is an integer greater than or equal to 1 and less than n, n is the number of compressors in the air handling unit, and the frequency switching point is used to indicate the frequency critical point at which the startup number of the compressor switches from i to i+1.

[0010] In the above technical solution, the server periodically obtains the compression work data set of each air handling unit and performs calculations to achieve continuous optimization of the switching point. The compression work data set of the air handling unit includes at least one total power, cooling capacity, compression frequency and startup status of each compressor corresponding to each time point of the air handling unit in the compressor mixed mode. The compression frequency of the air handling unit represents the frequency of the compressor in the air handling unit, that is, the sum of the compression frequencies of the compressors started in the air handling unit. For any air handling unit, the data in the compression work data of the air handling unit are grouped according to the number of compressor starts, and the first data sets corresponding to different start numbers are obtained respectively. It can be understood that each start number corresponds to a first data set. Then, according to the total power and cooling capacity at different compression frequencies in the first data set corresponding to the start number i and the total power and cooling capacity at different compression frequencies in the first data set corresponding to the start number i+1, the frequency switching point when the start number of the compressor increases from i to i+1 is obtained. By comparing the energy consumption and cooling capacity under different compressor start numbers, it is ensured that the cooling effect and stability of the system will not be sacrificed while saving energy.

[0011] Optionally, before periodically acquiring the compressed working data set of each air handling unit, the method further includes:

[0012] Periodically acquiring a working data set of each air handling unit, wherein the working data set includes a working mode, total power, cooling capacity, compression frequency and a start-up state of each compressor of each air handling unit corresponding to each time point, wherein the working mode includes a compressor mixed mode, a spray wet mode and a natural cooling and drying mode;

[0013] Screening is performed based on the working mode of each air handling unit to obtain a compressed working data set of each air handling unit.

[0014] Optionally, based on the startup status of each compressor corresponding to each time point in the compression working data set of the air handling unit, the data in the compression working data set of the air handling unit are grouped according to the startup number of the compressors to obtain first data sets corresponding to different startup numbers, including:

[0015] Based on the startup status of each compressor corresponding to each time point in the compression work data set of the air handling unit, determining the startup number of the compressor corresponding to each time point in the compression work data set;

[0016] According to the startup number of the compressor corresponding to each time point, the data in the compression work data set are grouped to obtain first data sets corresponding to different startup numbers.

[0017] In the above technical solution, the data in the compression work data set are grouped based on the number of compressors started at different time points, which facilitates the comparison of energy consumption and cooling capacity under different numbers of compressors started, avoiding the impact on the system.

[0018] Optionally, obtaining a frequency switching point when the number of starts of the compressor increases from i to i+1 according to the total power and cooling capacity at different compression frequencies in the first data set corresponding to the start number i and the total power and cooling capacity at different compression frequencies in the first data set corresponding to the start number i+1 includes:

[0019] For any first data set in the first data sets corresponding to each startup quantity, classify the data in the first data set according to the compression frequency in the first data set, and calculate the total power average and the cooling capacity average corresponding to each compression frequency;

[0020] The compression frequency corresponding to the time when the average total power in the first data set corresponding to the start number i+1 is less than the average total power in the first data set corresponding to the start number i, and the average cooling capacity in the first data set corresponding to the start number i+1 is greater than the average cooling capacity in the first data set corresponding to the start number i, is used as the frequency switching point when the start number of the compressor is increased from i to i+1.

[0021] In the above technical solution, the compression frequency that meets the conditions is obtained as the frequency switching point based on the total power average and cooling capacity average corresponding to each compression frequency in the two first data sets corresponding to the adjacent start-up numbers, thereby improving the accuracy of determining the compressor switching point.

[0022] Optionally, according to the compression frequency in the first data set, the data in the first data set is classified, and the total power mean value and the cooling capacity mean value corresponding to each compression frequency are calculated, including:

[0023] Classifying the data in the first data set according to the compression frequencies in the first data set to obtain at least one total power and cooling capacity corresponding to each compression frequency;

[0024] For any compression frequency, at least one total power and cooling capacity corresponding to the compression frequency is averaged to obtain the average total power and the average cooling capacity corresponding to the compression frequency.

[0025] In the above technical solution, the data in each first data set is grouped according to the compression frequency, and each compression frequency corresponds to at least one piece of data. Based on the total power and cooling capacity in at least one piece of data corresponding to each compression frequency, the total power mean and cooling capacity mean corresponding to each compression frequency are calculated.

[0026] Optionally, the method further includes:

[0027] If there are multiple compression frequencies corresponding to the time when the average total power in the first data set corresponding to the start number i+1 is less than the average total power in the first data set corresponding to the start number i, and the average cooling capacity in the first data set corresponding to the start number i+1 is greater than the average cooling capacity in the first data set corresponding to the start number i, then the smallest compression frequency among the multiple compression frequencies is used as the frequency switching point when the start number of the compressor is increased from i to i+1.

[0028] Optionally, the compression working data set of the air handling unit may also include the return air temperature, indoor fan speed, supply air temperature and outdoor inlet air temperature corresponding to each time point when the air handling unit is in the compressor mixed mode.

[0029] Optionally, the method further includes:

[0030] For any time point, the cooling capacity corresponding to the time point is calculated based on the return air temperature, indoor fan speed, supply air temperature and outdoor inlet air temperature corresponding to the time point.

[0031] In a second aspect, an embodiment of the present invention provides a system for compressor switching control based on big data deep learning, comprising:

[0032] An acquisition module is used to periodically acquire a compression work data set of each air handling unit; the air handling unit includes at least one compressor, and the compression work data set of the air handling unit includes the total power, cooling capacity, compression frequency and startup status of each compressor corresponding to each time point of the air handling unit in the compressor mixed mode, and the compression frequency represents the frequency of the compressor in the air handling unit;

[0033] a processing module, for grouping data in the compression work data set of the air handling unit according to the start-up number of the compressors in the compression work data set of the air handling unit for any air handling unit, based on the start-up state of each compressor corresponding to each time point in the compression work data set of the air handling unit, to obtain first data sets corresponding to different start-up numbers;

[0034] According to the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i and the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i+1, the frequency switching point when the startup number of the compressor increases from i to i+1 is obtained, and the startup state of each compressor is switched based on the frequency switching point, i is an integer greater than or equal to 1 and less than n, n is the number of compressors in the air handling unit, and the frequency switching point is used to indicate the frequency critical point at which the startup number of the compressor switches from i to i+1.

[0035] Optionally, the processing module is specifically used for:

[0036] Periodically acquiring a working data set of each air handling unit, wherein the working data set includes a working mode, total power, cooling capacity, compression frequency and a start-up state of each compressor of each air handling unit corresponding to each time point, wherein the working mode includes a compressor mixed mode, a spray wet mode and a natural cooling and drying mode;

[0037] Screening is performed based on the working mode of each air handling unit to obtain a compressed working data set of each air handling unit.

[0038] Optionally, the processing module is specifically used for:

[0039] Based on the startup status of each compressor corresponding to each time point in the compression work data set of the air handling unit, determining the startup number of the compressor corresponding to each time point in the compression work data set;

[0040] According to the startup number of the compressor corresponding to each time point, the data in the compression work data set are grouped to obtain first data sets corresponding to different startup numbers.

[0041] Optionally, the processing module is specifically used for:

[0042] For any first data set in the first data sets corresponding to each startup quantity, classify the data in the first data set according to the compression frequency in the first data set, and calculate the total power average and the cooling capacity average corresponding to each compression frequency;

[0043] The compression frequency corresponding to the time when the average total power in the first data set corresponding to the start number i+1 is less than the average total power in the first data set corresponding to the start number i, and the average cooling capacity in the first data set corresponding to the start number i+1 is greater than the average cooling capacity in the first data set corresponding to the start number i, is used as the frequency switching point when the start number of the compressor is increased from i to i+1.

[0044] Optionally, the processing module is specifically used for:

[0045] Classifying the data in the first data set according to the compression frequencies in the first data set to obtain at least one total power and cooling capacity corresponding to each compression frequency;

[0046] For any compression frequency, at least one total power and cooling capacity corresponding to the compression frequency is averaged to obtain the average total power and the average cooling capacity corresponding to the compression frequency.

[0047] Optionally, the processing module is further used for:

[0048] If there are multiple compression frequencies corresponding to the time when the average total power in the first data set corresponding to the start number i+1 is less than the average total power in the first data set corresponding to the start number i, and the average cooling capacity in the first data set corresponding to the start number i+1 is greater than the average cooling capacity in the first data set corresponding to the start number i, then the smallest compression frequency among the multiple compression frequencies is used as the frequency switching point when the start number of the compressor is increased from i to i+1.

[0049] Optionally, the compression working data set of the air handling unit may also include the return air temperature, indoor fan speed, supply air temperature and outdoor inlet air temperature corresponding to each time point when the air handling unit is in the compressor mixed mode.

[0050] Optionally, the processing module is further used for:

[0051] For any time point, the cooling capacity corresponding to the time point is calculated based on the return air temperature, indoor fan speed, supply air temperature and outdoor inlet air temperature corresponding to the time point.

[0052] In a third aspect, an embodiment of the present invention further provides a computer device, including:

[0053] A memory for storing program instructions;

[0054] The processor is used to call the program instructions stored in the memory and execute the above-mentioned compressor switching control method according to the obtained program.

[0055] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned method of compressor switching control based on big data deep learning.

[0056] In a fifth aspect, an embodiment of the present invention further provides a computer program product, which includes an executable program, and the executable program is executed by a processor to implement the above-mentioned method of compressor switching control based on big data deep learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments 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.

[0058] Figure 1 A schematic diagram of a system architecture provided by an embodiment of the present invention;

[0059] Figure 2 A flowchart of a method for compressor switching control based on big data deep learning provided by an embodiment of the present invention;

[0060] Figure 3 A structural schematic diagram of a system for compressor switching control based on big data deep learning provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] The application scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions protected by the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. It is known to those of ordinary skill in the art that with the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems. The terms "first" and "second" in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In the description of the present application, unless otherwise specified, the meaning of "multiple" is two or more.

[0063] Before introducing a method for compressor switching control based on big data deep learning provided in an embodiment of the present application, in order to facilitate understanding, the background technology involved in the embodiment of the present application is first introduced below.

[0064] Data centers are the core of modern information technology infrastructure, carrying a large amount of computing tasks and data storage. In order to ensure the stable operation and high performance of data centers, their environment must be strictly controlled in temperature and humidity. This usually involves the use of efficient cooling systems to prevent equipment from overheating. Indirect evaporative cooling is an energy-saving cooling technology that absorbs heat by using the evaporation of water to reduce the air temperature. Unlike direct evaporative cooling, indirect evaporative cooling does not increase the humidity of the air, making it more suitable for humidity-sensitive environments such as data centers.

[0065] In the cooling system of a data center, the compressor is one of the key components, which is responsible for providing the cooling capacity required. The operating status of the compressor (such as the number of units turned on) needs to be adjusted according to the real-time heat load of the data center to ensure cooling efficiency and reduce energy consumption. The compressor switching point refers to the critical point when switching from one compressor operating state to another under different heat load conditions. Optimizing these switching points can significantly improve the energy efficiency of the data center because they determine the operating time and energy consumption of the compressor. Existing solutions include:

[0066] Load analysis and energy consumption data collection: Analyze the load changes of AHU (air handling unit) in different seasons and time periods, collect energy consumption data, and understand the optimal operating frequency of the compressor under different loads. However, it may require a lot of data collection and analysis work, and the initial investment is large.

[0067] Experimental testing and simulation optimization: gradually adjust the switching frequency of the compressor in actual operation, record the energy consumption changes, and use simulation software to optimize the switching point. However, experimental testing may affect the normal operation of the system, simulation software may require professional operation, and the initial cost is high.

[0068] Continuous monitoring and adjustment: Install an energy consumption monitoring system to monitor the operating status and energy consumption of the AHU in real time, and continuously adjust and optimize the compressor switching point based on the monitoring data. However, the introduction of a monitoring system will increase the complexity and maintenance cost of the system, and requires operators to have certain professional knowledge.

[0069] Expert consultation and training: Consult experts in the HVAC field to obtain their experience and suggestions, and train operators. However, expert consultation may require additional fees, and operator training also takes time and costs.

[0070] Figure 1 A system architecture applicable to an embodiment of the present invention is exemplarily shown. The system architecture includes a server 100 . The server 100 may include a processor 110 , a communication interface 120 , and a memory 130 .

[0071] The communication interface 120 is used to transmit data with the air handling unit.

[0072] The processor 110 is the control center of the server 100, and uses various interfaces and routes to connect various parts of the entire server 100, and executes various functions of the server 100 and processes data by running or executing software programs and / or modules stored in the memory 130, and calling data stored in the memory 130. Optionally, the processor 110 may include one or more processing units.

[0073] The memory 130 can be used to store software programs and modules. The processor 110 executes various functional applications and data processing by running the software programs and modules stored in the memory 130. The memory 130 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc.; the data storage area can store data created according to business processing, etc. In addition, the memory 130 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0074] It should be noted that the above Figure 1 The structure shown is only an example and is not limited to this embodiment of the present invention.

[0075] Based on the above description, Figure 2 A flow chart of a method for compressor switching control based on big data deep learning provided by an embodiment of the present invention is exemplarily shown, and the flow chart can be executed by a system for compressor switching control based on big data deep learning.

[0076] like Figure 2 As shown in the figure, the process specifically includes:

[0077] Step 210, periodically obtain the compression working data set of each air handling unit; the air handling unit includes at least one compressor, and the compression working data set of the air handling unit includes the total power, cooling capacity, compression frequency and start-up status of each compressor corresponding to each time point of the air handling unit in the compressor mixed mode, and the compression frequency represents the frequency of the compressor in the air handling unit.

[0078] In an embodiment of the present invention, the server periodically obtains a compressed working data set of each air handling unit. The period may be preset based on experience, such as obtaining a compressed working data set once an hour for switching point calculation, which is not specifically limited here. The air handling unit includes at least one compressor, for example, one air handling unit has four compressors. The number of air handling units is the number of air handling units in the data center for which the switching point needs to be calculated, for example, there are 20 air handling units in a data center, and the number of air handling units is not specifically limited here.

[0079] The compression work data set of the air handling unit includes the total power, cooling capacity, compression frequency and startup status of each compressor at each time point of the air handling unit in the compressor mixed mode. Among them, the compression frequency represents the frequency of the compressor in the air handling unit, that is, the sum of the frequencies of the compressors started in the air handling unit.

[0080] In some embodiments, the cooling capacity can be calculated by the data center, directly obtained by the server, or calculated after obtaining other data. For example, the server obtains the return air temperature, indoor fan speed, supply air temperature and outdoor inlet air temperature corresponding to each time point, and then for any time point, the cooling capacity corresponding to the time point is calculated according to the return air temperature, indoor fan speed, supply air temperature and outdoor inlet air temperature corresponding to the time point. The method of obtaining and calculating the cooling capacity is not specifically limited here.

[0081] In a possible implementation, the server periodically obtains the working data set of each air handling unit before obtaining the compressed working data set of each air handling unit. The working data set includes the working mode, total power, cooling capacity, compression frequency and startup status of each compressor of each air handling unit corresponding to each time point. Among them, each time point can be set based on experience, for example, one data every five minutes, which is not specifically limited here. The working mode includes a compressor mixed mode, a spray wet mode and a natural cold dry mode. Exemplarily, the python language Pandas is used to read the full amount of csv data, and the full amount of csv data includes the working data of 20 air handling units in a data center room. Then, based on the air handling unit identification and address included in each working data, the full amount of csv data is grouped to obtain the working data set of each air handling unit.

[0082] The compressed working data set of each air handling unit is obtained by filtering based on the working mode of each air handling unit. Specifically, for any air handling unit, the data in the working data set of the air handling unit is filtered according to the working mode of each data in the working data set of the air handling unit to obtain the compressed working data set of the air handling unit.

[0083] Step 220, for any air handling unit, based on the startup status of each compressor corresponding to each time point in the compression working data set of the air handling unit, the data in the compression working data set of the air handling unit are grouped according to the startup number of the compressors, and first data sets corresponding to different startup numbers are obtained respectively.

[0084] In an embodiment of the present invention, for any air handling unit, based on the startup status of each compressor included in each data in the compression work data set of the air handling unit, the data in the compression work data set of the air handling unit are grouped according to the startup number of the compressors, and first data sets corresponding to different startup numbers are obtained. Specifically, based on the startup status of each compressor corresponding to each time point in the compression work data set of the air handling unit, the startup number of the compressor corresponding to each time point in the compression work data set is determined. Then, according to the startup number of the compressor corresponding to each time point, the data in the compression work data set is grouped, and first data sets corresponding to different startup numbers are obtained. Exemplarily, there are 4 compressors in an air handling unit, and the server groups the data based on the startup number of the compressors through groupby, and obtains the first data set corresponding to the startup number of 1, the first data set corresponding to the startup number of 2, the first data set corresponding to the startup number of 3, and the first data set corresponding to the startup number of 4.

[0085] Step 230, according to the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i and the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i+1, obtain the frequency switching point when the startup number of the compressor increases from i to i+1, and switch the startup state of each compressor based on the frequency switching point, i is an integer greater than or equal to 1 and less than n, n is the number of compressors in the air handling unit, and the frequency switching point is used to indicate the frequency critical point when the startup number of the compressor switches from i to i+1.

[0086] In an embodiment of the present invention, for a plurality of first data sets corresponding to any air handling unit, the frequency switching point when the start number of the compressor increases from i to i+1 is obtained according to the total power and cooling capacity at different compression frequencies in the first data set corresponding to the start number i and the total power and cooling capacity at different compression frequencies in the first data set corresponding to the start number i+1. Specifically, for any first data set in the first data sets corresponding to each start number, the data in the first data set is classified according to the compression frequency in the first data set, and the mean total power and the mean cooling capacity corresponding to each compression frequency are calculated. Exemplarily, each first data set is grouped according to the compression frequency through groupby. The first data set corresponding to the start number 1 includes multiple compression frequencies. For any compression frequency, the data corresponding to the compression frequency in the first data set is extracted to obtain at least one piece of data, and then the mean total power and the mean cooling capacity in the at least one piece of data are calculated. The dataframe data row index is reset, and the dataframe data features are renamed, compression frequency: Frequency, air conditioning total power: power, cooling capacity. For example, the code is as follows:

[0087] grouped_df = df.groupby('AHU compressor frequency').agg({'air conditioning total power':'mean','cooling capacity':'mean'}).reset_index()

[0088] grouped_df.columns=['Frequency','power','Cooling_Capacity']

[0089] And the total power average value and the cooling capacity average value in the first data set are sorted in ascending order according to the compression frequency.

[0090] In some embodiments, a data sliding window is also performed on the total power mean value and the cooling capacity mean value in each first data set to reduce data noise. For example, the code is as follows:

[0091] rolling_df=round_df.rolling(window=window_size).mean()

[0092] Note: window_size, users can determine the window size of the data sliding window according to their needs.

[0093] Then, the compression frequency corresponding to the time when the total power mean value in the first data set corresponding to the start number i+1 is less than the total power mean value in the first data set corresponding to the start number i, and the average cooling capacity in the first data set corresponding to the start number i+1 is greater than the average cooling capacity in the first data set corresponding to the start number i, is used as the frequency switching point when the start number of the compressor is increased from i to i+1. Exemplarily, taking i as 1 as an example, the compression frequency corresponding to the time when the total power mean value in the first data set corresponding to the start number 2 is less than the total power mean value in the first data set corresponding to the start number 1, and the average cooling capacity in the first data set corresponding to the start number 2 is greater than the average cooling capacity in the first data set corresponding to the start number 1, is used as the frequency switching point when the start number of the compressor is increased from 1 to 2. Repeat the calculation until the frequency switching point when the start number of the compressor is increased from 2 to 3 and the frequency switching point when the start number of the compressor is increased from 3 to 4 are obtained.

[0094] Finally, the frequency switching point when the number of compressors started in each air handling unit increases from i to i+1 is calculated, and the start-up state of each compressor is switched based on the frequency switching point obtained above.

[0095] In some embodiments, the obtained frequency switching points will also be stored in Redis, TDengine and Mysql respectively. They will be stored in the Redis database for real-time display, in the TDengine database for historical data display, and in the Mysql database for front-end and back-end interaction and some back-end function development.

[0096] In one possible implementation, if there are multiple compression frequencies corresponding to the first data set when the start number is i+1 and the average total power in the first data set corresponding to the start number is i+1 is less than the average total power in the first data set corresponding to the start number is i, and the average cooling capacity in the first data set corresponding to the start number is i+1 is greater than the average cooling capacity in the first data set corresponding to the start number is i, then the smallest compression frequency among the multiple compression frequencies is used as the frequency switching point when the start number of the compressor is increased from i to i+1.

[0097] In an embodiment of the present invention, a timed task is used to obtain the working data of the air handling unit at a regular time, and the data pulled at a regular time each time will be appended downward to obtain a working data of a data increment, and then the switching point of the compressor is determined, so that the compressor load switching point corresponding to each air handling unit is more accurate. When determining the switching point, by comparing the energy consumption and cooling capacity under different numbers of compressors turned on, it is ensured that the cooling effect and stability of the system are not sacrificed while saving energy. And through refined data analysis and dynamic adjustment, the energy-saving compressor switching point can be found more accurately, thereby achieving better energy-saving effects. The overall process of the present invention can be executed automatically, reducing manual intervention and improving computing efficiency. At the same time, the design of the present invention has a certain degree of scalability and can adapt to possible expansion needs in the future.

[0098] Based on the same technical concept, Figure 3 The structural diagram of a system for compressor switching control based on big data deep learning provided by an embodiment of the present invention is exemplarily shown. The system can execute the process of a method for compressor switching control based on big data deep learning.

[0099] like Figure 3 As shown, the system specifically includes:

[0100] The acquisition module 310 is used to periodically acquire a compression work data set of each air handling unit; the air handling unit includes at least one compressor, and the compression work data set of the air handling unit includes the total power, cooling capacity, compression frequency and startup status of each compressor corresponding to each time point of the air handling unit in the compressor mixed mode, and the compression frequency represents the frequency of the compressor in the air handling unit;

[0101] The processing module 320 is used for grouping the data in the compression work data set of the air handling unit according to the start-up number of the compressors based on the start-up state of each compressor corresponding to each time point in the compression work data set of the air handling unit, and obtaining first data sets corresponding to different start-up numbers respectively;

[0102] According to the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i and the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i+1, the frequency switching point when the startup number of the compressor increases from i to i+1 is obtained, and the startup state of each compressor is switched based on the frequency switching point, i is an integer greater than or equal to 1 and less than n, n is the number of compressors in the air handling unit, and the frequency switching point is used to indicate the frequency critical point at which the startup number of the compressor switches from i to i+1.

[0103] Optionally, the processing module 320 is specifically used for:

[0104] Periodically acquiring a working data set of each air handling unit, wherein the working data set includes a working mode, total power, cooling capacity, compression frequency and a start-up state of each compressor of each air handling unit corresponding to each time point, wherein the working mode includes a compressor mixed mode, a spray wet mode and a natural cooling and drying mode;

[0105] Screening is performed based on the working mode of each air handling unit to obtain a compressed working data set of each air handling unit.

[0106] Optionally, the processing module 320 is specifically used for:

[0107] Based on the startup status of each compressor corresponding to each time point in the compression work data set of the air handling unit, determining the startup number of the compressor corresponding to each time point in the compression work data set;

[0108] According to the startup number of the compressor corresponding to each time point, the data in the compression work data set are grouped to obtain first data sets corresponding to different startup numbers.

[0109] Optionally, the processing module 320 is specifically used for:

[0110] For any first data set in the first data sets corresponding to each startup quantity, classify the data in the first data set according to the compression frequency in the first data set, and calculate the total power average and the cooling capacity average corresponding to each compression frequency;

[0111] The compression frequency corresponding to the time when the average total power in the first data set corresponding to the start number i+1 is less than the average total power in the first data set corresponding to the start number i, and the average cooling capacity in the first data set corresponding to the start number i+1 is greater than the average cooling capacity in the first data set corresponding to the start number i, is used as the frequency switching point when the start number of the compressor is increased from i to i+1.

[0112] Optionally, the processing module 320 is specifically used for:

[0113] Classifying the data in the first data set according to the compression frequencies in the first data set to obtain at least one total power and cooling capacity corresponding to each compression frequency;

[0114] For any compression frequency, at least one total power and cooling capacity corresponding to the compression frequency is averaged to obtain the average total power and the average cooling capacity corresponding to the compression frequency.

[0115] Optionally, the processing module 320 is further used for:

[0116] If there are multiple compression frequencies corresponding to the time when the average total power in the first data set corresponding to the start number i+1 is less than the average total power in the first data set corresponding to the start number i, and the average cooling capacity in the first data set corresponding to the start number i+1 is greater than the average cooling capacity in the first data set corresponding to the start number i, then the smallest compression frequency among the multiple compression frequencies is used as the frequency switching point when the start number of the compressor is increased from i to i+1.

[0117] Optionally, the compression working data set of the air handling unit may also include the return air temperature, indoor fan speed, supply air temperature and outdoor inlet air temperature corresponding to each time point when the air handling unit is in the compressor mixed mode.

[0118] Optionally, the processing module 320 is further used for:

[0119] For any time point, the cooling capacity corresponding to the time point is calculated based on the return air temperature, indoor fan speed, supply air temperature and outdoor inlet air temperature corresponding to the time point.

[0120] Based on the same technical concept, an embodiment of the present invention further provides a computer device, including:

[0121] A memory for storing program instructions;

[0122] The processor is used to call the program instructions stored in the memory and execute the above-mentioned method of compressor switching control based on big data deep learning according to the obtained program.

[0123] Based on the same technical concept, an embodiment of the present invention also provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned compressor switching control method based on big data deep learning.

[0124] Based on the same technical concept, an embodiment of the present invention also provides a computer program product, characterized in that the computer program product includes an executable program, which is executed by a processor to implement the above-mentioned method of compressor switching control based on big data deep learning.

[0125] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0126] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0127] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0128] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0129] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for compressor switching control based on big data deep learning, characterized in that: include: Periodically acquiring a compression work data set of each air handling unit; the air handling unit includes at least one compressor, and the compression work data set of the air handling unit includes the total power, cooling capacity, compression frequency and startup status of each compressor corresponding to each time point of the air handling unit in a compressor mixed mode, and the compression frequency represents the frequency of the compressor in the air handling unit; For any air handling unit, based on the startup status of each compressor corresponding to each time point in the compression work data set of the air handling unit, the data in the compression work data set of the air handling unit are grouped according to the startup number of the compressors, and first data sets corresponding to different startup numbers are obtained respectively; According to the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i and the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i+1, the frequency switching point when the startup number of the compressor increases from i to i+1 is obtained, and the startup state of each compressor is switched based on the frequency switching point, i is an integer greater than or equal to 1 and less than n, n is the number of compressors in the air handling unit, and the frequency switching point is used to indicate the frequency critical point at which the startup number of the compressor switches from i to i+1.

2. The method according to claim 1, characterized in that Before periodically acquiring the compressed working data set of each air handling unit, the method further includes: Periodically acquiring a working data set of each air handling unit, wherein the working data set includes a working mode, total power, cooling capacity, compression frequency and a start-up state of each compressor of each air handling unit corresponding to each time point, wherein the working mode includes a compressor mixed mode, a spray wet mode and a natural cooling and drying mode; Screening is performed based on the working mode of each air handling unit to obtain a compressed working data set of each air handling unit.

3. The method according to claim 1, characterized in that Based on the startup status of each compressor corresponding to each time point in the compression work data set of the air handling unit, the data in the compression work data set of the air handling unit are grouped according to the startup number of the compressors, and first data sets corresponding to different startup numbers are obtained respectively, including: Based on the startup status of each compressor corresponding to each time point in the compression work data set of the air handling unit, determining the startup number of the compressor corresponding to each time point in the compression work data set; According to the startup number of the compressor corresponding to each time point, the data in the compression work data set are grouped to obtain first data sets corresponding to different startup numbers.

4. The method according to claim 1, characterized in that According to the total power and cooling capacity at different compression frequencies in the first data set corresponding to the start number i and the total power and cooling capacity at different compression frequencies in the first data set corresponding to the start number i+1, the frequency switching point when the start number of the compressor increases from i to i+1 is obtained, including: For any first data set in the first data sets corresponding to each startup quantity, classify the data in the first data set according to the compression frequency in the first data set, and calculate the total power average and the cooling capacity average corresponding to each compression frequency; The compression frequency corresponding to the time when the average total power in the first data set corresponding to the start number i+1 is less than the average total power in the first data set corresponding to the start number i, and the average cooling capacity in the first data set corresponding to the start number i+1 is greater than the average cooling capacity in the first data set corresponding to the start number i, is used as the frequency switching point when the start number of the compressor is increased from i to i+1.

5. The method according to claim 4, characterized in that According to the compression frequency in the first data set, the data in the first data set are classified, and the total power average and the cooling capacity average corresponding to each compression frequency are calculated, including: Classifying the data in the first data set according to the compression frequencies in the first data set to obtain at least one total power and cooling capacity corresponding to each compression frequency; For any compression frequency, at least one total power and cooling capacity corresponding to the compression frequency is averaged to obtain the average total power and the average cooling capacity corresponding to the compression frequency.

6. The method according to claim 4, characterized in that The method further comprises: If there are multiple compression frequencies corresponding to the time when the average total power in the first data set corresponding to the start number i+1 is less than the average total power in the first data set corresponding to the start number i, and the average cooling capacity in the first data set corresponding to the start number i+1 is greater than the average cooling capacity in the first data set corresponding to the start number i, then the smallest compression frequency among the multiple compression frequencies is used as the frequency switching point when the start number of the compressor is increased from i to i+1.

7. The method according to claim 1, characterized in that The compression working data set of the air handling unit may also include the return air temperature, indoor fan speed, supply air temperature and outdoor inlet air temperature corresponding to each time point when the air handling unit is in the compressor mixed mode.

8. The method according to claim 7, characterized in that The method further comprises: For any time point, the cooling capacity corresponding to the time point is calculated based on the return air temperature, indoor fan speed, supply air temperature and outdoor inlet air temperature corresponding to the time point.

9. A compressor switching control system based on big data deep learning, characterized in that: include: An acquisition module is used to periodically acquire a compression work data set of each air handling unit; the air handling unit includes at least one compressor, and the compression work data set of the air handling unit includes the total power, cooling capacity, compression frequency and startup status of each compressor corresponding to each time point of the air handling unit in the compressor mixed mode, and the compression frequency represents the frequency of the compressor in the air handling unit; A processing module, for any air handling unit, based on the startup status of each compressor corresponding to each time point in the compression work data set of the air handling unit, and according to the startup number of the compressor, grouping the data in the compression work data set of the air handling unit to obtain first data sets corresponding to different startup numbers; According to the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i and the total power and cooling capacity at different compression frequencies in the first data set corresponding to when the startup number is i+1, the frequency switching point when the startup number of the compressor increases from i to i+1 is obtained, and the startup state of each compressor is switched based on the frequency switching point, i is an integer greater than or equal to 1 and less than n, n is the number of compressors in the air handling unit, and the frequency switching point is used to indicate the frequency critical point at which the startup number of the compressor switches from i to i+1.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the method according to any one of claims 1 to 8.

Images