Control Method, Device and System for Air Conditioning Operating Load

Abstract

This application discloses a method, device, and system for controlling the operating load of an air conditioner. The system comprises: a computer device having a communication interface for acquiring basic data, a neural network model running on the computer device, and the neural network model generating load forecasts for the air conditioner system using the basic data required for load forecasting; and an air conditioner group control system connected to the computer device for controlling the operation of the air conditioner system according to the load forecast results. This application can address the technical issue of high energy consumption in air conditioner system operation.

Description

Technical Field

[0001] The present application relates to the field of air conditioning technology, and more specifically, to a method, device, and system for controlling the operating load of an air conditioner. Background Art

[0002] Due to the complexity of ice-storage air conditioning systems, traditional air conditioning system control methods cannot effectively meet system requirements. Therefore, to optimize ice storage and melting control strategies, air conditioning operating load forecasting is required to achieve economical operation. Air conditioning operating load forecasting refers to the prediction of the cooling and heating requirements for future air conditioning system operation during the building operation phase. It has developed with the rise of ice-storage air conditioning systems. Currently, with the development of air conditioning and new energy technologies, complex systems such as trigeneration systems and solar air conditioning systems have emerged. At the same time, building energy consumption has increased year by year, and the energy conservation and emission reduction situation has become increasingly severe. There is an urgent need to use air conditioning operating load forecasting software to optimize system control and achieve building energy conservation.

[0003] At present, hundreds of energy consumption simulation software have been developed at home and abroad, such as EnergyPlus and BLAST in the United States, ESP-r in the United Kingdom, and DeST in China, etc. These software are used to establish building simulation models, which can predict air-conditioning loads. However, these software are mainly widely used for load forecasting in the design stage, which does not match the purpose and effect of load forecasting in the operation stage; secondly, the modeling work and the acquisition of building influencing parameters are both difficult, and are not suitable for use by non-professional staff. Whether the selected software is inappropriate or the data is inappropriate, it will cause inaccurate predictions, which will in turn affect the energy consumption of the air-conditioning system in the building.

[0004] With respect to the technical problem of high energy consumption in the operation of the above-mentioned air-conditioning system, no effective solution has been proposed so far. Summary of the Invention

[0005] The embodiments of the present application provide a method, device, and system for controlling the operating load of an air conditioner to solve the technical problem of high energy consumption in the operation of an air conditioning system.

[0006] In order to solve the above technical problems, according to one aspect of an embodiment of the present application, a control system for air-conditioning operation load is provided, including: a computer device, the computer device having a communication interface for obtaining basic data, a neural network model running on the computer device, and the neural network model being used to generate a load forecast result of the air-conditioning system using the basic data, wherein the basic data is the data required for load forecasting; an air-conditioning group control, connected to the computer device, for controlling the operation of the air-conditioning system according to the load forecast result.

[0007] Optionally, the communication interface uses the Modbus TCP / IP communication protocol to obtain basic data from the air conditioning group control or third-party software; the basic data includes the cooling station supply water temperature, the cooling station return water temperature, the cooling capacity of the cooling station, the outdoor dry bulb temperature, the outdoor relative humidity, meteorological data, onboard load, dual-condition load and ice melting load.

[0008] Optionally, the neural network model is an LSTM neural network model, which is used to use basic data to generate load forecast results for the air-conditioning system in the next hour and the next 24 hours, and use the load forecast results in the next hour to update and optimize the load forecast results in the next 24 hours.

[0009] Optionally, load forecasting software for calling a neural network model is installed on the computer device, and the load forecasting software has at least one of the following functions: a new creation function, which is used to create a new project and configure the project name, geographical location, prediction data source, training data source, data training cycle and network address for the new project; a delete function, which is used to delete the project; a setting function, which is used to modify the project name, geographical location, prediction data source, training data source, data training cycle and network address of the project; a browse function, which is used to visualize the selected project, and the display content includes 24 hours of actual load data, load forecast results for the next 24 hours, ice melting load, dual-condition load and airborne load; a project management function, which is used to enter the new creation function, the delete function, the setting function and the browse function; a user management function, which is used to classify users and manage the permissions of each type of user; and a personal management function, which is used for users to modify their own user information.

[0010] According to another aspect of an embodiment of the present application, a method for controlling the operating load of an air conditioner is also provided, including: obtaining basic data required for load prediction through a communication interface; calling a neural network model and using the basic data to generate a load prediction result of the air conditioning system; and controlling the operation of the air conditioning system according to the load prediction result.

[0011] Optionally, a neural network model is called to generate a load forecast result of the air-conditioning system using basic data, including: preprocessing the basic data to remove abnormal data in the basic data, wherein the basic data includes the cooling station water supply temperature, the cooling station return water temperature, the cooling capacity of the cooling station, the outdoor dry bulb temperature, the outdoor relative humidity, meteorological data, the onboard load, the dual-condition load and the ice melting load; the preprocessed basic data is input into the neural network model matching the target engineering project to obtain the load forecast result of the air-conditioning system in the next 1 hour and the load forecast result in the next 24 hours, and the load forecast result in the next 1 hour is used to update and optimize the load forecast result in the next 24 hours, wherein the target engineering project is the engineering project where the basic data is located.

[0012] Optionally, before calling the neural network model and using basic data to generate a load forecast result for the air-conditioning system, the control method also includes: obtaining historical operating data of the target project; using the historical operating data to train the original model to obtain a neural network model that matches the target project.

[0013] Optionally, after the original model is trained using historical operating data to obtain a neural network model that matches the target engineering project, the control method further includes: when the interval between the previous training reaches a specified time length, the neural network model is trained and optimized using the data within the interval time length.

[0014] According to another aspect of an embodiment of the present application, a device for controlling the operating load of an air conditioner is also provided, including: an acquisition unit for acquiring basic data required for load prediction through a communication interface; a prediction unit for calling a neural network model and generating a load prediction result of the air conditioning system using the basic data; and a control unit for controlling the operation of the air conditioning system according to the load prediction result.

[0015] Optionally, the prediction unit is also used to: pre-process basic data to remove abnormal data in the basic data, wherein the basic data includes the cooling station water supply temperature, the cooling station return water temperature, the cooling capacity of the cooling station, the outdoor dry bulb temperature, the outdoor relative humidity, meteorological data, the onboard load, the dual-condition load and the ice melting load; input the pre-processed basic data into a neural network model that matches the target engineering project to obtain the load forecast results of the air-conditioning system in the next hour and the load forecast results in the next 24 hours, and use the load forecast results in the next hour to update and optimize the load forecast results in the next 24 hours, wherein the target engineering project is the engineering project where the basic data is located.

[0016] Optionally, the device of the present application may also include: a training unit for obtaining historical operating data of the target engineering project before calling the neural network model and using basic data to generate load prediction results for the air-conditioning system; using the historical operating data to train the original model to obtain a neural network model that matches the target engineering project.

[0017] Optionally, the training unit is also used to: after training the original model using historical operating data to obtain a neural network model that matches the target engineering project, the control method also includes: when the interval between the previous training reaches a specified time length, using the data within the interval time length to train and optimize the neural network model.

[0018] According to another aspect of an embodiment of the present application, a computer-readable storage medium is further provided, which includes a stored program, and the program implements the above method when executed by a processor.

[0019] According to another aspect of an embodiment of the present application, an electronic device is also provided, including: one or more processors; a storage device for storing one or more programs, which enables the one or more processors to implement the above-mentioned method when the one or more programs are executed by the one or more processors.

[0020] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of any of the above-described method embodiments.

[0021] By applying the technical solution of the present application, the basic data required for load prediction is obtained through a communication interface; the neural network model is called to generate a load prediction result for the air-conditioning system using the basic data; and the operation of the air-conditioning system is controlled according to the load prediction result. Since the basic data required for load prediction can be obtained through a standard communication interface, the matched load prediction result can be obtained. The operation of the air-conditioning system is controlled using the load prediction result, which can solve the technical problem of high energy consumption in the operation of the air-conditioning system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a schematic diagram of an optional air-conditioning operating load control system according to an embodiment of the present application;

[0023] Figure 2 is a flow chart of an optional method for controlling air-conditioning operating load according to an embodiment of the present application;

[0024] Figure 3is a functional diagram of an optional air-conditioning operating load prediction software according to an embodiment of the present application;

[0025] Figure 4 is a schematic diagram of an optional load forecasting algorithm framework according to an embodiment of the present application;

[0026] Figure 5 is a schematic diagram of an optional air-conditioning operating load control device according to an embodiment of the present application;

[0027] Figure 6 This is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] To make the objectives, technical solutions, and advantages of this application more clear, this application will be further described in detail below with reference to the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of this application.

[0029] The terms used in the examples of this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms "a," "the," and "the" used in the examples of this application and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0030] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0031] It should be understood that although the terms first, second, third, etc. may be used to describe certain technical features in the embodiments of the present application, these technical features should not be limited to these terms. These terms are only used to distinguish these technical features.

[0032] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0033] It should also be noted that the terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a product or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such product or device. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the product or device comprising the element.

[0034] Example 1

[0035] According to one aspect of the embodiments of the present application, an embodiment of a control system for air conditioning operation load is provided, such as Figure 1 As shown, the system includes:

[0036] Computer device 11 has a communication interface for obtaining basic data. A neural network model runs on the computer device. The neural network model is used to generate a load forecast result of the air-conditioning system using the basic data, wherein the basic data is the data required for load forecasting.

[0037] Optionally, the communication interface uses the Modbus TCP / IP communication protocol to obtain basic data from the air conditioning group control or third-party software; the basic data includes the cooling station supply water temperature, the cooling station return water temperature, the cooling capacity of the cooling station, the outdoor dry bulb temperature, the outdoor relative humidity, meteorological data, onboard load, dual-condition load and ice melting load.

[0038] The above neural network model is an LSTM neural network model. The LSTM neural network model is used to generate the load forecast results of the air-conditioning system in the next hour and the load forecast results in the next 24 hours using basic data, and use the load forecast results in the next hour to update and optimize the load forecast results in the next 24 hours.

[0039] The computer device is installed with load forecasting software for calling a neural network model, and the load forecasting software has at least one of the following functions: a new creation function, which is used to create a new project and configure the project name, geographical location, prediction data source, training data source, data training cycle and network address for the new project; a delete function, which is used to delete the project; a setting function, which is used to modify the project name, geographical location, prediction data source, training data source, data training cycle and network address of the project; a browse function, which is used to visualize the selected project, and the display content includes 24 hours of actual load data, load forecast results for the next 24 hours, ice melting load, dual-condition load and airborne load; a project management function, which is used to enter the new creation function, the delete function, the setting function and the browse function; a user management function, which is used to classify users and manage the permissions of each type of user; and a personal management function, which is used for users to modify their own user information.

[0040] The air conditioning group control 12 (also known as the group control system) is connected to a computer and is used to control the operation of the air conditioning system according to load forecast results. The air conditioning group control connects all controllable devices to a central control center via a network and uses various sensors placed within the space, air conditioning equipment, and ducts to monitor various operating data.

[0041] The air conditioning operation load prediction software of the present application communicates in real time with the group control system or other third-party software through the standard Modbus TCP / IP communication protocol, reads the hourly load data, dry-bulb temperature, relative humidity, and holiday data of the engineering project, uses the LSTM neural network model to build a load prediction algorithm, trains the data, and predicts the air conditioning load for the next 24 hours. It then updates and optimizes it with more accurate prediction results for the next hour. The prediction algorithm can be modified according to the data characteristics of different engineering projects to meet the load prediction requirements of various complex engineering projects. It can help guide the optimization of the control strategy of the ice storage air conditioning system to achieve the goal of reducing system energy consumption and improving economic benefits.

[0042] Through the above embodiment, the basic data required for load prediction is obtained through the communication interface; the neural network model is called to generate the load prediction result of the air-conditioning system using the basic data; the operation of the air-conditioning system is controlled according to the load prediction result. Since the basic data required for load prediction can be obtained through the standard communication interface, the matched load prediction result can be obtained, and the operation of the air-conditioning system is controlled using the load prediction result, which can solve the technical problem of high energy consumption in the operation of the air-conditioning system.

[0043] Example 2

[0044] According to one aspect of the embodiments of the present application, an embodiment of a method for controlling an air-conditioning operating load is provided, such as Figure 2 As shown, the method includes the following steps:

[0045] Step S1: Obtain basic data required for load forecasting through a communication interface.

[0046] Step S2: calling the neural network model and using the basic data to generate the load prediction result of the air-conditioning system.

[0047] In the above embodiment, the historical operation data of the target engineering project can be acquired in advance; the original model is trained using the historical operation data to obtain a neural network model that matches the target engineering project.

[0048] Later, when performing load forecasting, the basic data can be preprocessed to remove abnormal data in the basic data, where the basic data includes the cooling station water supply temperature, cooling station return water temperature, cooling station cooling capacity, outdoor dry bulb temperature, outdoor relative humidity, meteorological data, onboard load, dual-condition load and ice melting load; the preprocessed basic data is input into the neural network model matching the target project to obtain the load forecast results of the air-conditioning system in the next hour and the load forecast results in the next 24 hours, and the load forecast results in the next hour are used to update and optimize the load forecast results in the next 24 hours, where the target project is the project where the basic data is located.

[0049] Step S3: Control the operation of the air-conditioning system according to the load forecast result.

[0050] After using historical operating data to train the original model and obtain a neural network model that matches the target engineering project, in order to improve the model's prediction accuracy, when the interval between the previous training reaches a specified length of time (such as half a year), the neural network model can be trained and optimized using the data within the interval.

[0051] Through the above steps, the basic data required for load prediction is obtained through the communication interface; the neural network model is called to generate the load prediction result of the air-conditioning system using the basic data; the operation of the air-conditioning system is controlled according to the load prediction result. Since the basic data required for load prediction can be obtained through the standard communication interface, the matched load prediction result can be obtained. The operation of the air-conditioning system is controlled using the load prediction result, which can solve the technical problem of high energy consumption in the operation of the air-conditioning system.

[0052] Example 3

[0053] The air conditioning load prediction software of this application communicates with the group control system in real time via the standard Modbus TCP / IP communication protocol. It reads the hourly time, load data, dry-bulb temperature, relative humidity, and holiday data of the project, builds a load prediction algorithm using the LSTM neural network model, trains the data, and predicts the air conditioning load for the next 24 hours. It then updates and optimizes the prediction results using the more accurate prediction results for the next hour. The prediction algorithm can be modified based on the data characteristics of different projects to meet the load prediction requirements of various complex projects. It can help guide the optimization of the control strategy of the ice storage air conditioning system to achieve the goal of reducing system energy consumption and improving economic benefits. As an optional embodiment, the technical solution of this application is further described in detail below in conjunction with the specific implementation method:

[0054] The overall architecture of load forecasting software is as follows: Figure 1 :

[0055] 1) The load forecasting software uses the standard Modbus TCP / IP protocol to enable real-time communication with the group control system or other third-party software. It reads real-time load data and other characteristic data for each project in the group control system or other third-party software and saves it to the software's local database. A load forecasting algorithm based on the LSTM neural network model selects data from the corresponding project in the database and trains the algorithm. After training, the algorithm then performs load forecasts for the next 24 hours and, more accurately, the next hour. The next-hour forecast is used to update and optimize the 24-hour forecast, outputting the next 24-hour load forecast and feeding it back to the group control system.

[0056] 2) The protocol content includes the cooling station supply water temperature, cooling station return water temperature, cooling station cooling capacity, outdoor dry-bulb temperature, outdoor relative humidity, meteorological data 1 (including calm, light breeze, windy, strong wind, typhoon, etc., converted to 0, 1, 2, 3, ... 35, int type data), meteorological data 2 (including sunny, overcast, cloudy, light rain, heavy rain, light snow, heavy snow, etc., converted to 0, 1, 2, 3, ... 35, int type data), onboard load, dual-condition load, and ice melting load.

[0057] Load forecasting software features such as Figure 3 As shown:

[0058] 1) Project management function: Project management is divided into four functions: create, set, browse and delete;

[0059] 2) New function: Create a new project. The new project information includes: project name, city and province, forecast data source (the forecast requires the real-time operation data of the project, so you need to select the corresponding project in the group control system here), training data source (data training requires the historical operation data of the project. You can select the corresponding project in the group control system to read historical data, or choose to customize and import files with fixed data formats), data training cycle (the data training cycle set for this software is the past one year, the past two years, and the past three years), project introduction, IP address (the IP address is required for this software to communicate with the group control system or other third-party software). After the new project information is set, data training can be carried out, and load forecasting will automatically start after data training is completed;

[0060] 3) Setting function: Modify the information of the established project, including the project name, city and province, forecast data source, training data source, data training cycle, project profile, and IP address. After the project information is modified and set up, data training can be carried out, and load forecasting will automatically start after data training is completed;

[0061] 4) Browsing function: Select the project you want to view for visual display, including measured 24-hour data, predicted 24-hour data, ice melting load, dual-condition load, and airborne load;

[0062] 5) Delete function: delete the project;

[0063] 6) User management function: mainly the management function of advanced users over ordinary users. This software currently divides users into advanced users and ordinary users. Advanced users can use all functional permissions of the software, while ordinary users can only browse the visualization display results of engineering projects allowed by advanced users. Advanced users can create, set, and delete the account information of ordinary users, including account number, password, and the scope of projects that can be browsed. Advanced users can set the engineering projects that ordinary users can view. After logging in, ordinary users can only browse the data visualization display of the corresponding engineering projects. The display content includes measured 24-hour data, predicted 24-hour data, ice melting load, dual-condition load, and airborne load. It does not have other functions of engineering management;

[0064] 7) Personal Management: Users can modify their username, password, and security questions. This software is designed and developed as a standalone version. Because users may forget their passwords, a new login method, security question login, has been added. Users are required to set a custom security question upon initial login to facilitate subsequent logins should they forget their password. The personal management function also supports password modification.

[0065] Load forecasting algorithms such as Figure 4 As shown:

[0066] 1) The load forecasting algorithm is based on the LSTM neural network model. The LSTM neural network model is designed to process data with long-term dependencies. It can purposefully transmit and express the content of long-term series while avoiding the loss of historical information. The software produces two forecast results: a 24-hour load forecast and a more accurate one-hour load forecast. The one-hour load forecast is used to update and optimize the 24-hour load forecast. The load forecasting algorithm consists of two parts: data training and forecasting.

[0067] 2) Data training refers to reading the characteristics of the data based on historical operating data using the established algorithm model, and then calculating the error between the predicted value and the actual value. Then, according to the back-propagation algorithm, the error is calculated back, and the output affects each neuron in the input stage. Through repeated cycles, the error is continuously reduced, and the predicted value is closer to the actual value. It is through data training that the neural network algorithm learns the changing relationships and patterns in the data before it can make predictions. Data characteristics refer to the type of data. For example, for air conditioning operating load prediction, the data that needs to be read must include the feature of "air conditioning operating load". Other data that have an impact on load changes or show a certain change pattern with load changes can be used as data features, such as time, dry-bulb temperature, and relative humidity. The change pattern of air conditioning load on weekdays and holidays is different, so holiday data can also be used as data features. The data features that need to be read by the software's load prediction algorithm are hourly time, load data, dry-bulb temperature, relative humidity, and holiday data, which can be modified according to the data characteristics of different engineering projects;

[0068] 3) The prediction is based on real-time operating data, reading the data features, and then performing abnormal data detection and processing. After the processing is completed, the trained LSTM neural network model is used for prediction to obtain the prediction results. Abnormal data detection and processing mainly targets outliers in the data. For example, in actual engineering projects, due to problems with on-site detection instruments, the load data in the real-time operating data is 0, or the relative humidity is greater than 100%, or the dry-bulb temperature at certain moments is suddenly greater than or less than the local normal temperature range for the day. These data caused by measurement errors are called abnormal data and need to be detected by algorithms and processed and corrected before they can be used;

[0069] 4) Data training and prediction are both performed for the same project. Data training is first performed using the project's historical operating data, and then the trained algorithm model and real-time operating data are used to predict future operating data. Therefore, the algorithm model trained with the historical data of Project A and then used to predict with the real-time operating data of Project B will definitely be incorrect. In theory, the longer the data period used for data training, the better. The longer the data period, the smaller the error.

[0070] 5) The load forecast results are updated every hour, outputting the air conditioning operating load for the next 24 hours. The load forecast algorithm automatically conducts data training and updates the optimization algorithm model every six months based on the latest operating data.

[0071] The present application provides a technical solution for air conditioning operation load prediction, which can solve the following technical problems: 1) The existing ice storage air conditioning system adopts a traditional control strategy, the system energy efficiency is low, the operation is not economical, and the optimization of the ice storage and melting control strategy is not timely and in place; 2) The modeling work and building impact parameter acquisition of the existing energy consumption simulation software are difficult, which is not conducive to use by non-professional staff.

[0072] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0073] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0074] Example 4

[0075] According to another aspect of the embodiment of the present application, there is also provided an embodiment of an air conditioning operation load control device for implementing the above-mentioned air conditioning operation load control method, such as Figure 5 As shown, the device may include:

[0076] An acquisition unit 51 is configured to acquire basic data required for load forecasting through a communication interface;

[0077] The prediction unit 53 is used to call the neural network model and generate the load prediction result of the air conditioning system using the basic data;

[0078] The control unit 55 is used to control the operation of the air-conditioning system according to the load prediction result.

[0079] Through the above modules, the basic data required for load forecasting is obtained through the communication interface; the neural network model is called to generate the load forecast results of the air-conditioning system using the basic data; the operation of the air-conditioning system is controlled according to the load forecast results. Since the basic data required for load forecasting can be obtained through the standard communication interface, the matched load forecast results can be obtained. The operation of the air-conditioning system is controlled using the load forecast results, which can solve the technical problem of high energy consumption in the operation of the air-conditioning system.

[0080] Optionally, the prediction unit is also used to: pre-process basic data to remove abnormal data in the basic data, wherein the basic data includes the cooling station water supply temperature, the cooling station return water temperature, the cooling capacity of the cooling station, the outdoor dry bulb temperature, the outdoor relative humidity, meteorological data, the onboard load, the dual-condition load and the ice melting load; input the pre-processed basic data into a neural network model that matches the target engineering project to obtain the load forecast results of the air-conditioning system in the next hour and the load forecast results in the next 24 hours, and use the load forecast results in the next hour to update and optimize the load forecast results in the next 24 hours, wherein the target engineering project is the engineering project where the basic data is located.

[0081] Optionally, the device of the present application may also include: a training unit for obtaining historical operating data of the target engineering project before calling the neural network model and using basic data to generate load prediction results for the air-conditioning system; using the historical operating data to train the original model to obtain a neural network model that matches the target engineering project.

[0082] Optionally, the training unit is also used to: after training the original model using historical operating data to obtain a neural network model that matches the target engineering project, the control method also includes: when the interval between the previous training reaches a specified time length, using the data within the interval time length to train and optimize the neural network model.

[0083] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules, as part of the device, can run in a corresponding hardware environment and can be implemented by software or hardware, wherein the hardware environment includes a network environment.

[0084] Example 5

[0085] This embodiment provides an electronic device (such as a refrigerator, an air purifier, or other household appliances), the electronic device comprising: a processor 201, a memory 202, and a transmission device 203, such as Figure 6 As shown, the terminal may further include input and output devices 204; wherein:

[0086] The memory 202 can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application. The processor 201 executes various functional applications and data processing by running the software programs and modules stored in the memory 202, that is, implementing the above-mentioned method. The memory 202 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 202 may further include a memory remotely located relative to the processor 201, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0087] The transmission device 203 is used to receive or send data via a network, and can also be used for data transmission between a processor and a memory. Specific examples of the network may include wired networks and wireless networks. In one embodiment, the transmission device 203 includes a network interface controller (NIC), which can be connected to other network devices and a router via a network cable to communicate with the Internet or a local area network. In one embodiment, the transmission device 203 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0088] Specifically, the memory 202 is used to store application programs.

[0089] The processor 201 may call the application program stored in the memory 202 through the transmission device 203 to execute the steps in the above embodiment.

[0090] Example 6

[0091] The embodiments of the present application provide a software for executing the technical solutions described in the above embodiments and preferred implementation modes.

[0092] An embodiment of the present application provides a non-volatile computer storage medium, which stores computer-executable instructions. The computer-executable instructions can execute the method for editing content in a document in any of the above method embodiments.

[0093] The above-mentioned software is stored in the above-mentioned storage medium, which includes but is not limited to: a CD, a floppy disk, a hard disk, a rewritable memory, etc.

[0094] The above-mentioned product can execute the method provided in the embodiment of this application, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not fully described in this embodiment, please refer to the method provided in the embodiment of this application.

[0095] The electronic devices of the embodiments of the present application exist in various forms, including but not limited to:

[0096] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and are primarily designed to provide voice and data communications. These terminals include smartphones (e.g., iPhones), multimedia phones, feature phones, and low-end phones.

[0097] (2) Ultra-mobile personal computer devices: These devices fall under the category of personal computers, have computing and processing capabilities, and generally also have mobile Internet access. These terminals include PDAs, MIDs, and UMPCs, such as the iPad.

[0098] (3) Portable entertainment devices: These devices can display and play multimedia content. These devices include audio and video players (such as iPods), handheld game consoles, e-books, smart toys, and portable car navigation devices.

[0099] (4) Server: A device that provides computing services. The server consists of a processor, hard disk, memory, device bus, etc. The server is similar to a general computer architecture, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability.

[0100] (5) Other electronic devices with data interaction functions, such as televisions, large-screen cars, etc.

[0101] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0102] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A control system for air conditioning operation load, characterized in that: The control system includes: A computer device having a communication interface for acquiring basic data, a neural network model running on the computer device, the neural network model being configured to generate a load forecast result for the air conditioning system using the basic data, wherein the basic data is data required for load forecasting; an air conditioning group control, the air conditioning group control being connected to the computer device and being used to control the operation of the air conditioning system according to the load forecast result; The basic data include cooling station water supply temperature, cooling station return water temperature, cooling station cooling capacity, outdoor dry bulb temperature, outdoor relative humidity, meteorological data, onboard load, dual-mode load and ice melting load; The neural network model is used to use the basic data to generate a load forecast result of the air-conditioning system at a first preset time in the future and a load forecast result of a second preset time in the future, and to use the load forecast result of the first preset time in the future to update and optimize the load forecast result of the second preset time in the future, where the first preset time is less than the second preset time.

2. The control system according to claim 1, characterized in that: The communication interface uses the Modbus TCP / IP communication protocol to obtain the basic data from the air conditioning group control or third-party software.

3. The control system according to claim 1, characterized in that: The neural network model is an LSTM neural network model, which is used to use the basic data to generate a load forecast result for the air-conditioning system in the next hour and a load forecast result for the next 24 hours, and use the load forecast result for the next hour to update and optimize the load forecast result for the next 24 hours.

4. The control system according to claim 1, characterized in that: The computer device is installed with load forecasting software for calling the neural network model, and the load forecasting software has at least one of the following functions: Create a new project, which is used to create a new project and configure the project name, geographical location, prediction data source, training data source, data training cycle and network address for the new project; A delete function, which is used to delete a project; A settings function, which is used to modify the project name, geographical location, prediction data source, training data source, data training cycle, and network address of the project; A browsing function is used to visually display the selected project, including 24-hour load measurement data, load forecast results for the next 24 hours, ice melting load, dual-operation load, and airborne load; Project management function, the project management function is used to enter the create function, the delete function, the setting function and the browse function; User management function, which is used to classify users and manage the permissions of each type of user; The personal management function is used by users to modify their own user information.

5. A method for controlling air conditioning operating load, characterized in that: The control method includes: Obtain basic data required for load forecasting through the communication interface; Invoking a neural network model to generate a load forecast result for the air conditioning system using the basic data; controlling the operation of the air conditioning system according to the load forecast result; The basic data include cooling station water supply temperature, cooling station return water temperature, cooling station cooling capacity, outdoor dry bulb temperature, outdoor relative humidity, meteorological data, onboard load, dual-mode load and ice melting load; The neural network model is used to use the basic data to generate a load forecast result of the air-conditioning system at a first preset time in the future and a load forecast result of a second preset time in the future, and to use the load forecast result of the first preset time in the future to update and optimize the load forecast result of the second preset time in the future, where the first preset time is less than the second preset time.

6. The control method according to claim 5, characterized in that: The neural network model is called to generate a load forecast result of the air conditioning system using the basic data, including: Preprocessing the basic data to remove abnormal data in the basic data, wherein the basic data includes cooling station supply water temperature, cooling station return water temperature, cooling station cooling capacity, outdoor dry bulb temperature, outdoor relative humidity, meteorological data, onboard load, dual-mode load, and ice melting load; The preprocessed basic data is input into the neural network model that matches the target project to obtain the load forecast results of the air-conditioning system in the next hour and the load forecast results in the next 24 hours, and the load forecast results in the next hour are used to update and optimize the load forecast results in the next 24 hours, wherein the target project is the project where the basic data is located.

7. The control method according to claim 6, characterized in that: Before calling the neural network model and generating a load prediction result of the air-conditioning system using the basic data, the control method further includes: Obtaining historical operation data of the target engineering project; The original model is trained using the historical operation data to obtain the neural network model that matches the target engineering project.

8. The control method according to claim 7, characterized in that: After the original model is trained using the historical operation data to obtain the neural network model that matches the target engineering project, the control method further includes: When the interval between the training and the previous training reaches a specified duration, the neural network model is trained and optimized using the data within the interval.

9. A control device for air conditioning operation load, characterized in that: The control device comprises: An acquisition unit, used for acquiring basic data required for load forecasting through a communication interface; A prediction unit, configured to call a neural network model and generate a load prediction result for the air-conditioning system using the basic data; a control unit, configured to control the operation of the air-conditioning system according to the load prediction result; The basic data include cooling station water supply temperature, cooling station return water temperature, cooling station cooling capacity, outdoor dry bulb temperature, outdoor relative humidity, meteorological data, onboard load, dual-mode load and ice melting load; The prediction unit is used to use the basic data to generate a load prediction result of the air-conditioning system at a first preset time in the future and a load prediction result at a second preset time in the future, and use the load prediction result of the first preset time in the future to update and optimize the load prediction result of the second preset time in the future, where the first preset time is less than the second preset time.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 5 to 8 is implemented.

11. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, causes the one or more processors to implement the method according to any one of claims 5 to 8.

Images