Water multi-connected system, end device, computing device, and control device

Abstract

The application relates to the technical field of intelligent household appliances, and discloses a water multi-connected system, a terminal device, a computing device and a control device, which comprise: a plurality of terminal devices, which are used for distributing cold energy generated by a water system, and generating actual cold energy according to collected cold energy parameters; a plurality of computing devices, each of which is connected with one or more terminal devices, and is used for calculating predicted cold energy according to the actual cold energy generated by the one or more terminal devices, and generating adjusting instructions for controlling the operation of the terminal devices; and a control device, which is connected with the plurality of computing devices, and is used for generating control instructions for adjusting the refrigeration capacity of the water system according to the predicted cold energy calculated by the plurality of computing devices. In this way, a large amount of cold energy data is dispersed to the plurality of computing devices for calculation, the data calculation time is shortened, the control authority is dispersed to the computing devices, and fast response is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent household appliances, for example to a water multi-connected system, a terminal device, a computing device and a control device. BACKGROUND

[0002] At present, the energy consumption of a central air conditioning system accounts for a large proportion of building energy consumption. During air conditioning operation, there is a demand to reduce air conditioning energy consumption.

[0003] To address the demand to reduce air conditioning energy consumption, the related art discloses a terminal cooling capacity balancing control system, comprising: a terminal device and a control device. The terminal device collects total cooling capacity requirements of each terminal and communicates with an air conditioning host. The air conditioning host calculates the optimal number of running refrigerators and the running frequency of a water pump, and controls the device to run. Then, a PID controller is used to adjust the frequency of the terminal air pipe, so as to realize dynamic adjustment of the chilled water system according to the requirements of terminal loads, and ensure energy-saving operation of the system.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that at least the following problems exist in the related art:

[0005] Although the related art reduces the running energy consumption of the air conditioning system, all collected data is fed back to the air conditioning host for calculation, which results in a large amount of calculation data and slow response time.

[0006] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present application, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0007] To have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not a general review, nor is it intended to determine key / important components or delineate the scope of protection of these embodiments, but as a prelude to the detailed description below.

[0008] The embodiments of the present disclosure provide a water multi-connected system, a terminal device, a computing device and a control device to reduce the calculation pressure of the air conditioning host and speed up the response rate.

[0009] In some embodiments, the water multi-connected system comprises: a terminal device, configured to distribute the cooling capacity generated by a water system, and generate actual cooling capacity according to collected cooling capacity parameters; a plurality of computing devices, each of which is connected with one or more terminal devices, configured to calculate predicted cooling capacity according to the actual cooling capacity generated by the one or more terminal devices, and generate adjustment instructions for controlling the operation of the terminal device; and a control device, connected with the plurality of computing devices, configured to generate control instructions for adjusting the refrigeration capacity of the water system according to the predicted cooling capacity calculated by the plurality of computing devices.

[0010] In some embodiments, the terminal device comprises: a plurality of terminal coils; a parameter acquisition module configured to acquire a cooling capacity parameter of each terminal coil; a model calling module connected to the parameter acquisition module and configured to generate an actual cooling capacity of each terminal coil according to the cooling capacity parameter of each terminal coil; a first aggregation module configured to aggregate the actual cooling capacity of each terminal coil to generate a total actual cooling capacity; and a first communication module configured to send the total actual cooling capacity to a corresponding computing device.

[0011] In some embodiments, the model calling module comprises: a calling submodule configured to call a cooling capacity model after receiving the cooling capacity parameter of the corresponding terminal coil; and a cooling capacity generation module configured to map the cooling capacity parameter of each terminal coil to the actual cooling capacity of each terminal coil according to the cooling capacity model.

[0012] In some embodiments, the computing device comprises: a load prediction module configured to calculate the total actual cooling capacity as a predicted cooling capacity according to a preset load prediction model; a second communication module comprising a receiving submodule configured to receive the total actual cooling capacity sent by the terminal device, and a sending submodule configured to send the predicted cooling capacity to a control device.

[0013] In some embodiments, the sending submodule is further configured to, in a case where the total actual cooling capacity is outside a set range, adjust the actual cooling capacity of the terminal coil according to a preset swarm planning algorithm until the total actual cooling capacity is adjusted to be within the set range, and send the total actual cooling capacity to the control device.

[0014] In some embodiments, the set range is 95% to 105% of the predicted cooling capacity.

[0015] In some embodiments, the computing device further comprises: a fuzzy control module configured to acquire a cooling capacity error, a cooling capacity error change rate, a fuzzy control rule table, and membership parameters, perform fuzzy output according to the cooling capacity error, the cooling capacity error change rate, the fuzzy control rule table, and the membership parameters, and generate a fuzzy signal; and an instruction generation module configured to generate a PID signal according to the fuzzy signal, and generate an adjustment instruction according to the PID signal.

[0016] In some embodiments, the control device comprises: a third communication module configured to receive the predicted cooling capacity sent by the computing device, and send a control instruction to a water system; a second aggregation module configured to aggregate the predicted cooling capacities sent by a plurality of computing devices to generate a total predicted cooling capacity; a data acquisition module configured to acquire environmental parameters and user control data; and an optimization module configured to perform coupled solution according to the total predicted cooling capacity, the environmental parameters, and the user control data, generate an optimal control parameter, and generate the control instruction according to the optimal control parameter.

[0017] In some embodiments, the terminal device for a water multi-connected system comprises: an adjustment module for distributing the cooling capacity generated by the water system; a cooling capacity generation module for generating actual cooling capacity according to collected cooling capacity parameters; wherein the actual cooling capacity is used to generate predicted cooling capacity.

[0018] In some embodiments, the cooling capacity generation module comprises: a parameter acquisition module for acquiring cooling capacity parameters of each terminal coil; a model calling module connected with the parameter acquisition module for generating actual cooling capacity of each terminal coil according to the cooling capacity parameters of each terminal coil; a first aggregation module for aggregating the actual cooling capacity of each terminal coil to generate total actual cooling capacity; and a first communication module for sending the total actual cooling capacity to a corresponding computing device.

[0019] In some embodiments, the model calling module comprises: a calling sub-module for calling a cooling capacity model after receiving the cooling capacity parameters of the corresponding terminal coil; and a cooling capacity generation module for mapping the cooling capacity parameters of each terminal coil to the actual cooling capacity of each terminal coil according to the cooling capacity model.

[0020] In some embodiments, the computing device for a water multi-connected system comprises: a computing module for calculating predicted cooling capacity according to 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 device.

[0021] In some embodiments, the computing module comprises: a load prediction module for calculating the total actual cooling capacity as predicted cooling capacity according to a preset load prediction model; a second communication module comprising a receiving sub-module for receiving the total actual cooling capacity sent by the terminal device; and a sending sub-module for sending the predicted cooling capacity to a control device.

[0022] In some embodiments, the sending sub-module is further configured to, in the case that the total actual cooling capacity is outside a set range, adjust the actual cooling capacity of the terminal coil according to a preset swarm optimization algorithm until the total actual cooling capacity is adjusted to be within the set range, and send the total actual cooling capacity to the control device.

[0023] In some embodiments, the set range is 95% to 105% of the predicted cooling capacity.

[0024] In some embodiments, the computing device further comprises: a fuzzy control module for acquiring cooling capacity error, cooling capacity error change rate, fuzzy control rule table and membership parameter, performing fuzzy output according to the cooling capacity error, cooling capacity error change rate, fuzzy control rule table and membership parameter, and generating a fuzzy signal; and an instruction generation module for generating a PID signal according to the fuzzy signal and generating adjustment instructions according to the PID signal.

[0025] In some embodiments, the control device for the water multi-connected system comprises a processing module configured to generate control instructions for adjusting the refrigeration capacity of the water system according to the predicted cooling capacity calculated by the computing device.

[0026] In some embodiments, the processing module comprises a third communication module configured to receive the predicted cooling capacity sent by the computing device and send the control instructions to the water system; a second aggregation module configured to aggregate the predicted cooling capacities sent by the plurality of computing devices to generate a total predicted cooling capacity; a data acquisition module configured to acquire environmental parameters and user control data; and an optimization module configured to perform coupled solution according to the total predicted cooling capacity, the environmental parameters and the user control data to generate optimal control parameters, and generate the control instructions according to the optimal control parameters.

[0027] The water multi-connected system, the terminal device, the computing device and the control device provided by the embodiments of the present disclosure can achieve the following technical effects:

[0028] A plurality of computing devices are provided, and the computing devices are configured to calculate predicted cooling capacity according to the cooling capacity data collected by the terminal and transmit the predicted cooling capacity to the control device. The control device is configured to issue control instructions to the water system according to the predicted cooling capacity, and the water system is configured to generate cooling capacity according to the control instructions. Finally, the computing device adjusts the terminal. In this way, a plurality of independent computing devices are provided, and a large amount of cooling capacity data is distributed to the plurality of computing devices for calculation, thereby shortening the data calculation time. Moreover, the control authority is distributed to the computing devices to achieve fast response. Therefore, the computing pressure of the air conditioner host can be reduced, and the response rate can be accelerated.

[0029] The foregoing general description and the following description are only exemplary and explanatory, and are not intended to limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0030] One or more embodiments are exemplarily illustrated by corresponding drawings, which do not constitute limitation on the embodiments, and elements with the same reference numerals in the drawings are shown as similar elements, the drawings do not constitute proportional limitation, and wherein:

[0031] Figure 1 is a water multi-connected system structure schematic diagram provided by the embodiments of the present disclosure;

[0032] Figure 2 is a terminal device structure schematic diagram provided by the embodiments of the present disclosure;

[0033] Figure 3 is a model calling module structure schematic diagram provided by the embodiments of the present disclosure;

[0034] Figure 4 is a computing device structure schematic diagram provided by the embodiments of the present disclosure;

[0035] Figure 5 is a flowchart for establishing a load prediction model provided by an embodiment of the present disclosure;

[0036] Figure 6 is a control device structure schematic diagram provided by an embodiment of the present disclosure;

[0037] Figure 7 is an actual application structure schematic diagram provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0038] In order to enable a person skilled in the art to more fully understand the features and technical contents of the embodiments of the present disclosure, the implementation of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings, which are only used for reference and do not limit the embodiments of the present disclosure. In the following technical description, in order to facilitate explanation, a plurality of details are provided to provide a full understanding of the disclosed embodiments. However, one or more embodiments can still be implemented without these details. In other cases, in order to simplify the drawings, well-known structures and devices can be simplified.

[0039] The terms "first", "second", and the like in the specification and claims of the embodiments of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion.

[0040] Unless otherwise specified, the term "a plurality of" means two or more.

[0041] The term "corresponding" can refer to an association or binding relationship. A and B correspond to each other means that A and B have an association or binding relationship.

[0042] It should be noted that the embodiments in the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0043] In combination Figure 1As shown, the embodiment of the present disclosure provides a water multi-connected system, which comprises a plurality of terminal devices 130, a plurality of computing devices 120 and a control device 110. Wherein, the terminal device 130 is used to distribute the cooling capacity generated by the water system, and generate the actual cooling capacity according to the collected cooling capacity parameters; each computing device 120 is connected with one or more terminal devices 130 respectively, and is used to calculate the predicted cooling capacity according to the actual cooling capacity generated by the one or more terminal devices 130, and generate the adjustment instruction for controlling the operation of the terminal device 130; the control device 110 is connected with the plurality of computing devices 120 respectively, and is used to generate the control instruction for adjusting the refrigeration capacity of the water system according to the predicted cooling capacity calculated by the plurality of computing devices 120.

[0044] A plurality of computing devices are arranged, and the computing devices are used to calculate the predicted cooling capacity according to the cooling capacity data collected by the terminal, and transmit the predicted cooling capacity to the control device. The control device generates the control instruction for the water system according to the predicted cooling capacity, the water system generates the cooling capacity according to the control instruction, and finally the computing device adjusts the terminal device. In this way, a plurality of independent computing devices are arranged, a large amount of cooling capacity data is dispersed to the plurality of computing devices for calculation, so that the data calculation time is shortened, and the control authority is dispersed to the computing devices, so that the response is fast. Therefore, the computing pressure of the air conditioner host can be reduced, and the response rate can be accelerated.

[0045] Optionally, in combination with Figure 1 and Figure 2 As shown, the terminal device 130 comprises a terminal coil 131, a parameter acquisition module 132, a model calling module 133, a first summarizing module 134 and a first communication module 135. Wherein, the parameter acquisition module 132 is used to acquire the cooling capacity parameters of each terminal coil 131; the model calling module 133 is connected with the parameter acquisition module 132, and is used to generate the actual cooling capacity of each terminal coil 131 according to the cooling capacity parameters of each terminal coil 131; the first summarizing module 134 is used to summarize the actual cooling capacity of each terminal coil 131 to generate the total actual cooling capacity; and the first communication module 135 is used to send the total actual cooling capacity to the corresponding computing device 120.

[0046] Optionally, the cooling capacity parameters comprise part or all of the environmental parameters, the control parameters, the people flow intensity, the fresh air volume and the comfort degree. The actual cooling capacity of each terminal coil is generated according to the cooling capacity parameters, so that the cooling capacity of each region is counted, which is convenient for subsequent cooling supply according to the region, thereby helping the system to run energy-efficiently.

[0047] Optionally, in combination with Figure 2 and Figure 3As shown, the model calling module 133 includes a calling sub-module 1331 and a cold quantity generation module 1332. The calling sub-module 1331 is configured to call the cold quantity model after receiving the cold quantity parameter of the corresponding terminal coil 131; and the cold quantity generation module 1332 is configured to map the cold quantity parameter of each terminal coil 131 to the actual cold quantity of each terminal coil 131 according to the cold quantity model.

[0048] The preset cold quantity model is used to map the cold quantity parameter to the actual cold quantity, so as to accelerate the generation rate of the actual cold quantity and reduce the calculation pressure.

[0049] Optionally, the cold quantity model is stored in the computing device, and the modeling of the cold quantity model includes some or all of the input environmental parameters, the control parameters, the human flow intensity, the fresh air volume, and the comfort level. The standardized model is used to train a mapping function relationship.

[0050] The standardized model can be a black box model or an expression model.

[0051] Optionally, in combination with Figure 1 and Figure 4 As shown, 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 cold quantity as a predicted cold quantity according to a preset load prediction model; and the second communication module 122 includes a receiving sub-module and a sending sub-module. The receiving sub-module is configured to receive the total actual cold quantity sent by the terminal device 130; and the sending sub-module is configured to send the predicted cold quantity to the control device 110.

[0052] The plurality of computing devices are used to respectively predict the next time cold quantity of the corresponding terminal coil, so as to improve the prediction accuracy, facilitate subsequent regional cooling, disperse the calculation pressure, and accelerate the response rate.

[0053] In the load prediction, according to the actual situation of the computing device and the historical operation data of the computing device, the overall load of the area covered by the computing device is predicted, and the historical load data of the area corresponding to each computing device needs to be preliminarily processed.

[0054] In this embodiment, the long short-term memory network plus attention mechanism is used to predict the load of each computing device, and the main factors to be considered include the external temperature, the external radiation intensity, the external enthalpy, the fresh air volume, and the previous time load data.

[0055] In combination with Figure 5 As shown, the process of establishing the load prediction model by using the long short-term memory network plus attention mechanism includes:

[0056] S101, obtaining a data structure;

[0057] S102, cleaning the data;

[0058] S103, completing feature quantity of the cleaned data;

[0059] S104, dividing the data after completion of feature quantity into a training set and a test set;

[0060] S105, training the data in the training set to generate a load prediction model;

[0061] S106, testing the load prediction model by using the data in the test set;

[0062] S107, outputting the load prediction model.

[0063] Optionally, the acquisition and cleaning of the data are based on time, so as to ensure that the data correspond to time, and in the case of missing data, a corresponding time is not directly deleted. The completion of feature quantity of the data includes extraction of seasonal factors and filling of missing values. It is suggested that the missing values be first completed by completing seasonal factors, for example, whether it is a working day, the number of hours, the month, the week of the year, etc. Then, interpolation is performed in a machine learning manner, for example, K-nearest neighbor, etc. In this way, the completion of missing values and the enhancement of periodic characteristics can be achieved.

[0064] Optionally, the training set and the test set can be divided according to a certain proportion. The training set is used for training and generating a load prediction model, and the test set is used for testing the generated load prediction model.

[0065] In the embodiment, the output load prediction model is saved on the computing device, and the training model for establishing the load prediction model is saved on the host computer, i.e., the cloud server of the control device. In each prediction of load, the computing device is directly run, and the training model is used to train the load prediction model periodically to update the deployed model parameters.

[0066] Optionally, the sending sub-module is further configured to, in a case where 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 be within the set range, and send the total actual cooling capacity to the control device.

[0067] Optionally, the set range is 95% to 105% of the predicted cooling capacity of the terminal coil, and specifically can be 95%, 97%, 103% or 105%.

[0068] In the case that the total actual cooling capacity on the terminal coil does not meet the predicted cooling capacity, the sending submodule automatically triggers the group planning algorithm to regulate the corresponding terminal coil with the minimum comfort sacrifice, so as to realize that the total actual cooling capacity meets the predicted cooling capacity range. In this way, the accuracy of the cooling capacity prediction can be improved, and the cooling can be supplied according to the needs of the region, and the comfort degree is emphasized while the energy-saving space is maximized.

[0069] Optionally, as shown in Figure 1 and Figure 4 As shown, 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, perform fuzzy output according to the cooling capacity error, the cooling capacity error change rate, the fuzzy control rule table and the membership parameter, and generate a fuzzy signal; and the instruction generation module 124 is configured to generate a PID signal according to the fuzzy signal, and generate an adjustment instruction according to the PID signal.

[0070] In actual application, 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 parameter, the fuzzy controller performs fuzzy output and generates a fuzzy signal; and the PID controller generates an adjustment instruction for adjusting the frequency of the terminal coil according to the fuzzy signal.

[0071] The computing device controls the frequency of the terminal coil according to the fuzzy control module and the instruction generation module, so that the air system control authority of the host computer is dispersed to the computing device. In this way, the response can be quickly. At the same time, when the computing device controls the frequency of the terminal coil, the fuzzy control gives the control freedom, and the comfort degree and the cooling capacity supply are not strictly divided, which helps to reduce the calculation pressure.

[0072] Optionally, as shown in Figure 1 and Figure 6 As shown, the control device 110 includes a third communication module 111, a second summarizing 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 configured to send a control instruction to the water system; the second summarizing module 112 is configured to summarize the predicted cooling capacities sent by the plurality of 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 coupled solution according to the total predicted cooling capacity, the environmental parameters and the user control data to generate optimal control parameters, and generate a control instruction according to the optimal control parameters.

[0073] The optimization module can be a cloud solver. After receiving the total predicted cooling capacity, the cloud solver reads the current environmental parameters according to the required real-time variables in the preset fitness objective function. Meanwhile, the user needs to input the adjustable range of the control parameters to be optimized and customize the boundary conditions, which are coupled into the fitness objective function of the cloud solver, so as to solve the optimal control parameters and issue commands to the water system refrigeration.

[0074] After the water system refrigeration, the environmental parameters, control parameter range, boundary conditions and time characteristics change accordingly, forming a control closed loop. On this basis, the water system can actively respond to real-time loads and ensure the optimal operation of each device, realizing multi-level autonomous brain control.

[0075] Optionally, an end device for a water multi-split system includes an adjustment module and a cooling capacity generation module. The adjustment 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 according to collected cooling capacity parameters; wherein the actual cooling capacity is used to generate predicted cooling capacity.

[0076] Optionally, the cooling capacity generation module includes a plurality of end coils, a parameter acquisition module, a model calling module, a first summary module and a first communication module. The parameter acquisition module is used to acquire the cooling capacity parameters of each end coil; the model calling module is connected with the parameter acquisition module and is used to generate the actual cooling capacity of each end coil according to the cooling capacity parameters of each end coil; the first summary module is used to summarize the actual cooling capacity of each end coil to generate total actual cooling capacity; and the first communication module is used to send the total actual cooling capacity to the corresponding computing device.

[0077] Optionally, the cooling capacity parameters include part or all of the environmental parameters, control parameters, passenger flow intensity, fresh air volume and comfort level. The actual cooling capacity of each end coil is generated according to the cooling capacity parameters, so as to count the cooling capacity of each area, facilitate subsequent cooling supply by area, and thus help the system to run energy-efficiently.

[0078] Optionally, the model calling module includes a calling sub-module and a cooling capacity generation module. The calling sub-module is used to call the cooling capacity model after receiving the cooling capacity parameters of the corresponding end coil; and the cooling capacity generation module is used to map the cooling capacity parameters of each end coil to the actual cooling capacity of each end coil according to the cooling capacity model.

[0079] The preset cooling capacity model is used to map the cooling capacity parameters to the actual cooling capacity, so as to accelerate the generation rate of the actual cooling capacity and reduce the calculation pressure.

[0080] Optionally, the cooling capacity model is stored in the computing device. The modeling of the cooling capacity model includes inputting part or all of the environmental parameters, control parameters, passenger flow intensity, fresh air volume and comfort level, using a standardized model, and training to generate a mapping function relationship.

[0081] The standardized model can be a black box model or an expression model.

[0082] Optionally, a computing device for a water multi-connected system includes a computing module and a control module. The computing module is configured to calculate 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. The control module is configured to generate adjustment instructions for controlling the operation of the terminal device.

[0083] Optionally, the computing module includes a load prediction module configured to calculate 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 configured to receive the total actual cooling capacity sent by the terminal device; and a sending submodule configured to send the predicted cooling capacity to the control device.

[0084] Using multiple computing devices to respectively predict the next time cooling capacity of the corresponding terminal coil helps to improve the accuracy of the prediction, facilitate subsequent regional cooling, and also distribute the computing pressure and speed up the response rate.

[0085] In load prediction, according to the actual situation of the computing device and the historical operation data of the computing device, the overall load of the area covered by the computing device is predicted, which requires preliminary processing of historical data into historical load data of the area corresponding to each computing device.

[0086] In this embodiment, long short-term memory network plus attention mechanism is used to predict the load of each computing device, and the main factors to be considered are: external temperature, external radiation intensity, external enthalpy, fresh air volume, and previous time load data.

[0087] As shown in Figure 5 The process of establishing a load prediction model using long short-term memory network plus attention mechanism includes:

[0088] S101, obtaining a data structure;

[0089] S102, cleaning the data;

[0090] S103, completing feature quantities of the cleaned data;

[0091] S104, dividing the data with completed feature quantities into a training set and a test set;

[0092] S105, training the data in the training set using a network to generate a load prediction model;

[0093] S106, testing the load prediction model using data in the test set;

[0094] S107, output the load prediction model.

[0095] Optionally, the data acquisition and cleaning are time-based, ensuring that the data corresponds to the time, and in the case of data missing, a corresponding time is not directly deleted. The feature quantity completion of the data includes: extraction of seasonal factors and filling of missing values. Among them, it is suggested to first complete the seasonal factors for filling missing values. For example, whether it is a working day, the number of hours, the month, the first week of the year, etc. Then take a machine learning-like way to interpolate, such as K-nearest neighbor, etc. In this way, the missing value can be completed, and the periodic feature can be enhanced.

[0096] Optionally, the training set and the test set can be divided according to a certain proportion; the training set is used for training and generating the load prediction model, and the test set is used for testing the generated load prediction model.

[0097] In this embodiment, the output load prediction model is saved on the computing device, and the training model for establishing the load prediction model is saved on the cloud server of the control device. In each prediction of the load, the training model is directly run on the computing device, and the deployed model parameters are updated by periodically training the load prediction model.

[0098] Optionally, the sending submodule is further configured to, in a case where the total actual cold quantity is outside the set range, adjust the actual cold quantity of the terminal coil according to a preset group planning algorithm until the total actual cold quantity is adjusted to be within the set range, and send the total actual cold quantity to the control device.

[0099] Optionally, the set range is 95% to 105% of the predicted cold quantity, and specifically can be 95%, 97%, 103%, or 105%.

[0100] In a case where the total actual cold quantity on the terminal coil does not conform to the predicted cold quantity, the sending submodule automatically triggers the group planning algorithm to regulate the corresponding terminal coil with the smallest comfort sacrifice, so that the total actual cold quantity conforms to the predicted cold quantity range. In this way, the accuracy of the cold quantity prediction can be improved, and cold supply can be realized according to the needs of the region, emphasizing comfort while maximizing energy-saving space.

[0101] Optionally, the computing device further comprises a fuzzy control module configured to acquire a cold quantity error, a cold quantity error change rate, a fuzzy control rule table, and membership degree parameters, perform fuzzy output according to the cold quantity error, the cold quantity error change rate, the fuzzy control rule table, and the membership degree parameters, and generate a fuzzy signal; and an instruction generation module configured to generate a PID signal according to the fuzzy signal and generate an adjustment instruction according to the PID signal.

[0102] 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, the fuzzy controller performs fuzzy output to generate a fuzzy signal; and the PID controller generates an adjustment instruction for adjusting the frequency of the terminal coil according to the fuzzy signal.

[0103] The computing device controls the frequency of the terminal coil according to the fuzzy control module and the instruction generation module, so that the air system control authority of the host computer is dispersed to the computing device. In this way, it is helpful to quickly respond. At the same time, when the computing device controls the frequency of the terminal coil, the fuzzy control gives the control freedom, and does not strictly divide the comfort and the cooling capacity supply, which helps to reduce the computing pressure.

[0104] Optionally, a control device for a water multi-connected system includes a processing module for generating a control instruction for adjusting the cooling capacity of the water system according to the predicted cooling capacity calculated by the computing device.

[0105] Optionally, the processing module includes a third communication module for receiving the predicted cooling capacity sent by the computing device; and for sending the control instruction to the water system; a second aggregation module for aggregating the predicted cooling capacities sent by the plurality of 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 coupling solving according to the total predicted cooling capacity, the environmental parameters and the user control data to generate optimal control parameters, and generating the control instruction according to the optimal control parameters.

[0106] The optimization module can be a cloud solver. After the cloud solver receives the total predicted cooling capacity, it reads the current environmental parameters according to the real-time variables required in the preset fitness objective function. At the same time, the user needs to input the adjustable range of the control parameter to be optimized and customize the boundary conditions, and couple them into the fitness objective function of the cloud solver, so as to solve the optimal control parameter and issue a command to the water system refrigeration.

[0107] After the water system refrigeration, the environmental parameters, the control parameter range, the boundary conditions and the time characteristics change accordingly to form a control closed loop. On this basis, the water system can actively respond to the real-time load and ensure the optimal operation of each device to realize multi-level autonomous brain control.

[0108] In combination Figure 7 As shown in the figure, in practical applications, the terminal device is set as a terminal autonomous execution node; the computing device includes a plurality of computing nodes and is set as a secondary computing node; and the control device includes a cloud solver, an intelligent control cabinet and a water system device, and is set as a highest control node.

[0109] The terminal coil collects cold energy and reports to the corresponding computing node; the computing node calls the load prediction model to predict the cold energy, generates predicted cold energy, and transmits the predicted cold energy 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 cold energy, real-time environmental parameters, control parameters and boundary conditions, obtains the optimal control parameters, and issues commands to the intelligent control cabinet; the intelligent control cabinet adjusts the refrigeration of the water system according to the commands; the computing node calls the terminal optimization model, i.e. fuzzy control, to regulate the frequency of the terminal coil.

[0110] In this way, the control authority of the air conditioning system controlled by the host computer is dispersed to the computing nodes for control, so that fast response is realized.

[0111] In the embodiment, multiple node layers can be arranged between the terminal device and the control device, which helps to further improve the prediction accuracy and thus improve the energy saving space, and meanwhile, the node layer itself has computing capability and can operate independently of the cloud computing layer.

[0112] The above description and drawings sufficiently illustrate the embodiments of the present disclosure to enable one skilled in the art to practice them. Other embodiments can include structural, logical, electrical, process, and other changes. The embodiments represent only a few of the possible variations. Individual components and functions are optional unless explicitly required, and the order of operations can be changed. Parts and features of some embodiments can be included or replaced by parts and features of other embodiments. Also, the words used in this application are only used to describe the embodiments and are not intended to limit the claims. As used in the description of the embodiments and the claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise. Similarly, as used in this application, the term "and / or" means to include one or more associated listed items in any and all possible combinations. In addition, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" and the like mean the presence of the stated features, integers, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. Without more limitations, the element defined by the statement "comprises one" does not exclude the presence of additional identical elements in the process, method, or device that includes the stated element. In this document, each embodiment focuses on the differences from other embodiments, and the same or similar parts between embodiments can be referred to each other. For the methods, products, etc. disclosed by the embodiments, if they correspond to the method part disclosed by the embodiments, the relevant parts can be referred to the description of the method part.

Claims

1. A water chiller system comprising a water system for refrigeration, characterized by, Also comprising: a plurality of end devices for distributing the cooling capacity generated by the water system, and generating actual cooling capacity according to collected cooling capacity parameters; a plurality of computing devices, each connected to one or more end devices, for calculating predicted cooling capacity according to the actual cooling capacity generated by the one or more end devices, and generating adjustment instructions for controlling the operation of the end devices; a control device connected to the plurality of computing devices, for generating control instructions for adjusting the cooling capacity of the water system according to the predicted cooling capacity calculated by the plurality of computing devices; the computing device comprising: a load prediction module for calculating the total actual cooling capacity as predicted cooling capacity according to a preset load prediction model; a second communication module including a receiving submodule for receiving the total actual cooling capacity sent by the end device, and a sending submodule for sending the predicted cooling capacity to the control device, and further for adjusting the actual cooling capacity of the end coil according to a preset swarm optimization algorithm if the total actual cooling capacity is outside the set range, until the total actual cooling capacity is adjusted to within the set range, and sending the total actual cooling capacity to the control device.

2. The system of claim 1, wherein, The end device comprises: a plurality of end coils; a parameter acquisition module for acquiring cooling capacity parameters of each end coil; a model calling module connected to the parameter acquisition module for generating actual cooling capacity of each end coil according to the cooling capacity parameters of each end coil; a first aggregation module for aggregating the actual cooling capacity of each end coil to generate total actual cooling capacity; a first communication module for sending the total actual cooling capacity to the corresponding computing device.

3. The system of claim 1, wherein, The control device comprises: a third communication module for receiving the predicted cooling capacity sent by the computing device, and for sending the control instructions to the water system; a second aggregation module for aggregating the predicted cooling capacity sent by the plurality of computing devices to generate total predicted cooling capacity; a data acquisition module for acquiring environmental parameters and user control data; an optimization module for coupling and solving according to the total predicted cooling capacity, environmental parameters and user control data to generate optimal control parameters, and generating control instructions according to the optimal control parameters.

4. An end device for use in a water multi-connected system as claimed in any one of claims 1 to 3, characterized in that Comprising: an adjustment module for distributing the cooling capacity generated by the water system; a cooling capacity generation module for generating actual cooling capacity according to collected cooling capacity parameters; wherein the actual cooling capacity is used to generate predicted cooling capacity.

5. The end device of claim 4, wherein, The cooling capacity generation module comprises: a parameter acquisition module for acquiring cooling capacity parameters of each end coil; a model calling module connected to the parameter acquisition module for generating actual cooling capacity of each end coil according to the cooling capacity parameters of each end coil; a first aggregation module for aggregating the actual cooling capacity of each end coil to generate total actual cooling capacity; a first communication module for sending the total actual cooling capacity to the corresponding computing device.

6. A computing device for use in a water chiller system as claimed in any one of claims 1 to 3, characterized in that, Comprising: a computing module for calculating predicted cooling capacity according to the actual cooling capacity generated by one or more end 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 end devices.

7. The computing device of claim 6, wherein, The computing module comprises: a load prediction module for calculating the total actual cooling capacity as predicted cooling capacity according to a preset load prediction model; a second communication module including a receiving submodule for receiving the total actual cooling capacity sent by the end device, and a sending submodule for sending the predicted cooling capacity to the control device, and further for adjusting the actual cooling capacity of the end coil according to a preset swarm optimization algorithm if the total actual cooling capacity is outside the set range, until the total actual cooling capacity is adjusted to within the set range, and sending the total actual cooling capacity to the control device. The second communication module comprises a receiving submodule for receiving the total actual cold quantity sent by the terminal device, and a sending submodule for sending the predicted cold quantity to the control device.

8. The computing device of claim 7, wherein, The sending submodule is further configured to, in a case where the total actual cold quantity is outside the set range, adjust the actual cold quantity of the terminal coil according to a preset group planning algorithm until the total actual cold quantity is adjusted to be within the set range, and send the total actual cold quantity to the control device.

9. A control device for the water chiller system as claimed in any one of claims 1 to 3, characterized in that, The method comprises: The processing module is configured to generate a control instruction for adjusting the refrigeration capacity of the water system according to the predicted cold quantity calculated by the computing device.

10. The control device according to claim 9, characterized by The processing module comprises: The third communication module is configured to receive the predicted cold quantity sent by the computing device, and send the control instruction to the water system. The second aggregation module is configured to aggregate the predicted cold quantities sent by the plurality of computing devices to generate a total predicted cold quantity. The data acquisition module is configured to acquire environmental parameters and user control data. The optimization module is configured to perform coupled solving according to the total predicted cold quantity, the environmental parameters and the user control data to generate optimal control parameters, and generate the control instruction according to the optimal control parameters.

Images