Cold machine combination determination method and apparatus, device, and storage medium

Abstract

Embodiments of the present disclosure provide a cold unit combination determination method and device, equipment and storage medium, which are applied to the technical field of building energy management. The method comprises: predicting total refrigeration capacity provided by an air conditioning system in a next time period; determining one or more cold unit combinations in the air conditioning system that meet refrigeration requirements according to the total refrigeration capacity; for any cold unit combination, dividing the total refrigeration capacity into multiple target refrigeration capacities according to rated refrigeration capacities of each cold unit in the cold unit combination, and distributing the target refrigeration capacities to the corresponding cold units; calculating the thermodynamic perfection of each cold unit according to the target refrigeration capacity and the rated refrigeration capacity of each cold unit in the cold unit combination, and calculating the opening value index of the cold unit combination; and determining the cold unit combination with the maximum opening value index as the cold unit combination to be started in the air conditioning system in the next time period. In this way, the appropriate cold unit combination in the next time period can be quickly determined, thereby improving the overall operation efficiency of the water chiller and saving energy.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of building energy management, and particularly relates to a cold machine combination determination method and device, equipment and a storage medium. BACKGROUND

[0002] At present, most buildings are equipped with air conditioning systems. For large commercial buildings, multiple cold machines are often used in the air conditioning system to cope with the changes in indoor cooling load. When the indoor load changes, the refrigerating capacity of the air conditioning system is changed by changing the start-stop state of the cold machine.

[0003] The traditional cold machine combination determination scheme is usually based on the rated refrigerating capacity of the cold machine. Only when the refrigerating capacity is close to the design value, an additional cold machine will be started. This results in a low coefficient of performance (COP) of the cold machine during actual operation, and accordingly, the energy consumption of the cold machine combination is also high. Therefore, how to determine a suitable cold machine combination has become a technical problem to be solved. SUMMARY

[0004] The present disclosure provides a cold machine combination determination method, device, equipment and storage medium.

[0005] In a first aspect, the embodiments of the present disclosure provide a cold machine combination determination method, which comprises:

[0006] predicting a total refrigerating capacity required by the air conditioning system in a next time period;

[0007] determining one or more cold machine combinations in the air conditioning system that meet the refrigerating demand according to the total refrigerating capacity and the rated refrigerating capacity of each cold machine;

[0008] calculating the thermodynamic perfection of each cold machine according to the target refrigerating capacity and the rated refrigerating capacity of each cold machine in the cold machine combination, and calculating the opening value index of the cold machine combination according to the thermodynamic perfection of each cold machine in the cold machine combination; and determining the cold machine combination with the largest opening value index as the cold machine combination to be started in the air conditioning system in the next time period.

[0009] In some implementable manners of the first aspect, the total refrigerating capacity required by the air conditioning system in the next time period is predicted by:

[0010] inputting the air conditioning system feature data at the current time into a pre-trained total refrigerating capacity prediction model to obtain the total refrigerating capacity required by the air conditioning system in the next time period, wherein the air conditioning system feature data comprises time data, meteorological data of the building to which the air conditioning system belongs, and historical refrigerating capacity data of the air conditioning system.

[0011] In some possible implementation manners of the first aspect, the total refrigeration capacity prediction model is obtained by training a preset neural network using a training data set, wherein a sample in the training data set takes air conditioning system feature data at a certain moment as sample feature data, and takes actual total refrigeration capacity provided by the air conditioning system in a next time period at the certain moment as a label.

[0012] In some possible implementation manners of the first aspect, the one or more chiller combinations meeting the refrigeration demand in the air conditioning system are determined according to the total refrigeration capacity and the rated refrigeration capacities of the chillers, including:

[0013] The one or more chiller combinations in the air conditioning system with a total rated refrigeration capacity greater than or equal to the total refrigeration capacity are determined according to the total refrigeration capacity and the rated refrigeration capacities of the chillers.

[0014] In some possible implementation manners of the first aspect, the target refrigeration capacities of the chillers in the chiller combination are determined by the following steps:

[0015] The total refrigeration capacity is divided into multiple target refrigeration capacities according to the proportions of the rated refrigeration capacities of the chillers in the chiller combination in the total rated refrigeration capacity, and the target refrigeration capacities are distributed to the corresponding chillers.

[0016] In some possible implementation manners of the first aspect, the thermal perfection degrees of the chillers are calculated according to the target refrigeration capacities and the rated refrigeration capacities of the chillers in the chiller combination, including:

[0017] The thermal perfection degrees of the chillers are calculated according to the target refrigeration capacities and the rated refrigeration capacities of the chillers in the chiller combination, and the thermal perfection degrees of the chillers are calculated according to the PLRs of the chillers.

[0018] In some possible implementation manners of the first aspect, the method further includes:

[0019] calculating a coincidence degree of the chiller combination and a currently running chiller combination;

[0020] The opening value index of the chiller combination is calculated according to the thermal perfection degrees of the chillers in the chiller combination, including:

[0021] The average thermal perfection degree of the chiller combination is calculated according to the thermal perfection degrees of the chillers in the chiller combination.

[0022] The opening value index of the chiller combination is obtained by weighted summation of the average thermal perfection degree and the coincidence degree corresponding to the chiller combination.

[0023] In the second aspect, embodiments of the present disclosure provide a chiller combination determination device, which includes:

[0024] The prediction module is configured to predict a total refrigeration capacity required to be provided by the air conditioning system in a next time period;

[0025] The determination module is used to determine one or more combinations of chillers in the air conditioning system that meet the cooling requirements, based on the total cooling capacity and the rated cooling capacity of each chiller.

[0026] The calculation module is used to calculate the thermal completeness of each chiller in the chiller combination based on the target cooling capacity and rated cooling capacity of each chiller; and to calculate the start-up value index of the chiller combination based on the thermal completeness of each chiller in the chiller combination; and to determine the chiller combination with the highest start-up value index as the chiller combination to be turned on by the air conditioning system in the next time period.

[0027] Thirdly, embodiments of this disclosure provide an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; the memory storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the methods described above.

[0028] Fourthly, embodiments of this disclosure provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the methods described above.

[0029] In the embodiments of this disclosure, the total cooling capacity required by the air conditioning system in the next time period can be predicted to determine the chiller combination that meets the cooling demand in the next time period. Then, the thermal perfection of each chiller in the chiller combination can be calculated, and the start-up value index of the chiller combination can be calculated based on the thermal perfection with strong operating efficiency evaluation capability. In this way, the appropriate chiller combination in the next time period can be accurately determined, thereby improving the overall operating efficiency of the chiller combination and reducing operating energy consumption.

[0030] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0031] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. The drawings are provided for a better understanding of the invention and are not intended to limit the scope of this disclosure. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0032] Figure 1 A flowchart of a chiller combination determination method provided by an embodiment of the present disclosure is shown;

[0033] Figure 2 A structural diagram of a refrigeration unit combination determination device provided by an embodiment of the present disclosure is shown;

[0034] Figure 3 A structural diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0036] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0037] To address the problems in the background art, embodiments of this disclosure provide a method, apparatus, device, and storage medium for determining chiller combinations. Specifically, the method involves predicting the total cooling capacity required by the air conditioning system in the next time period; determining one or more chiller combinations in the air conditioning system that meet the cooling demand based on the total cooling capacity; for any chiller combination, dividing the total cooling capacity into multiple target cooling capacities based on the rated cooling capacity of each chiller in the combination, and allocating them to the corresponding chillers; calculating the thermal completeness of each chiller based on its target cooling capacity and rated cooling capacity, and using this to calculate the activation value index of the chiller combination; and determining the chiller combination with the highest activation value index as the chiller combination to be activated by the air conditioning system in the next time period.

[0038] In this way, by predicting the total cooling capacity required by the air conditioning system in the next time period, the appropriate chiller combination to meet the cooling demand in the next time period can be determined. Then, the thermal completeness of each chiller in the chiller combination can be calculated, and the start-up value index of the chiller combination can be calculated based on the thermal completeness with strong operational efficiency evaluation capabilities. This can accurately determine the appropriate chiller combination in the next time period, thereby improving the overall operating efficiency of the chiller combination and reducing operating energy consumption.

[0039] The following detailed description, with reference to the accompanying drawings, illustrates the chiller combination determination method, apparatus, equipment, and storage medium provided in the embodiments of this disclosure through specific examples.

[0040] Figure 1 A flowchart illustrating a method for determining a chiller combination according to an embodiment of this disclosure is shown, such as... Figure 1As shown, the refrigeration unit combination determination method 100 may include the following steps:

[0041] S110, predicts the total cooling capacity that the air conditioning system needs to provide in the next time period.

[0042] In some embodiments, the total cooling capacity required by the air conditioning system in the next time period (e.g., 1 hour) can be predicted based on the current air conditioning system characteristic data.

[0043] The characteristic data of the air conditioning system may include: time data (e.g., which specific hour in a 24-hour day, which specific day in a 7-day week, whether it is a weekday or a holiday, etc.), meteorological data of the building to which the air conditioning system belongs (e.g., dry bulb temperature, relative humidity, dew point temperature, solar radiation, wind speed, etc.), and historical cooling capacity data of the air conditioning system (e.g., cooling capacity data for each day or hour previously, etc.).

[0044] For example, the current air conditioning system feature data can be input into a pre-trained total cooling capacity prediction model. The total cooling capacity prediction model processes the input data to quickly obtain the total cooling capacity that the air conditioning system needs to provide in the next time period, thereby effectively improving the prediction effect.

[0045] The total cooling capacity prediction model is obtained by training a preset neural network (such as a convolutional neural network, a recurrent neural network, a long short-term memory neural network, etc.) using a training dataset. The samples in the training dataset use the characteristic data of the air conditioning system at a certain moment as the sample feature data, and the actual total cooling capacity provided by the air conditioning system in the next time period is used as the label.

[0046] As an example, the training process for a total cooling capacity prediction model can be as follows:

[0047] (1) Preprocess the samples according to the “3σ” rule, remove outliers and fill in missing data, and allocate 80% of the processed samples as the training dataset and 20% as the test dataset.

[0048] (2) Perform sample feature expansion on the samples in the training dataset, that is, extract high-dimensional features from the sample feature data.

[0049] Specifically, high-dimensional feature extraction is performed on time data to obtain time index, date type, etc.

[0050] High-dimensional feature extraction is performed on the meteorological data of the building to which the air conditioning system is located to obtain smoothed meteorological data, differential meteorological data, etc. A smoothing filter is used to remove high-frequency fluctuations in the meteorological data to preserve the data trend and change. The first and second derivatives of the meteorological data are then calculated. The first derivative is used as smoothed meteorological data and the second derivative is used as differential meteorological data.

[0051] High-dimensional feature extraction is performed on historical cooling capacity data of air conditioning systems to obtain periodic data, statistical data, etc.

[0052] (3) The Elite Genetic Algorithm (EGA) is used to select high-dimensional features (time index, date type, smoothed meteorological data, differential meteorological data, periodic data, statistical data, etc.) of the samples in the training dataset after the sample features are expanded, and the hyperparameters of the preset neural network are tuned.

[0053] (4) Delete the high-dimensional features of the samples that were not selected in the training dataset, train the optimized preset neural network according to the latest training dataset, and test the trained preset neural network according to the test dataset. If the test results meet the requirements, the trained preset neural network will be used as the total cooling capacity prediction model.

[0054] S120, based on the total cooling capacity and the rated cooling capacity of each chiller, determines one or more chiller combinations in the air conditioning system that meet the cooling requirements.

[0055] In some embodiments, based on the total cooling capacity and the rated cooling capacity of each chiller, one or more chiller combinations in the air conditioning system with a total rated cooling capacity greater than or equal to the total cooling capacity can be easily and quickly identified as one or more chiller combinations that meet the cooling requirements.

[0056] S130: Calculate the thermal completeness of each chiller in the chiller combination based on the target cooling capacity and rated cooling capacity of each chiller; and calculate the start-up value index of the chiller combination based on the thermal completeness of each chiller in the chiller combination; and determine the chiller combination with the highest start-up value index as the chiller combination to be turned on in the air conditioning system in the next time period.

[0057] The target cooling capacity is the cooling capacity that the chiller needs to provide in the next time period. For example, it can be determined through the following steps:

[0058] Based on the proportion of the rated cooling capacity of each chiller in the chiller combination to the total customized cooling capacity, the total cooling capacity is divided into multiple target cooling capacities and allocated to the corresponding chillers.

[0059] For example, the total cooling capacity is 12000W, and the chiller combination includes chillers 1-5. The rated cooling capacities of chillers 1-5 are 2000W, 2000W, 3000W, 4000W, and 4000W, respectively. In this case, the calculated proportions of the rated cooling capacities of chillers 1-5 in the total customized cooling capacity of 15000W are 2 / 15, 2 / 15, 3 / 15, 4 / 15, and 4 / 15, respectively. Therefore, the total cooling capacity is divided into 1600W, 1600W, 2400W, 3200W, and 3200W, and 1600W, 1600W, 2400W, 3200W, and 3200W are allocated to chillers 1-5 respectively.

[0060] In this way, the PLR ​​of each chiller in the same chiller combination can be consistent based on the proportion of rated cooling capacity, so that each chiller is in a high-efficiency state.

[0061] In some embodiments, the PLR ​​of each chiller can be calculated based on the target cooling capacity and rated cooling capacity of each chiller in the chiller assembly, and the thermal perfection of each chiller can be calculated accurately and quickly based on the PLR ​​of each chiller.

[0062] For example, the PLR ​​of each chiller can be calculated according to formula (1). Formula (1) is shown below:

[0063]

[0064] The thermal perfection of each chiller can be calculated using formula (2) corresponding to each chiller. Formula (2) is shown below:

[0065]

[0066] in, The values ​​a, b, and c represent the thermal perfection of the chiller and are related to the chiller itself. They can be obtained by fitting the chiller's factory data. Furthermore, for chillers that have operated for more than one refrigeration season, a, b, and c in formula (2) can be fitted using operating data collected from the previous refrigeration season. The fitting process is as follows:

[0067] During a refrigeration season when the chiller is running continuously, as the cooling load changes, the chilled water flow rate, chilled water supply and return water temperature, evaporator surface temperature (condensing temperature), condenser surface temperature (evaporating temperature), PLR, and chiller power of each chiller under different cooling loads are collected and stored in a database for further data processing.

[0068] During data processing, the chiller's cooling capacity under different cooling loads is calculated based on the chilled water flow rate and chilled water supply and return temperatures collected under different cooling loads. The thermodynamic completeness of the chiller under different cooling loads is calculated based on the condensing temperature, evaporating temperature, chiller power, and corresponding cooling capacity collected under different cooling loads. The calculation formulas are as follows:

[0069]

[0070] in, Let φ represent the chiller COP. It can be seen that φ has a linear relationship with the chiller COP, and there is a certain correlation between the chiller COP and its PLR. For a fixed-frequency chiller, as the PLR ​​increases, the COP gradually increases and eventually stabilizes. For a variable-frequency chiller, the COP will first increase and then decrease with the increase of the PLR, so there is a suitable range. When the PLR ​​is inside the range, the chiller COP is higher; when the PLR ​​is outside the range, the chiller COP is lower. Therefore, φ can be represented by a second-order polynomial of the PLR, as shown in formula (2).

[0071] At this point, the thermodynamic perfection calculated for the chiller under different cooling loads and the corresponding collected PLR can be fitted to obtain a, b, c corresponding to the chiller, and then the formula (2) corresponding to the chiller can be obtained.

[0072] In some embodiments, the average thermal completeness of the chiller assembly can be calculated based on the thermal completeness of each chiller in the assembly, and the average thermal completeness can be used as the start-up value index of the chiller assembly.

[0073] For example, the average thermodynamic perfection of the chiller assembly can be calculated according to formula (4). Formula (4) is shown below:

[0074]

[0075] in, This indicates the average thermal perfection of the chiller assembly. Q represents the thermal perfection of the i-th chiller in the chiller assembly. i This represents the rated cooling capacity of the i-th chiller.

[0076] In addition, to avoid frequent starts of the chiller and extend its lifespan, the overlap between the chiller combination and the currently operating chiller combination can be calculated.

[0077] For example, the overlap between the chiller unit and the currently operating chiller unit can be calculated according to formula (5), where formula (5) is as follows:

[0078]

[0079] Where S0 represents the number of identical chillers in the chiller combination and the currently operating chiller combination, S1 represents the number of chillers in the chiller combination, and S2 represents the number of chillers in the currently operating chiller combination.

[0080] The start-up value index of the chiller combination is obtained by weighted summation of the average thermal perfection and overlap of the chiller combination.

[0081] For example, the start-up value index of the chiller combination can be obtained by weighted summing of the average thermal perfection and overlap corresponding to the chiller combination according to formula (6). Formula (6) is shown below:

[0082]

[0083] Where π represents the start-up value index of the chiller combination, m represents the weight of the average thermal perfection, n represents the weight of the overlap, and m+n=1.

[0084] In this way, a chiller start-stop state can be introduced on the basis of chiller efficiency, and a balance can be established between chiller efficiency and chiller start-stop state, thereby saving chiller energy consumption and extending the service life of the chiller.

[0085] In the embodiments of this disclosure, the total cooling capacity required by the air conditioning system in the next time period can be predicted to determine the chiller combination that meets the cooling demand in the next time period. Then, the thermal perfection of each chiller in the chiller combination can be calculated, and the start-up value index of the chiller combination can be calculated based on the thermal perfection with strong operating efficiency evaluation capability. In this way, the appropriate chiller combination in the next time period can be accurately determined, thereby improving the overall operating efficiency of the chiller combination and reducing operating energy consumption.

[0086] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this disclosure, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this disclosure.

[0087] The above is an introduction to the method embodiments. The following describes the solution described in this disclosure further through device embodiments.

[0088] Figure 2 A structural diagram of a refrigeration unit combination determining device provided by an embodiment of the present disclosure is shown, as follows: Figure 2 As shown, the refrigeration unit combination determining device 200 may include:

[0089] The prediction module 210 is used to predict the total cooling capacity that the air conditioning system needs to provide in the next time period.

[0090] The determination module 220 is used to determine one or more combinations of chillers in the air conditioning system that meet the cooling requirements, based on the total cooling capacity and the rated cooling capacity of each chiller.

[0091] The calculation module 230 is used to calculate the thermal completeness of each chiller in the chiller combination based on the target cooling capacity and rated cooling capacity of each chiller in the chiller combination; and to calculate the start-up value index of the chiller combination based on the thermal completeness of each chiller in the chiller combination; and to determine the chiller combination with the highest start-up value index as the chiller combination to be turned on by the air conditioning system in the next time period.

[0092] In some embodiments, the prediction module 210 is specifically used for:

[0093] The current air conditioning system characteristic data is input into a pre-trained total cooling capacity prediction model to obtain the total cooling capacity that the air conditioning system needs to provide in the next time period. The air conditioning system characteristic data includes: time data, meteorological data of the building to which the air conditioning system belongs, and historical cooling capacity data of the air conditioning system.

[0094] In some embodiments, the total cooling capacity prediction model is obtained by training a preset neural network using a training dataset. The samples in the training dataset are labeled with the characteristic data of the air conditioning system at a certain moment and the total cooling capacity actually provided by the air conditioning system in the next time period.

[0095] In some embodiments, the determining module 220 is specifically used for:

[0096] Based on the total cooling capacity and the rated cooling capacity of each chiller, determine one or more chiller combinations in the air conditioning system whose total rated cooling capacity is greater than or equal to the total cooling capacity.

[0097] In some embodiments, the target cooling capacity of each chiller in the chiller assembly is determined by the following steps:

[0098] Based on the proportion of the rated cooling capacity of each chiller in the chiller combination to the total customized cooling capacity, the total cooling capacity is divided into multiple target cooling capacities and allocated to the corresponding chillers.

[0099] In some embodiments, the calculation module 230 is specifically used for:

[0100] Based on the target cooling capacity and rated cooling capacity of each chiller in the chiller assembly, calculate the PLR ​​of each chiller, and calculate the thermal perfection of each chiller based on the PLR ​​of each chiller.

[0101] In some embodiments, the calculation module 230 is specifically used for:

[0102] Calculate the overlap between the chiller unit and the currently operating chiller unit;

[0103] Calculate the average thermal perfection of the chiller assembly based on the thermal perfection of each chiller in the chiller assembly.

[0104] The start-up value index of the chiller combination is obtained by weighted summation of the average thermal perfection and overlap of the chiller combination.

[0105] Understandable, Figure 2 Each module / unit in the refrigeration unit combination determination device 200 shown has the ability to realize Figure 1 The functions of each step in the chiller combination determination method 100 shown, and the corresponding technical effects they achieve, will not be elaborated here for the sake of brevity.

[0106] Figure 3 A structural diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. Electronic device 300 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 300 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0107] like Figure 3 As shown, the electronic device 300 may include a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. The RAM 303 may also store various programs and data required for the operation of the electronic device 300. The computing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0108] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0109] The computing unit 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 may be implemented as a computer program product, including a computer program tangibly contained in a computer-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by the computing unit 301, one or more steps of method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to perform method 100 by any other suitable means (e.g., by means of firmware).

[0110] The various embodiments described above can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), payload programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0112] In the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of computer-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0113] It should be noted that this disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute method 100 and achieve the corresponding technical effects achieved by the embodiments of this disclosure in executing the method. For the sake of brevity, these will not be elaborated here.

[0114] In addition, this disclosure also provides a computer program product including a computer program that implements method 100 when executed by a processor.

[0115] To provide interaction with a user, the embodiments described above can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0116] The embodiments described above can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with the implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., a communication network) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0117] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0118] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0119] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for determining chiller combinations, characterized in that, The method includes: Predict the total cooling capacity that the air conditioning system will need to provide in the next time period; Based on the total cooling capacity and the rated cooling capacity of each chiller, determine one or more chiller combinations in the air conditioning system that meet the cooling requirements; Based on the target cooling capacity and rated cooling capacity of each chiller in the chiller combination, the thermal completeness of each chiller is calculated; and based on the thermal completeness of each chiller in the chiller combination, the start-up value index of the chiller combination is calculated; the chiller combination with the highest start-up value index is determined as the chiller combination to be started by the air conditioning system in the next time period. The step of calculating the thermal perfection of each chiller based on its target cooling capacity and rated cooling capacity in the chiller assembly includes: Based on the target cooling capacity and rated cooling capacity of each chiller in the chiller combination, calculate the partial load rate (PLR) of each chiller, and calculate the thermal perfection of each chiller based on the PLR ​​of each chiller. The method further includes: Calculate the overlap between the chiller assembly and the currently operating chiller assembly; The calculation of the start-up value index of the refrigeration unit based on the thermal perfection of each refrigeration unit in the refrigeration unit includes: Calculate the average thermal perfection of the refrigeration unit based on the thermal perfection of each refrigeration unit in the refrigeration unit; The start-up value index of the chiller combination is obtained by weighted summation of the average thermal perfection and overlap of the chiller combination. The predicted total cooling capacity that the air conditioning system needs to provide in the next time period includes: The current air conditioning system feature data is input into a pre-trained total cooling capacity prediction model to obtain the total cooling capacity that the air conditioning system needs to provide in the next time period. The air conditioning system feature data includes: time data, meteorological data of the building to which the air conditioning system belongs, and historical cooling capacity data of the air conditioning system. The total cooling capacity prediction model is obtained by training a preset neural network using a training dataset. The samples in the training dataset use the characteristic data of the air conditioning system at a certain moment as the sample feature data, and the actual total cooling capacity provided by the air conditioning system in the next time period is used as the label. The training process for the total cooling capacity prediction model includes: The samples were preprocessed according to the 3σ rule, outliers were removed and missing data were filled. 80% of the processed samples were allocated as the training dataset, and 20% as the test dataset. The training dataset underwent feature expansion, i.e., high-dimensional feature extraction. Specifically, high-dimensional feature extraction was performed on the time data to obtain the time index and date type; high-dimensional feature extraction was also performed on the meteorological data of the building to which the air conditioning system belonged to obtain smoothed meteorological data and differential meteorological data. This involved using a smoothing filter to remove high-frequency fluctuations in the meteorological data to preserve data trends and changes, and then calculating the first and second derivatives of the subsequent meteorological data. The first-order derivative is used as smooth meteorological data, and the second-order derivative is used as difference meteorological data. High-dimensional features are extracted from the historical cooling capacity data of the air conditioning system to obtain periodic and statistical data. The high-dimensional features of the samples in the expanded training dataset are selected using an elite genetic algorithm, and the hyperparameters of the preset neural network are tuned. Unselected high-dimensional features of the samples in the training dataset are deleted. The tuned preset neural network is trained based on the latest training dataset, and tested based on the test dataset. If the test results meet the requirements, the trained preset neural network is used as the total cooling capacity prediction model.

2. The method according to claim 1, characterized in that, The step of determining one or more chiller combinations in the air conditioning system that meet the cooling requirements based on the total cooling capacity and the rated cooling capacity of each chiller includes: Based on the total cooling capacity and the rated cooling capacity of each chiller, determine one or more chiller combinations in the air conditioning system whose total rated cooling capacity is greater than or equal to the total cooling capacity.

3. The method according to claim 1, characterized in that, The target cooling capacity of each chiller in the chiller assembly is determined through the following steps: Based on the proportion of the rated cooling capacity of each chiller in the chiller combination to the total customized cooling capacity, the total cooling capacity is divided into multiple target cooling capacities and allocated to the corresponding chillers.

4. A refrigeration unit combination determining device, characterized in that, The device includes: The prediction module is used to predict the total cooling capacity that the air conditioning system needs to provide in the next time period; The determining module is used to determine one or more combinations of chillers in the air conditioning system that meet the cooling requirements, based on the total cooling capacity and the rated cooling capacity of each chiller. The calculation module is used to calculate the thermal completeness of each chiller in the chiller combination based on the target cooling capacity and rated cooling capacity of each chiller; and to calculate the start-up value index of the chiller combination based on the thermal completeness of each chiller in the chiller combination; and to determine the chiller combination with the largest start-up value index as the chiller combination to be turned on by the air conditioning system in the next time period. The calculation module is specifically used for: calculating the partial load factor (PLR) of each chiller in the chiller combination based on the target cooling capacity and rated cooling capacity of each chiller; calculating the thermal completeness of each chiller based on the PLR; calculating the overlap between the chiller combination and the currently operating chiller combination; calculating the average thermal completeness of the chiller combination based on the thermal completeness of each chiller in the chiller combination; and performing a weighted summation of the average thermal completeness and overlap corresponding to the chiller combination to obtain the start-up value index of the chiller combination. The prediction module is specifically used to: input the current air conditioning system feature data into a pre-trained total cooling capacity prediction model to obtain the total cooling capacity that the air conditioning system needs to provide in the next time period. The air conditioning system feature data includes: time data, meteorological data of the building to which the air conditioning system belongs, and historical cooling capacity data of the air conditioning system. The total cooling capacity prediction model is obtained by training a preset neural network using a training dataset. The samples in the training dataset use the characteristic data of the air conditioning system at a certain moment as the sample feature data, and the actual total cooling capacity provided by the air conditioning system in the next time period is used as the label. The training process of the total cooling capacity prediction model includes: preprocessing the samples according to the 3σ rule, removing outliers and filling in missing data, allocating 80% of the processed samples as the training dataset and 20% as the test dataset; expanding the sample features of the samples in the training dataset, i.e., extracting high-dimensional features from the sample feature data; specifically, extracting high-dimensional features from the time data to obtain the time index and date type; extracting high-dimensional features from the meteorological data of the building to which the air conditioning system belongs to obtain smoothed meteorological data and differential meteorological data, i.e., using a smoothing filter to remove high-frequency fluctuations in the meteorological data to preserve data trends and changes, and calculating the first-order microvariable of the subsequent meteorological data. First-order derivatives and second-order derivatives are used as smoothed meteorological data, and second-order derivatives are used as differential meteorological data. High-dimensional features are extracted from historical cooling capacity data of the air conditioning system to obtain periodic and statistical data. Elite genetic algorithms are used to select high-dimensional features from samples in the expanded training dataset and to fine-tune the hyperparameters of the preset neural network. Unselected high-dimensional features are removed from the training dataset. The fine-tuned preset neural network is trained based on the latest training dataset and tested based on the test dataset. If the test results meet the requirements, the trained preset neural network is used as the total cooling capacity prediction model.

5. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.

6. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-3.

Images