Air conditioner energy-saving control method and system based on smart cloud analysis

Abstract

The invention provides an air conditioner energy-saving control method and system based on smart cloud analysis, and relates to the technical field of air conditioner energy-saving control, and the air conditioner energy-saving control system comprises a sensing layer, a network layer, a cloud platform layer, an application layer and an execution layer; and the cloud platform layer processes and analyzes the data by adopting a big data analysis tool and an artificial intelligence algorithm. Multi-dimensional data such as indoor and outdoor temperature, humidity, personnel activity conditions and illumination intensity are collected through the sensing layer, sequence data are analyzed through the recurrent neural network, historical information can be effectively stored, future energy consumption can be predicted, in addition, the system carries out big data analysis and artificial intelligence decision through the cloud platform, dynamic optimization control is achieved, and the energy consumption is reduced. Meanwhile, compared with the prior art, the energy-saving effect is improved, the flexibility and adaptability of the system are improved through the intelligent cloud platform, and the dual requirements of a user for comfort and energy saving can be better met.

Description

Technical Field

[0001] The present invention relates to the technical field of air-conditioning energy-saving control, and specifically to an air-conditioning energy-saving control method and system based on smart cloud analysis. Background Art

[0002] With the continuous increase in global energy demand and the growing awareness of environmental protection, air-conditioning energy-saving control technology has become a research hotspot. Traditional air-conditioning control systems usually rely on simple temperature sensors and preset operating modes, which makes it difficult to achieve refined energy consumption management and environmental comfort optimization. In recent years, with the rapid development of the Internet of Things, big data and artificial intelligence technologies, air-conditioning energy-saving control systems based on intelligent cloud analysis have gradually become a research direction.

[0003] The applicant found the application number 202411004724.3 through search, and its name is "An air conditioning control method and system for improving energy-saving effects through energy consumption prediction." The patent proposes an air conditioning control method for improving energy-saving effects through energy consumption prediction. It constructs an energy consumption prediction model through a multi-layer perception neural network algorithm, and combines real-time environmental parameters and historical weather data to predict energy consumption. Although this method can achieve certain energy-saving effects, its model construction is relatively complex and lacks comprehensive analysis of multi-dimensional data such as personnel activities and light intensity.

[0004] The applicant found the application number 202411606987.1 through search, and its name is communication control device, method and air conditioner for air conditioning controller. The patent proposes a communication control device and method for air conditioning controller, which solves the problems of high communication bus occupancy and slow response speed in the traditional single-host polling method. However, the patent mainly focuses on communication control, and involves less energy-saving control and intelligent decision-making functions of the air conditioner.

[0005] Considering the shortcomings of existing technologies, 1. Limited energy-saving effects: Traditional air-conditioning control systems cannot be dynamically adjusted according to real-time environmental parameters and historical energy consumption data, resulting in poor energy-saving effects; 2. Lack of intelligence: Existing technologies mostly rely on manual settings and cannot automatically adapt to environmental changes and user needs; 3. Insufficient data processing capabilities: Traditional systems lack the ability to process and analyze big data and cannot achieve accurate energy consumption prediction and optimization. Summary of the invention

[0006] 1. Technical issues to be solved

[0007] In view of the shortcomings of the prior art, the present invention provides an air-conditioning energy-saving control method and system based on intelligent cloud analysis, which solves the problems that traditional air-conditioning control systems cannot be dynamically adjusted according to real-time environmental parameters and historical energy consumption data, resulting in poor energy-saving effects; the prior art mostly relies on manual settings and cannot automatically adapt to environmental changes and user needs; and the traditional system lacks the ability to process and analyze big data and cannot achieve accurate energy consumption prediction and optimization.

[0008] (II) Technical solution

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: an air conditioning energy-saving control system based on smart cloud analysis, including a perception layer, a network layer, a cloud platform layer, an application layer and an execution layer;

[0010] The cloud platform layer includes a data storage and management module, a data analysis and decision-making module, and a remote monitoring and management module. The data analysis and decision-making module uses big data analysis tools and artificial intelligence algorithms to process and analyze data;

[0011] The artificial intelligence algorithm mainly uses a recurrent neural network for calculation. The recurrent neural network consists of an input layer, a hidden layer and an output layer. The neurons in the hidden layer not only receive the input data of the current time step, but also receive the output of the hidden layer of the previous time step. This cyclic connection enables the recurrent neural network to save historical information in the sequence data.

[0012] Furthermore, the perception layer is composed of various sensors, which are mainly responsible for real-time monitoring of indoor and outdoor environmental parameters and the operating status of air-conditioning equipment, thereby providing data support for the control system.

[0013] Furthermore, the network layer mainly realizes data transmission and communication functions, and can transmit the data collected by the perception layer to the cloud, and can also transmit the control instructions from the cloud to the controller of the air-conditioning equipment.

[0014] Furthermore, the data storage and management module needs to have strong storage capabilities so that it can store a large amount of historical data and real-time data, and can classify, organize and back up the data, thereby facilitating subsequent query and analysis.

[0015] Furthermore, the remote monitoring and management module mainly provides users with a remote monitoring interface, so that users can view the operating status of the air-conditioning system anytime and anywhere through mobile phones and computers, thereby performing remote control and parameter adjustment.

[0016] Furthermore, the execution layer includes a controller and an air-conditioning actuator, and the actuator includes a compressor control mechanism, a damper control mechanism, a throttling device control mechanism and a temperature and humidity adjustment actuator.

[0017] Furthermore, when the recurrent neural network realizes intelligent regulation and control of the air conditioner, it is first necessary to collect and preprocess the data, then build and train the model, then evaluate and optimize the trained model, and finally use the model to realize intelligent regulation and control of the air conditioner.

[0018] Furthermore, the recurrent neural network performs intelligent energy-saving control of the air conditioner by first accurately predicting the indoor temperature and outdoor environment, and then adjusting the air conditioner in advance, then monitoring the operating status of the equipment and dynamically sensing the indoor environment, and then achieving reasonable allocation and utilization of energy, and then comprehensively considering multiple goals such as energy saving and comfort to formulate the optimal control strategy. At the same time, the control strategy can be continuously updated and optimized based on the adaptive learning ability of the recurrent neural network.

[0019] An air conditioning energy-saving control method based on intelligent cloud analysis includes the following steps:

[0020] Step 1: Data collection, real-time collection of outdoor data and air conditioning operating parameters, such as real-time collection of indoor and outdoor temperature, humidity, human activity and light intensity, as well as the compressor frequency, wind speed, and cooling and heating power of the air conditioner;

[0021] Step 2: Data transmission: The data collected by the sensor is transmitted to the smart cloud, such as through Wi-Fi, ZigBee and Bluetooth, to ensure the stability and real-time performance of data transmission, so that the cloud can obtain the latest information in a timely manner;

[0022] Step 3: Data analysis, through the establishment of models for predictive analysis and finally formulate corresponding strategies;

[0023] Step 4: Instruction issuance and execution: the instruction is sent to the controller of the air-conditioning equipment through the network, and then the operating status of the air-conditioning is controlled and adjusted;

[0024] Step 5: Effect feedback and optimization, compare the actual operation status with the expected operation status and make optimization adjustments based on the results.

[0025] Furthermore, the model established in step three is to establish an air conditioning energy consumption model and an environmental comfort model based on historical data and real-time data, and analyze the relationship between energy consumption and environmental parameters and air conditioning operation parameters.

[0026] (III) Beneficial effects

[0027] The present invention provides an air conditioning energy-saving control method and system based on intelligent cloud analysis. It has the following beneficial effects:

[0028] In this solution, multi-dimensional data such as indoor and outdoor temperature, humidity, human activity and light intensity are collected through the perception layer, and the recurrent neural network is used to analyze the sequence data, which can effectively save historical information and predict future energy consumption. In addition, the system realizes dynamic optimization control through big data analysis and artificial intelligence decision-making through the cloud platform. At the same time, compared with the existing technology, the present invention not only improves the energy-saving effect, but also improves the flexibility and adaptability of the system through the intelligent cloud platform, which can better meet the user's dual needs for comfort and energy saving. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a schematic diagram of the architecture of an air-conditioning energy-saving control system based on smart cloud analysis proposed by the present invention;

[0030] Figure 2 This is a flow chart of an air conditioning energy-saving control method based on intelligent cloud analysis proposed in the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Example:

[0033] like Figure 1-2 As shown, the embodiment of the present invention provides an air-conditioning energy-saving control system based on intelligent cloud analysis, including a perception layer composed of various sensors, which are mainly responsible for real-time monitoring of indoor and outdoor environmental parameters and the operating status of air-conditioning equipment, and then providing data support for the control system. The effect of collecting data is achieved by deploying various sensors in the air-conditioning use environment, such as temperature sensors, humidity sensors, human activity sensors, light sensors, etc.;

[0034] The network layer mainly realizes the data transmission and communication functions. By adopting wired network or wireless network technology, the data collected by the perception layer can be transmitted to the cloud. At the same time, the control instructions from the cloud can also be transmitted to the controller of the air-conditioning equipment, which can ensure the stability and real-time performance of data transmission so that the cloud can obtain the latest information in time.

[0035] The cloud platform layer includes data storage and management modules, data analysis and decision-making modules, and remote monitoring and management modules. The data analysis and decision-making modules use big data analysis tools and artificial intelligence algorithms to process and analyze data.

[0036] Data storage and management has powerful data storage capabilities, capable of storing large amounts of historical data and real-time data, and classifying, organizing and backing up the data, thereby facilitating subsequent query and analysis;

[0037] Artificial intelligence algorithms mainly use recurrent neural networks for calculations. Recurrent neural networks are composed of input layers, hidden layers, and output layers. The neurons in the hidden layer not only receive the input data of the current time step, but also receive the output of the hidden layer of the previous time step. This cyclic connection enables the recurrent neural network to save historical information in the sequence data.

[0038] At each time step t, the recurrent neural network receives an input vector x t , and combined with the hidden state h of the previous time step t-1 To calculate the hidden state h of the current time step t , whose formula is h t =σ(W xh x t +W hh h t-1 +b h ), where W xh is the weight matrix input to the hidden layer, W hh is the weight matrix from hidden layer to hidden layer, b h is the bias vector of the hidden layer, σ is the activation function (such as tanh function), and then according to the current hidden state h t Calculate the output vector y t , whose formula is y t =W hy h t +b y , where W hy is the weight matrix from the hidden layer to the output layer, b y is the bias vector of the output layer;

[0039] When the recurrent neural network is used to realize intelligent regulation and control of air conditioners, it is necessary to first collect and preprocess the data, then build and train the model, then evaluate and optimize the trained model, and finally use the model to realize intelligent regulation and control of the air conditioner.

[0040] The intelligent energy-saving control of air conditioners by the recurrent neural network first accurately predicts the indoor temperature and outdoor environment, and then adjusts the air conditioner in advance. Then it monitors the operating status of the equipment and dynamically perceives the indoor environment, so as to achieve the reasonable allocation and utilization of energy. Then, it formulates the optimal control strategy by comprehensively considering multiple goals such as energy saving and comfort. At the same time, the control strategy can be continuously updated and optimized based on the adaptive learning ability of the recurrent neural network.

[0041] Build a recurrent neural network (RNN) model for air conditioning energy-saving control. Here we take the long short-term memory network (LSTM) as an example because it can effectively avoid the gradient vanishing problem of traditional RNN when processing sequence data and is more suitable for air conditioning energy-saving control scenarios. The construction process mainly includes the following key steps:

[0042] S1: clarify the problem and prepare data;

[0043] (1) Problem definition: In the air conditioning energy-saving control scenario, our goal may be to predict the air conditioning energy consumption or indoor temperature changes in the future, or to determine the optimal air conditioning operating parameters based on the current environment and historical data. Clarifying the problem helps determine the input and output of the model.

[0044] (2) Data collection: Collect data related to air-conditioning operation and environment, including but not limited to:

[0045] ① Environmental data: indoor and outdoor temperature, humidity, light intensity and wind speed, etc.;

[0046] ② Air conditioning operation data: compressor frequency, fan speed, cooling / heating power and operation mode, etc.;

[0047] ③Other relevant data: such as the number of people indoors, activity intensity, etc.;

[0048] These data can be collected by various sensors and recorded at certain time intervals (such as every minute, every five minutes) to form time series data;

[0049] (3) Data preprocessing:

[0050] ① Data cleaning: remove noise, outliers and missing values ​​in the data. For example, a sensor may fail, resulting in an obviously unreasonable recorded temperature value. These abnormal data need to be removed. Missing values ​​can be filled using interpolation methods (such as linear interpolation and spline interpolation).

[0051] ② Data normalization: Map data of different ranges to the same interval, usually [0, 1] or [-1, 1]. Common normalization methods include minimum-maximum normalization and Z-score normalization. Taking minimum-maximum normalization as an example, the formula is:

[0052] Where x is the original data, x min and x max are the minimum and maximum values ​​of the data, respectively, n is the normalized data;

[0053] ③Data division: Divide the preprocessed data into training set, validation set and test set. Generally speaking, the training set accounts for about 70%-80% for learning model parameters; the validation set accounts for about 10%-15% for adjusting the model's hyperparameters; the test set accounts for about 10%-15% for evaluating the final performance of the model;

[0054] S2: Choose a deep learning framework: Common deep learning frameworks include TensorFlow, PyTorch, etc. Here we take PyTorch as an example. It has a simple API and dynamic graph mechanism, which is convenient for model construction and debugging. First, you need to install PyTorch. You can choose the appropriate version according to your needs:

[0055] bash

[0056] pip install torch torchvision;

[0057] S3: Building an LSTM model: In PyTorch, you can build an LSTM model by defining a class that inherits from torch.nn.Module. The following is a simple example code:

[0058]

[0059]

[0060]

[0061] In the above code:

[0062] The __init__ method is used to initialize each layer of the model, including the LSTM layer and the fully connected layer. input_size represents the feature dimension of the input data, hidden_size represents the number of neurons in the LSTM hidden layer, num_layers represents the number of LSTM layers, and output_size represents the output dimension of the model.

[0063] The forward method defines the forward propagation process of the model. First, the hidden state and cell state are initialized, then the input data is passed to the LSTM layer, the output of the last time step is taken, and finally the final output is obtained through the fully connected layer;

[0064] S4: Define loss function and optimizer;

[0065] ① Loss function: For regression problems (such as predicting air conditioning energy consumption, temperature, etc.), the mean square error (MSE) is often used as the loss function. In PyTorch, nn.MSELoss() can be used to define it:

[0066] Python

[0067] criterion = nn.MSELoss()

[0068] ②Optimizer: Select a suitable optimizer to update the parameters of the model. Common optimizers include stochastic gradient descent (SGD), Adam, etc. Here we use the Adam optimizer:

[0069] Python

[0070] optimizer=torch.optim.Adam(model.parameters(),lr=0.001)

[0071] Where lr is the learning rate and needs to be adjusted according to actual conditions;

[0072] S5: Model training;

[0073] Here is an example of a simple training loop:

[0074]

[0075]

[0076] During the training process, the input data is passed into the model for forward propagation and loss calculation, and then backpropagation and parameter update are performed. The loss value is printed every certain number of rounds to observe the training status of the model.

[0077] S6: Model evaluation;

[0078] Use the test set data to evaluate the trained model and calculate the evaluation indicators (such as MSE, MAE, etc.):

[0079]

[0080]

[0081] S7: Model tuning: If the evaluation results of the model are not ideal, you can try the following methods to tune it:

[0082] ① Adjust hyperparameters: such as the number of hidden layer neurons, the number of LSTM layers, the learning rate, and the number of training rounds. You can use grid search or random search to find the optimal hyperparameter combination;

[0083] ② Increase the amount of data: collect more training data or perform data enhancement (such as translating and scaling time series data) to improve the generalization ability of the model;

[0084] ③ Improve the model structure: try adding more hidden layers, adjusting the structure of the fully connected layer, or using different activation functions, etc.

[0085] The data storage and management module needs to have strong storage capacity to store a large amount of historical data and real-time data, and can also classify, organize and back up the data to facilitate subsequent query and analysis;

[0086] The remote monitoring and management module mainly provides users with a remote monitoring interface, allowing users to view the operating status of the air conditioning system anytime and anywhere through mobile phones and computers, so as to perform remote control and parameter adjustment;

[0087] The application layer mainly develops corresponding application programs and functional modules according to different user needs and application scenarios, such as smart home applications for home users, which can control air conditioners through mobile phone apps; energy management systems for corporate users, which can centrally manage multiple air conditioners and conduct energy consumption statistics and analysis;

[0088] The execution layer includes the controller and the air conditioner's actuators, which include the compressor control mechanism, the damper control mechanism, the throttling device control mechanism and the temperature and humidity adjustment actuator;

[0089] An air conditioning energy-saving control method based on intelligent cloud analysis includes the following steps:

[0090] Step 1: Data collection, real-time collection of outdoor data and air conditioning operating parameters, such as real-time collection of indoor and outdoor temperature, humidity, human activity and light intensity, as well as the compressor frequency, wind speed, and cooling and heating power of the air conditioner;

[0091] Step 2: Data transmission: The data collected by the sensor is transmitted to the smart cloud, such as through Wi-Fi, ZigBee and Bluetooth, to ensure the stability and real-time performance of data transmission, so that the cloud can obtain the latest information in a timely manner;

[0092] Step 3: Data analysis, predictive analysis is carried out by building a model and finally corresponding strategies are formulated. The model is built based on historical data and real-time data to build air conditioning energy consumption model and environmental comfort model, and the relationship between energy consumption and environmental parameters and air conditioning operation parameters is analyzed;

[0093] Step 4: Instruction issuance and execution: the instruction is sent to the controller of the air-conditioning equipment through the network, and then the operating status of the air-conditioning is controlled and adjusted;

[0094] Step 5: Effect feedback and optimization, compare the actual operation status with the expected operation status and make optimization adjustments based on the results.

[0095] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An air conditioning energy-saving control system based on intelligent cloud analysis, characterized in that: It includes perception layer, network layer, cloud platform layer, application layer and execution layer; The cloud platform layer includes a data storage and management module, a data analysis and decision-making module, and a remote monitoring and management module. The data analysis and decision-making module uses big data analysis tools and artificial intelligence algorithms to process and analyze data; The artificial intelligence algorithm mainly uses a recurrent neural network for calculation. The recurrent neural network consists of an input layer, a hidden layer and an output layer. The neurons in the hidden layer not only receive the input data of the current time step, but also receive the output of the hidden layer of the previous time step. This cyclic connection enables the recurrent neural network to save historical information in the sequence data.

2. The air conditioning energy-saving control system based on intelligent cloud analysis according to claim 1 is characterized in that: The perception layer is composed of various sensors, which are mainly responsible for real-time monitoring of indoor and outdoor environmental parameters and the operating status of air-conditioning equipment, thereby providing data support for the control system.

3. The air conditioning energy-saving control system based on intelligent cloud analysis according to claim 1 is characterized in that: The network layer mainly realizes the data transmission and communication functions, and can transmit the data collected by the perception layer to the cloud, and can also transmit the control instructions from the cloud to the controller of the air-conditioning equipment.

4. The air conditioning energy-saving control system based on intelligent cloud analysis according to claim 1 is characterized in that: The data storage and management module needs to have strong storage capabilities so that it can store a large amount of historical data and real-time data, and can classify, organize and back up the data to facilitate subsequent query and analysis.

5. The air conditioning energy-saving control system based on intelligent cloud analysis according to claim 1 is characterized in that: The remote monitoring and management module mainly provides users with a remote monitoring interface, allowing users to view the operating status of the air-conditioning system anytime and anywhere through mobile phones and computers, thereby performing remote control and parameter adjustment.

6. The air conditioning energy-saving control system based on intelligent cloud analysis according to claim 1 is characterized in that: The execution layer includes a controller and an air conditioner execution mechanism, and the execution mechanism includes a compressor control mechanism, a damper control mechanism, a throttling device control mechanism and a temperature and humidity adjustment execution mechanism.

7. The air conditioning energy-saving control system based on intelligent cloud analysis according to claim 1 is characterized in that: When the recurrent neural network realizes intelligent regulation and control of the air conditioner, it is first necessary to collect and preprocess the data, then build and train the model, then evaluate and optimize the trained model, and finally use the model to realize intelligent regulation and control of the air conditioner.

8. The air conditioning energy-saving control system based on intelligent cloud analysis according to claim 1 is characterized in that: The recurrent neural network performs intelligent energy-saving control of the air conditioner by first accurately predicting the indoor temperature and outdoor environment, thereby realizing advance adjustment of the air conditioner, then monitoring the operating status of the equipment and dynamically sensing the indoor environment, thereby realizing reasonable allocation and utilization of energy, and then formulating the optimal control strategy by comprehensively considering multiple goals such as energy saving and comfort. At the same time, the control strategy can be continuously updated and optimized based on the adaptive learning ability of the recurrent neural network.

9. An air conditioning energy-saving control method based on intelligent cloud analysis, characterized in that: The following steps are involved: Step 1: Data collection, real-time collection of outdoor data and air conditioning operating parameters, such as real-time collection of indoor and outdoor temperature, humidity, human activity and light intensity, as well as the compressor frequency, wind speed, and cooling and heating power of the air conditioner; Step 2: Data transmission: The data collected by the sensor is transmitted to the smart cloud, such as through Wi-Fi, ZigBee and Bluetooth, to ensure the stability and real-time performance of data transmission, so that the cloud can obtain the latest information in a timely manner; Step 3: Data analysis, through the establishment of models for predictive analysis and finally formulate corresponding strategies; Step 4: Instruction issuance and execution: the instruction is sent to the controller of the air-conditioning equipment through the network, and then the operating status of the air-conditioning is controlled and adjusted; Step 5: Effect feedback and optimization, compare the actual operation status with the expected operation status and make optimization adjustments based on the results.

10. The air conditioning energy-saving control method based on intelligent cloud analysis according to claim 1, characterized in that: The model established in step three is to establish an air conditioning energy consumption model and an environmental comfort model based on historical data and real-time data, and analyze the relationship between energy consumption and environmental parameters and air conditioning operation parameters.

Images