Water-based multi-split system, end device, computing device and control device

By setting multiple computing devices in the air-conditioning system to distribute the calculation and control authority for cold volume data, the bottleneck in the data calculation and response time of the air-conditioning system is solved, and the rapid energy-saving operation of the system is achieved.

WO2024239665A1PCT designated stage expired Publication Date: 2024-11-28QINGDAO HAIER AIR CONDITIONING ELECTRONICS CO LTD +3

Patent Information

Application Number
PCT/CN2024/070938
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-05-25
Filing Date
2024-01-05
Publication Date
2024-11-28

AI Technical Summary

Technical Problem

There are bottlenecks in data calculation and response time of existing air conditioning systems, resulting in limited energy consumption reduction effects.

Method used

Using a multi-online system, multiple computing devices distribute cold data calculation and control permissions, shorten the data calculation time and speed up the response rate.

Benefits of technology

Effectively reduce the calculation pressure of the air conditioner host, improve the response rate, and achieve the rapid energy-saving operation of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2024070938_28112024_PF_FP_ABST
    Figure CN2024070938_28112024_PF_FP_ABST
Patent Text Reader

Abstract

A water-based multi-split system, an end device (130), a computing device (120) and a control device (110). The water-based multi-split system comprises: a plurality of end devices (130), which are used for distributing cold which is generated by a water system, and generating actual cold according to a collected cold parameter; a plurality of computing devices (120), each of the computing devices (120) being connected to one or more end devices (130), and being used for computing predicted cold according to the actual cold, which is generated by the one or more end devices (130), and generating an adjustment instruction for controlling the operation of the end devices (130); and a control device (110), which is respectively connected to the plurality of computing devices (120), and is used for generating, according to the predicted cold which is computed by the plurality of computing devices (120), a control instruction for adjusting the cooling capacity of the water system. In this way, a large quantity of pieces of cold data are dispersed to a plurality of computing devices (120) for computing, thereby shortening the data computing time; and control permissions are also dispersed to the computing devices (120), thereby realizing a quick response.
Need to check novelty before this filing date? Find Prior Art

Description

Water multi-connection system, terminal equipment, computing equipment and control equipment

[0001] This application is based on the Chinese patent application with application number 202310601940.5 and application date May 25, 2023, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby introduced into this application as a reference. Technical Field

[0002] The present application relates to the technical field of smart home appliances, for example, to a water multi-connection system, a terminal device, a computing device, and a control device. Background Art

[0003] At present, the energy consumption of central air-conditioning systems accounts for a large proportion of building energy consumption. During the operation of air-conditioning, there is a demand to reduce air-conditioning energy consumption.

[0004] In order to meet the demand for reducing air conditioning energy consumption, the relevant technology discloses a terminal cooling capacity balancing control system, including: terminal equipment and control equipment. The terminal equipment collects the total cooling capacity demand of each terminal and communicates with the air conditioning host. The air conditioning host calculates the optimal number of operating chillers and the operating frequency of the water pump, and controls the operation of the equipment. Then, the PID controller is used to adjust the frequency of the terminal air duct, so that the chilled water system can be dynamically adjusted according to the terminal load demand to ensure energy-saving operation of the system.

[0005] During the implementation of the embodiments of the present disclosure, it was found that at least the following problems exist in the related art:

[0006] Although the relevant technology reduces the operating energy consumption of the air-conditioning system, all collected data are fed back to the air-conditioning host for calculation. The amount of calculated data is large, resulting in slow response time.

[0007] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute prior art known to ordinary technicians in this field.

[0008] Summary of the Invention

[0009] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical elements or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.

[0010] The embodiments of the present disclosure provide a water multi-connected system, terminal equipment, computing equipment, and control equipment to reduce the computing pressure of the air-conditioning host and speed up the response rate.

[0011] In some embodiments, the water multi-split system includes: a terminal device, which is used to distribute the cooling capacity generated by the water system and generate actual cooling capacity based on the collected cooling capacity parameters; a plurality of computing devices, each computing device is respectively connected to one or more terminal devices, and is used to calculate the predicted cooling capacity based on the actual cooling capacity generated by one or more terminal devices, and generate adjustment instructions for controlling the operation of the terminal devices; a control device, which is respectively connected to the plurality of computing devices, and is used to generate control instructions for adjusting the cooling capacity of the water system based on the predicted cooling capacity calculated by the plurality of computing devices.

[0012] In some embodiments, the terminal device includes: multiple terminal coils; a parameter acquisition module for acquiring the cooling parameters of each terminal coil; a model calling module connected to the parameter acquisition module for generating the actual cooling capacity of each terminal coil based on the cooling parameters of each terminal coil; a first summary module for summarizing the actual cooling capacity of each terminal coil to generate the total actual cooling capacity; and a first communication module for sending the total actual cooling capacity to a corresponding computing device.

[0013] In some embodiments, the model calling module includes: a calling submodule, which is used to call the cooling model after receiving the cooling parameters of the corresponding terminal coil; and a cooling generation module, which is used to map the cooling parameters of each terminal coil into the actual cooling capacity of each terminal coil according to the cooling model.

[0014] In some embodiments, the computing device includes: a load prediction module for calculating the total actual cooling capacity as the predicted cooling capacity based on a preset load prediction model; a second communication module including a receiving submodule for receiving the total actual cooling capacity sent by the terminal device; and a sending submodule for sending the predicted cooling capacity to the control device.

[0015] In some embodiments, the sending submodule is also used to adjust the actual cooling capacity of the terminal coil according to a preset group planning algorithm when the total actual cooling capacity is outside the set range, until the total actual cooling capacity is adjusted to within the set range, and send the total actual cooling capacity to the control device.

[0016] In some embodiments, the set range is 95% to 105% of the predicted cooling capacity.

[0017] In some embodiments, the computing device further includes: a fuzzy control module for obtaining cooling error, cooling error change rate, fuzzy control rule table and membership parameters, performing fuzzy output according to cooling error, cooling error change rate, fuzzy control rule table and membership parameters to generate a fuzzy signal; an instruction generation module for generating a PID signal according to the fuzzy signal, and generating an adjustment instruction according to the PID signal.

[0018] In some embodiments, the control device includes: a third communication module for receiving the predicted cooling capacity sent by the computing device; and a module for sending control instructions to the water system; a second aggregation module for aggregating the predicted cooling capacity sent by multiple computing devices to generate a total predicted cooling capacity; a data acquisition module for acquiring environmental parameters and user control data; an optimization module for performing a coupled solution based on the total predicted cooling capacity, environmental parameters and user control data to generate optimal control parameters, and generating control instructions based on the optimal control parameters.

[0019] In some embodiments, the terminal device is used in a water multi-split system, including: a regulation module for distributing the cooling capacity generated by the water system; a cooling capacity generation module for generating actual cooling capacity based on the collected cooling capacity parameters; wherein the actual cooling capacity is used to generate predicted cooling capacity.

[0020] In some embodiments, the cooling capacity generation module includes: a parameter acquisition module for acquiring the cooling capacity parameters of each terminal coil; a model calling module connected to the parameter acquisition module for generating the actual cooling capacity of each terminal coil based on the cooling capacity parameters of each terminal coil; a first summary module for summarizing the actual cooling capacity of each terminal coil to generate the total actual cooling capacity; and a first communication module for sending the total actual cooling capacity to the corresponding computing device.

[0021] In some embodiments, the model calling module includes: a calling submodule, which is used to call the cooling model after receiving the cooling parameters of the corresponding terminal coil; and a cooling generation module, which is used to map the cooling parameters of each terminal coil into the actual cooling capacity of each terminal coil according to the cooling model.

[0022] In some embodiments, the computing device is used in a water multi-split system, comprising: a computing module for calculating predicted cooling capacity based on the actual cooling capacity generated by one or more terminal devices; wherein the predicted cooling capacity is used to generate control instructions for adjusting the cooling capacity of the water system; and a control module for generating adjustment instructions for controlling the operation of the terminal devices.

[0023] In some embodiments, the calculation module includes: a load prediction module, which is used to calculate the total actual cooling capacity as the predicted cooling capacity based on a preset load prediction model; a second communication module, which includes a receiving submodule, which is used to receive the total actual cooling capacity sent by the terminal device; and a sending submodule, which is used to send the predicted cooling capacity to the control device.

[0024] In some embodiments, the sending submodule is also used to adjust the actual cooling capacity of the terminal coil according to a preset group planning algorithm when the total actual cooling capacity is outside the set range, until the total actual cooling capacity is adjusted to within the set range, and send the total actual cooling capacity to the control device.

[0025] In some embodiments, the set range is 95% to 105% of the predicted cooling capacity.

[0026] In some embodiments, the computing device further includes: a fuzzy control module for obtaining cooling error, cooling error change rate, fuzzy control rule table and membership parameters, performing fuzzy output according to cooling error, cooling error change rate, fuzzy control rule table and membership parameters to generate a fuzzy signal; an instruction generation module for generating a PID signal according to the fuzzy signal, and generating an adjustment instruction according to the PID signal.

[0027] In some embodiments, the control device is used in a water multi-split system and includes: a processing module for generating control instructions for adjusting the cooling capacity of the water system based on the predicted cooling capacity calculated by the computing device.

[0028] In some embodiments, the processing module includes: a third communication module for receiving the predicted cooling capacity sent by the computing device; and a module for sending control instructions to the water system; a second aggregation module for aggregating the predicted cooling capacity sent by multiple computing devices to generate a total predicted cooling capacity; a data acquisition module for acquiring environmental parameters and user control data; an optimization module for performing a coupled solution based on the total predicted cooling capacity, environmental parameters and user control data to generate optimal control parameters, and generating control instructions based on the optimal control parameters.

[0029] The water multi-connection system, terminal device, computing device, and control device provided in the embodiments of the present disclosure can achieve the following technical effects:

[0030] Multiple computing devices are set up to calculate predicted cooling capacity based on cooling data collected by the terminal. This data is then transmitted to a control device. The control device then issues control instructions to the water system based on the predicted cooling capacity. The water system then generates cooling capacity according to the control instructions. Finally, the computing device regulates the terminal device. This approach not only distributes large amounts of cooling capacity data across multiple independent computing devices, thus shortening data calculation time, but also distributes control authority across the computing devices, enabling faster response times. This reduces the computing pressure on the air conditioner main unit and speeds up response times.

[0031] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] One or more embodiments are exemplarily described by corresponding drawings. These exemplary descriptions and drawings do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements. The drawings do not constitute a scale limitation. In addition,

[0033] FIG1 is a schematic structural diagram of a water multi-connection system provided by an embodiment of the present disclosure;

[0034] FIG2 is a schematic diagram of the structure of a terminal device provided by an embodiment of the present disclosure;

[0035] FIG3 is a schematic diagram of the structure of a model calling module provided by an embodiment of the present disclosure;

[0036] FIG4 is a schematic diagram of the structure of a computing device provided by an embodiment of the present disclosure;

[0037] FIG5 is a flow chart for establishing a load forecasting model provided by an embodiment of the present disclosure;

[0038] FIG6 is a schematic diagram of the structure of a control device provided by an embodiment of the present disclosure;

[0039] FIG7 is a schematic structural diagram of a practical application provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0040] In order to be able to understand the features and technical content of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The accompanying drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the sake of convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.

[0041] In the description and claims of the embodiments of the present disclosure, as well as in the accompanying drawings, the terms "first," "second," and the like are used to distinguish similar items and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate to describe the embodiments of the present disclosure herein. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions.

[0042] Unless otherwise stated, the term "plurality" means two or more.

[0043] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.

[0044] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0045] As shown in FIG1 , an embodiment of the present disclosure provides a water multi-connected system, comprising a plurality of terminal devices 130, a plurality of computing devices 120, and a control device 110. The terminal devices 130 are used to distribute the cooling capacity generated by the water system and generate actual cooling capacity based on collected cooling capacity parameters; each computing device 120 is respectively connected to one or more terminal devices 130 and is used to calculate predicted cooling capacity based on the actual cooling capacity generated by one or more terminal devices 130 and generate adjustment instructions for controlling the operation of the terminal devices 130; the control device 110 is respectively connected to the plurality of computing devices 120 and is used to generate control instructions for adjusting the cooling capacity of the water system based on the predicted cooling capacity calculated by the plurality of computing devices 120.

[0046] Multiple computing devices are set up. These devices calculate predicted cooling capacity based on cooling data collected by the terminal and transmit the data to the control device. The control device then issues control instructions to the water system based on the predicted cooling capacity. The water system generates cooling capacity according to the control instructions, and the computing device finally adjusts the terminal device. This not only allows multiple independent computing devices to distribute large amounts of cooling capacity data across multiple computing devices for calculation, thus shortening data calculation time, but also distributes control authority among the computing devices, enabling rapid response. This reduces the computing pressure on the air conditioner host and speeds up response time.

[0047] Optionally, as shown in FIG1 and FIG2 , the terminal device 130 includes a terminal coil 131, a parameter acquisition module 132, a model call module 133, a first aggregation module 134, and a first communication module 135. The parameter acquisition module 132 is configured to acquire the cooling capacity parameter of each terminal coil 131; the model call module 133 is connected to the parameter acquisition module 132 and is configured to generate the actual cooling capacity of each terminal coil 131 based on the cooling capacity parameter of each terminal coil 131; the first aggregation module 134 is configured to aggregate the actual cooling capacity of each terminal coil 131 to generate a total actual cooling capacity; and the first communication module 135 is configured to send the total actual cooling capacity to the corresponding computing device 120.

[0048] Optionally, cooling capacity parameters include some or all of the following: environmental parameters, control parameters, foot traffic intensity, fresh air volume, and comfort level. The actual cooling capacity of each terminal coil is generated based on the cooling capacity parameters, allowing for statistical analysis of the cooling capacity of each zone. This facilitates subsequent regional cooling, contributing to energy-efficient system operation.

[0049] Optionally, as shown in conjunction with Figures 2 and 3 , the model calling module 133 includes a calling submodule 1331 and a cooling capacity generation module 1332. The calling submodule 1331 is configured to call the cooling capacity model after receiving the cooling capacity parameters of the corresponding terminal coil 131; and the cooling capacity generation module 1332 is configured to map the cooling capacity parameters of each terminal coil 131 to the actual cooling capacity of each terminal coil 131 based on the cooling capacity model.

[0050] The preset cooling model is called to map the cooling parameters to actual cooling, thereby speeding up the generation rate of actual cooling and reducing the calculation pressure.

[0051] Optionally, the cooling capacity model is stored in a computing device. The modeling of the cooling capacity model includes inputting part or all of the environmental parameters, control parameters, crowd intensity, fresh air volume and comfort level, and adopts a standardized model to train and generate a mapping function relationship.

[0052] Among them, the standardized model can be a black box model or an expression model.

[0053] Optionally, as shown in FIG1 and FIG4 , the computing device 120 includes a load prediction module 121 and a second communication module 122. The load prediction module 121 is configured to calculate the total actual cooling capacity as the predicted cooling capacity based on a preset load prediction model; the second communication module 122 includes a receiving submodule and a sending submodule. The receiving submodule is configured to receive the total actual cooling capacity sent by the terminal device 130; the sending submodule is configured to send the predicted cooling capacity to the control device 110.

[0054] Using multiple computing devices to separately predict the cooling capacity of the corresponding terminal coils at the next moment helps improve the accuracy of the prediction, facilitates subsequent regional cooling, disperses computing pressure, and speeds up response speed.

[0055] When forecasting load, an overall load forecast is made for the area covered by the computing device based on the actual situation of the computing device and its historical operating data. The historical data needs to be preliminarily processed to obtain historical load data for the area corresponding to each computing device.

[0056] In this embodiment, a long short-term memory network plus an attention mechanism is used to predict the load of each computing device. The factors that need to be considered are: external temperature, external radiation intensity, external enthalpy value, fresh air volume, and previous load data.

[0057] As shown in Figure 5, the process of establishing a load forecasting model using a long short-term memory network plus an attention mechanism includes:

[0058] S101, obtaining a data structure;

[0059] S102, cleaning the data;

[0060] S103, completing the feature quantity of the cleaned data;

[0061] S104, dividing the data after feature complementation into a training set and a test set;

[0062] S105, performing network training on the data in the training set to generate a load forecasting model;

[0063] S106, testing the load forecasting model using data in the test set;

[0064] S107: Output the load forecasting model.

[0065] Optionally, data acquisition and cleaning are time-based to ensure data correspondence. Even if data is missing, corresponding time periods are not directly deleted. Data feature completion includes extracting seasonal factors and filling in missing values. For missing values, it is recommended to first fill in seasonal factors, such as weekdays, hours, months, and weeks of the year. Machine learning-like interpolation methods, such as K-nearest neighbors, are then used. This approach not only fills in missing values ​​but also enhances periodic features.

[0066] Optionally, the data may be divided into a training set and a test set according to a certain ratio; the training set is used to train and generate a load forecasting model, and the test set is used to test the generated load forecasting model.

[0067] In this embodiment, the output load forecast model is stored on the computing device, while the training model used to build the load forecast model is stored on the host computer, i.e., the cloud server that controls the device. Each time a load forecast is performed, it is run directly on the computing device. The training model is also used to periodically train the load forecast model and update the deployed model parameters.

[0068] Optionally, the sending submodule is also used to adjust the actual cooling capacity of the terminal coil according to a preset group planning algorithm when the total actual cooling capacity is outside the set range, until the total actual cooling capacity is adjusted to within the set range, and send the total actual cooling capacity to the control device.

[0069] Optionally, the setting range is 95% to 105% of the predicted cooling capacity of the corresponding terminal coil, and specifically can be 95%, 97%, 103% or 105%.

[0070] If the total actual cooling capacity uploaded by the terminal coil does not meet the predicted cooling capacity, the sending submodule automatically triggers the group planning algorithm, adjusting the corresponding terminal coil to ensure that the total actual cooling capacity meets the predicted cooling capacity range with minimal sacrifice in comfort. This helps improve the accuracy of cooling capacity prediction, achieves cooling supply based on regional demand, and maximizes energy savings while emphasizing comfort.

[0071] Optionally, as shown in conjunction with FIG1 and FIG4 , the computing device 120 further includes a fuzzy control module 123 and an instruction generation module 124. The fuzzy control module 123 is configured to obtain the cooling capacity error, the cooling capacity error change rate, the fuzzy control rule table, and the membership parameter, and perform fuzzy output based on the cooling capacity error, the cooling capacity error change rate, the fuzzy control rule table, and the membership parameter to generate a fuzzy signal; the instruction generation module 124 is configured to generate a PID signal based on the fuzzy signal and generate an adjustment instruction based on the PID signal.

[0072] In practical applications, the fuzzy control module can be a fuzzy controller, and the instruction generation module can be a PID controller. After the fuzzy controller obtains the cooling capacity error, the cooling capacity error change rate, the fuzzy control rule table, and the membership parameters, it performs fuzzy output to generate a fuzzy signal. The PID controller generates a control instruction for adjusting the terminal coil frequency based on the fuzzy signal.

[0073] The computing device controls the frequency of the terminal coils based on the fuzzy control module and the instruction generation module, thereby decentralizing the control authority of the wind system from the host computer to the computing device. This facilitates rapid response. Furthermore, the computing device uses fuzzy control to provide control freedom when controlling the frequency of the terminal coils, eliminating the strict distinction between comfort and cooling supply, which helps reduce computing pressure.

[0074] Optionally, as shown in conjunction with Figures 1 and 6 , the control device 110 includes a third communication module 111, a second aggregation module 112, a data acquisition module 113, and an optimization module 114. The third communication module 111 is configured to receive the predicted cooling capacity sent by the computing device 120; and, to send control instructions to the water system; the second aggregation module 112 is configured to aggregate the predicted cooling capacities sent by multiple computing devices 120 to generate a total predicted cooling capacity; the data acquisition module 113 is configured to acquire environmental parameters and user control data; and the optimization module 114 is configured to perform a coupled solution based on the total predicted cooling capacity, environmental parameters, and user control data to generate optimal control parameters, and to generate control instructions based on the optimal control parameters.

[0075] The optimization module can be a cloud-based solver. After receiving the total predicted cooling capacity, the cloud-based solver reads the current environmental parameters based on the real-time variables required by the preset fitness objective function. The user also enters the adjustable range of the control parameters to be optimized and customizes the boundary conditions. These are then coupled to the cloud-based solver's fitness objective function to determine the optimal control parameters and issue commands to the water system cooling system.

[0076] After the water system cools, environmental parameters, control parameter ranges, boundary conditions, and time characteristics change accordingly, forming a closed control loop. This allows the water system to proactively respond to real-time loads and ensure optimal operation of each device, achieving multi-level autonomous brain control.

[0077] Optionally, a terminal device for a water multi-split system includes a regulation module and a cooling capacity generation module. The regulation module is used to distribute the cooling capacity generated by the water system; the cooling capacity generation module is used to generate actual cooling capacity based on collected cooling capacity parameters; the actual cooling capacity is used to generate predicted cooling capacity.

[0078] Optionally, the cooling capacity generation module includes multiple terminal coils, a parameter acquisition module, a model call module, a first aggregation module, and a first communication module. The parameter acquisition module is used to obtain the cooling capacity parameters of each terminal coil; the model call module is connected to the parameter acquisition module and is used to generate the actual cooling capacity of each terminal coil based on the cooling capacity parameters of each terminal coil; the first aggregation module is used to aggregate the actual cooling capacity of each terminal coil to generate a total actual cooling capacity; and the first communication module is used to send the total actual cooling capacity to the corresponding computing device.

[0079] Optionally, cooling capacity parameters include some or all of the following: environmental parameters, control parameters, foot traffic intensity, fresh air volume, and comfort level. The actual cooling capacity of each terminal coil is generated based on the cooling capacity parameters, allowing for statistical analysis of the cooling capacity of each zone. This facilitates subsequent regional cooling, contributing to energy-efficient system operation.

[0080] Optionally, the model calling module includes a calling submodule and a cooling capacity generation module. The calling submodule is used to call the cooling capacity model after receiving the cooling capacity parameters of the corresponding terminal coil; the cooling capacity generation module is used to map the cooling capacity parameters of each terminal coil into the actual cooling capacity of each terminal coil based on the cooling capacity model.

[0081] The preset cooling model is called to map the cooling parameters to actual cooling, thereby speeding up the generation rate of actual cooling and reducing the calculation pressure.

[0082] Optionally, the cooling capacity model is stored in a computing device. The modeling of the cooling capacity model includes inputting part or all of the environmental parameters, control parameters, crowd intensity, fresh air volume and comfort level, and adopts a standardized model to train and generate a mapping function relationship.

[0083] Among them, the standardized model can be a black box model or an expression model.

[0084] Optionally, a computing device for a water multi-split system includes a computing module and a control module. The computing module is configured to calculate a predicted cooling capacity based on the actual cooling capacity generated by one or more terminal devices; the predicted cooling capacity is used to generate control instructions for adjusting the cooling capacity of the water system. The control module is configured to generate adjustment instructions for controlling the operation of the terminal devices.

[0085] Optionally, the calculation module includes a load prediction module, which is used to calculate the total actual cooling capacity as the predicted cooling capacity based on a preset load prediction model; the second communication module includes a receiving submodule, which is used to receive the total actual cooling capacity sent by the terminal device; and a sending submodule, which is used to send the predicted cooling capacity to the control device.

[0086] Using multiple computing devices to separately predict the cooling capacity of the corresponding terminal coils at the next moment helps improve the accuracy of the prediction, facilitates subsequent regional cooling, disperses computing pressure, and speeds up response speed.

[0087] When forecasting load, an overall load forecast is made for the area covered by the computing device based on the actual situation of the computing device and its historical operating data. The historical data needs to be preliminarily processed to obtain historical load data for the area corresponding to each computing device.

[0088] In this embodiment, a long short-term memory network plus an attention mechanism is used to predict the load of each computing device. The factors that need to be considered are: external temperature, external radiation intensity, external enthalpy value, fresh air volume, and previous load data.

[0089] As shown in Figure 5, the process of establishing a load forecasting model using a long short-term memory network plus an attention mechanism includes:

[0090] S101, obtaining a data structure;

[0091] S102, cleaning the data;

[0092] S103, completing the feature quantity of the cleaned data;

[0093] S104, dividing the data after feature complementation into a training set and a test set;

[0094] S105, performing network training on the data in the training set to generate a load forecasting model;

[0095] S106, testing the load forecasting model using data in the test set;

[0096] S107: Output the load forecasting model.

[0097] Optionally, data acquisition and cleaning are time-based to ensure data correspondence. Even if data is missing, corresponding time periods are not directly deleted. Data feature completion includes extracting seasonal factors and filling in missing values. For missing values, it is recommended to first fill in seasonal factors, such as weekdays, hours, months, and weeks of the year. Machine learning-like interpolation methods, such as K-nearest neighbors, are then used. This approach not only fills in missing values ​​but also enhances periodic features.

[0098] Optionally, the data may be divided into a training set and a test set according to a certain ratio; the training set is used to train and generate a load forecasting model, and the test set is used to test the generated load forecasting model.

[0099] In this embodiment, the output load forecast model is stored on the computing device, while the training model used to build the load forecast model is stored on the host computer, i.e., the cloud server that controls the device. Each time a load forecast is performed, it is run directly on the computing device. The training model is also used to periodically train the load forecast model and update the deployed model parameters.

[0100] Optionally, the sending submodule is also used to, when the total actual cooling capacity is outside the set range, adjust the actual cooling capacity of the terminal coil according to a preset group planning algorithm until the total actual cooling capacity is adjusted to within the set range, and send the total actual cooling capacity to the control device.

[0101] Optionally, the setting range is 95% to 105% of the predicted cooling capacity, specifically 95%, 97%, 103% or 105%.

[0102] If the total actual cooling capacity uploaded by the terminal coil does not meet the predicted cooling capacity, the sending submodule automatically triggers the group planning algorithm, adjusting the corresponding terminal coil to ensure that the total actual cooling capacity meets the predicted cooling capacity range with minimal sacrifice in comfort. This helps improve the accuracy of cooling capacity prediction, achieves cooling supply based on regional demand, and maximizes energy savings while emphasizing comfort.

[0103] Optionally, the computing device also includes a fuzzy control module for obtaining the cooling error, the cooling error change rate, the fuzzy control rule table and the membership parameters, performing fuzzy output based on the cooling error, the cooling error change rate, the fuzzy control rule table and the membership parameters to generate a fuzzy signal; an instruction generation module for generating a PID signal based on the fuzzy signal, and generating an adjustment instruction based on the PID signal.

[0104] In practical applications, the fuzzy control module can be a fuzzy controller, and the instruction generation module can be a PID controller. After the fuzzy controller obtains the cooling capacity error, the cooling capacity error change rate, the fuzzy control rule table, and the membership parameters, it performs fuzzy output to generate a fuzzy signal. The PID controller generates a control instruction for adjusting the terminal coil frequency based on the fuzzy signal.

[0105] The computing device controls the frequency of the terminal coils based on the fuzzy control module and the instruction generation module, thereby decentralizing the control authority of the wind system from the host computer to the computing device. This facilitates rapid response. Furthermore, the computing device uses fuzzy control to provide control freedom when controlling the frequency of the terminal coils, eliminating the strict distinction between comfort and cooling supply, which helps reduce computing pressure.

[0106] Optionally, a control device for a water multi-split system includes a processing module for generating control instructions for adjusting the cooling capacity of the water system based on the predicted cooling capacity calculated by the computing device.

[0107] Optionally, the processing module includes a third communication module for receiving the predicted cooling capacity sent by the computing device; and a module for sending control instructions to the water system; a second aggregation module for aggregating the predicted cooling capacity sent by multiple computing devices to generate a total predicted cooling capacity; a data acquisition module for acquiring environmental parameters and user control data; and an optimization module for performing a coupled solution based on the total predicted cooling capacity, environmental parameters and user control data to generate optimal control parameters, and generating control instructions based on the optimal control parameters.

[0108] The optimization module can be a cloud-based solver. After receiving the total predicted cooling capacity, the cloud-based solver reads the current environmental parameters based on the real-time variables required by the preset fitness objective function. The user also enters the adjustable range of the control parameters to be optimized and customizes the boundary conditions. These are then coupled to the cloud-based solver's fitness objective function to determine the optimal control parameters and issue commands to the water system cooling system.

[0109] After the water system cools, environmental parameters, control parameter ranges, boundary conditions, and time characteristics change accordingly, forming a closed control loop. This allows the water system to proactively respond to real-time loads and ensure optimal operation of each device, achieving multi-level autonomous brain control.

[0110] As shown in Figure 7, in actual applications, the terminal device is set as the terminal autonomous execution node; the computing device includes multiple computing nodes, which are set as secondary computing nodes; the control device includes a cloud solver, an intelligent control cabinet, and water system equipment, which are set as the highest control node.

[0111] The terminal coil collects cooling capacity and reports it to the corresponding computing node; the computing node calls the load prediction model, performs load prediction on the cooling capacity, generates predicted cooling capacity, and transmits the predicted cooling capacity to the cloud optimization solver; the cloud solver obtains real-time environmental parameters and receives control parameters and boundary conditions sent by the user, couples and solves the predicted cooling capacity, real-time environmental parameters, control parameters and boundary conditions, obtains the optimal control parameters, and sends commands to the intelligent control cabinet; the intelligent control cabinet adjusts the water system cooling according to the command; the computing node calls the terminal optimization model, that is, fuzzy control, to regulate the frequency of the terminal coil.

[0112] In this way, the control authority of the wind system controlled by the host computer is decentralized to the computing nodes for control, thereby achieving rapid response.

[0113] In this embodiment, a multi-level node layer can be set between the terminal device and the control device, which helps to further improve the prediction accuracy and thus increase the energy saving space. At the same time, since the node layer itself has computing power, it can run independently of the cloud computing layer.

[0114] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible variations. Unless explicitly required, individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to also include plural forms. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of one or more associated listings. In addition, when used in this application, the term "comprise" and its variations "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups of these. In the absence of further restrictions, an element defined by the sentence "comprising a..." does not exclude the presence of other identical elements in the process, method or device that includes the element. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments can be referenced to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can be found in the description of the method part.

Claims

1. A water multi-connection system, comprising a water system for refrigeration, characterized in that: Also includes: Multiple terminal devices are used to distribute the cooling capacity generated by the water system and generate actual cooling capacity according to the collected cooling capacity parameters; A plurality of computing devices, each computing device being connected to one or more terminal devices, and configured to calculate predicted cooling capacity based on actual cooling capacity generated by the one or more terminal devices, and to generate adjustment instructions for controlling operation of the terminal devices; The control device is connected to the multiple computing devices respectively, and is used to generate control instructions for adjusting the cooling capacity of the water system according to the predicted cooling capacity calculated by the multiple computing devices.

2. The system according to claim 1, characterized in that The terminal device comprises: Multiple terminal coils; A parameter acquisition module is used to obtain the cooling capacity parameters of each terminal coil; The model calling module is connected to the parameter acquisition module and is used to generate the actual cooling capacity of each terminal coil according to the cooling capacity parameters of each terminal coil; The first aggregation module is used to aggregate the actual cooling capacity of each terminal coil to generate the total actual cooling capacity; The first communication module is used to send the total actual cooling capacity to the corresponding computing device.

3. The system according to claim 1, characterized in that The computing device comprises: A load prediction module, used to calculate the total actual cooling capacity as the predicted cooling capacity according to a preset load prediction model; The second communication module includes a receiving submodule for receiving the total actual cooling capacity sent by the terminal device; and a sending submodule for sending the predicted cooling capacity to the control device.

4. The system according to claim 3, characterized in that The sending submodule is also used to adjust the actual cooling capacity of the terminal coil according to a preset group planning algorithm when the total actual cooling capacity is outside the set range, until the total actual cooling capacity is adjusted to within the set range, and send the total actual cooling capacity to the control device.

5. The system according to any one of claims 1 to 4, characterized in that: The control device comprises: A third communication module is used to receive the predicted cooling capacity sent by the computing device; and, is used to send a control instruction to the water system; A second aggregation module is used to aggregate the predicted cooling capacity sent by multiple computing devices to generate a total predicted cooling capacity; A data acquisition module, used to acquire environmental parameters and user control data; The optimization module is used to perform coupled solution based on the total predicted cooling capacity, environmental parameters and user control data, generate optimal control parameters, and generate control instructions based on the optimal control parameters.

6. A terminal device for a water multi-connection system, characterized in that: include: A regulating module for distributing the cooling capacity generated by the water system; The cooling capacity generation module generates actual cooling capacity according to the collected cooling capacity parameters; wherein the actual cooling capacity is used to generate predicted cooling capacity.

7. The terminal device according to claim 6, characterized in that: The cold energy generation module comprises: A parameter acquisition module is used to obtain the cooling capacity parameters of each terminal coil; The model calling module is connected to the parameter acquisition module and is used to generate the actual cooling capacity of each terminal coil according to the cooling capacity parameters of each terminal coil; The first aggregation module is used to aggregate the actual cooling capacity of each terminal coil to generate the total actual cooling capacity; The first communication module is used to send the total actual cooling capacity to the corresponding computing device.

8. A computing device for a water multi-connection system, characterized in that: include: A calculation module, for calculating predicted cooling capacity based on actual cooling capacity generated by one or more terminal devices; wherein the predicted cooling capacity is used to generate control instructions for adjusting the cooling capacity of the water system; and, The control module is used to generate adjustment instructions for controlling the operation of the terminal equipment.

9. The computing device according to claim 8, characterized in that The computing module comprises: A load prediction module, used to calculate the total actual cooling capacity as the predicted cooling capacity according to a preset load prediction model; The second communication module includes a receiving submodule for receiving the total actual cooling capacity sent by the terminal device; and a sending submodule for sending the predicted cooling capacity to the control device.

10. The computing device according to claim 9, characterized in that The sending submodule is also used to adjust the actual cooling capacity of the terminal coil according to a preset group planning algorithm when the total actual cooling capacity is outside the set range, until the total actual cooling capacity is adjusted to within the set range, and send the total actual cooling capacity to the control device.

11. A control device for a water multi-connection system, characterized in that: include: The processing module is used to generate a control instruction for adjusting the cooling capacity of the water system according to the predicted cooling capacity calculated by the computing device.

12. The control device according to claim 11, characterized in that The processing module comprises: A third communication module is used to receive the predicted cooling capacity sent by the computing device; and, is used to send a control instruction to the water system; A second aggregation module is used to aggregate the predicted cooling capacity sent by multiple computing devices to generate a total predicted cooling capacity; A data acquisition module, used to acquire environmental parameters and user control data; The optimization module is used to perform coupled solution based on the total predicted cooling capacity, environmental parameters and user control data, generate optimal control parameters, and generate control instructions based on the optimal control parameters.

Citation Information

Patent Citations

  • Water multi-split system, end equipment, computing equipment and control equipment

    CN119022409A

  • Multi-split air conditioning system and status switching control method therefor

    CN103206750A

  • Central arithmetic type multi-split air conditioner system and state switching control method thereof

    CN103644621A

  • Water chiller management control system based on cloud computing

    CN106556190A

  • Multi-split control system

    CN106765741A

Cited By

  • Industrial load management and control method based on cloud edge cooperation technology

    CN119966996A