A comprehensive energy-saving air conditioning control system and control method thereof

Abstract

The present invention discloses an all-round energy-saving air-conditioning control system and a control method thereof, which relates to the field of home automation technology, including monitoring sensor data and uploading it to a central control device; using a machine learning algorithm to analyze the sensor data and identify the user's behavior pattern; predicting the user's future usage needs based on the user's behavior pattern and weather forecast data; dynamically adjusting the operating state of the air conditioner according to the predicted user behavior; selecting the best energy-saving mode according to the current environmental conditions and the user's behavior pattern; integrating the air conditioner with the energy management system to optimize the overall energy utilization efficiency. The present invention realizes a comprehensive analysis and prediction of user behavior, as well as a dynamic adjustment of the air conditioner operating state based on the prediction results, improves energy utilization efficiency, reduces unnecessary energy waste, and not only improves the intelligence level of the system, but also significantly improves the user's experience and satisfaction.

Description

Technical Field

[0001] The present invention relates to the technical field of home automation, and in particular to an all-round energy-saving air-conditioning control system and a control method thereof. Background Art

[0002] As an indispensable part of modern buildings, air conditioning systems account for a large proportion of the total energy consumption of buildings. Therefore, how to achieve efficient and energy-saving control of air conditioning systems through intelligent means has become a hot research topic in recent years. Traditional air conditioning control systems often focus on temperature control of a single room or local area, lacking comprehensive consideration of user behavior habits and external environmental factors, resulting in widespread energy waste.

[0003] However, existing air conditioning control systems still have some shortcomings. On the one hand, most systems only focus on temperature regulation under current environmental conditions, and fail to fully consider the user's historical usage habits and personalized needs, resulting in the inability to accurately predict changes in user needs in some cases, thereby reducing the energy-saving effect of the system. On the other hand, although some systems attempt to improve energy efficiency by analyzing user behavior patterns, these systems often do not fully integrate external environmental information, resulting in low prediction accuracy and difficulty in accurately predicting user behavior change trends. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an all-round energy-saving air-conditioning control system and a control method thereof to solve the problem that the existing air-conditioning control system fails to fully consider user behavior patterns and external environmental changes, resulting in low energy utilization efficiency and poor energy-saving effect.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides an all-round energy-saving air conditioning control method, which includes:

[0008] Monitor sensor data and upload it to the central control device;

[0009] Use machine learning algorithms to analyze sensor data and identify user behavior patterns;

[0010] Predict users’ future usage needs based on user behavior patterns and weather forecast data;

[0011] Dynamically adjust the operating status of the air conditioner based on predicted user behavior;

[0012] Select the best energy-saving mode based on current environmental conditions and user behavior patterns.

[0013] As a preferred solution of the all-round energy-saving air conditioning control method of the present invention, wherein: monitoring sensor data and uploading it to the central control center includes the following steps:

[0014] Activate all sensors and monitoring devices and set basic parameters of sensors;

[0015] Collect sensor data on indoor temperature, humidity, carbon dioxide concentration, and whether there are people moving around;

[0016] The collected data are processed to remove outliers, fill in missing data and perform smoothing;

[0017] The processed data are stored in a database of the central control device.

[0018] As a preferred solution of the all-round energy-saving air conditioning control method of the present invention, wherein: using a machine learning algorithm to analyze sensor data and identify user behavior patterns includes the following steps:

[0019] Divide a day into several time periods, and calculate the probability of the air conditioner being turned on in each time period based on the user's air conditioner usage habits;

[0020] Clustering algorithms are used to identify user behavior patterns in different time periods to obtain clusters of users with similar behavior patterns.

[0021] As a preferred solution of the all-round energy-saving air conditioning control method of the present invention, wherein: based on the user behavior pattern and weather forecast data, predicting the user's future usage needs includes the following steps:

[0022] Get weather forecast data for outdoor temperature and humidity;

[0023] Based on weather forecast data, calculate the impact factor of weather on users' tendency to turn on air conditioning;

[0024] Combining weather influencing factors and user behavior pattern clusters, predict the user's future tendency to turn on the air conditioner. The expression is:

[0025]

[0026] in, is the predicted air conditioning opening tendency at time t, W f is the weather impact factor, P on (t) is the probability of the air conditioner being turned on at time t, C is the user behavior pattern cluster, c is a behavior pattern in the cluster, x is a data point, T x is the outdoor temperature at data point x, H x is the outdoor humidity in data point x, |c| is the number of data points in cluster c, Tref is the reference temperature, H ref is the reference humidity, and σ is the standard deviation of the impact of the deviation between the adjusted outdoor temperature and humidity and the reference temperature and humidity on the user's tendency to turn on the air conditioner.

[0027] As a preferred solution of the all-round energy-saving air conditioning control method of the present invention, wherein: dynamically adjusting the operating state of the air conditioning according to the predicted user behavior includes the following steps:

[0028] Calculate the estimated time of user arrival based on the predicted user's tendency to turn on the air conditioner;

[0029] Based on the user's estimated arrival time, the indoor temperature the user wants to reach, and the current indoor temperature, calculate the time point when the air conditioner needs to be adjusted in advance;

[0030] Based on the predicted air conditioning turning-on tendency, the current indoor temperature, the indoor temperature that the user wants to achieve, and the current outdoor temperature, the dynamic adjustment strategy of the air conditioner is calculated. The expression is:

[0031]

[0032] Among them, S(t) is the dynamic adjustment strategy of the air conditioner, T tar is the indoor temperature that the user wants to achieve, T cur is the current indoor temperature, t a is the estimated arrival time of the user, t is the current time, and P max is the maximum opening tendency of the air conditioner, α is the coefficient of the outdoor temperature on the indoor temperature, T out is the current outdoor temperature;

[0033] Adjust the operating status of the air conditioner according to the dynamic adjustment strategy.

[0034] As a preferred solution of the all-round energy-saving air conditioning control method of the present invention, wherein: selecting the best energy-saving mode according to the current environmental conditions and user behavior patterns includes the following steps:

[0035] Evaluate current environmental conditions based on current indoor temperature, humidity, carbon dioxide concentration, and occupant activity status;

[0036] Select the best energy-saving mode based on the results of environmental condition assessment and user behavior pattern clusters;

[0037] For the selected energy-saving mode, set the corresponding operating parameters;

[0038] Implement energy-saving mode according to the setting parameters of energy-saving mode;

[0039] During the implementation of the energy-saving mode, the working mode and parameters of the air conditioner are dynamically adjusted according to changes in the indoor environment.

[0040] In a second aspect, the present invention provides an all-round energy-saving air-conditioning control system, comprising:

[0041] Data collection and upload module, monitors sensor data and uploads it to the central control device;

[0042] User behavior pattern recognition module, which uses machine learning algorithms to analyze sensor data and identify user behavior patterns;

[0043] Usage demand forecasting module, based on user behavior patterns and weather forecast data, predicts users’ future usage needs;

[0044] Dynamic operation status adjustment module, dynamically adjusts the operation status of the air conditioner according to the predicted user behavior;

[0045] The energy-saving mode selection and implementation module selects the best energy-saving mode according to the current environmental conditions and user behavior patterns.

[0046] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the all-round energy-saving air-conditioning control method as described in the first aspect of the present invention is implemented.

[0047] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the all-round energy-saving air conditioning control method as described in the first aspect of the present invention is implemented.

[0048] The beneficial effects of the present invention are as follows: by monitoring sensor data and uploading it to the central control center, comprehensive monitoring of the indoor environment and collection of high-quality data are achieved; by analyzing sensor data through machine learning algorithms, user behavior patterns are identified, and the accuracy of user behavior prediction is improved; by combining user behavior patterns and weather forecast data, users' future usage needs are predicted, and the accuracy of prediction is improved; according to the predicted user behavior, the operating status of the air conditioner is dynamically adjusted, and the refined management of the operating status of the air conditioner is achieved, which improves the response speed and energy-saving effect of the system; by integrating the air conditioner with the energy management system, the overall energy utilization efficiency is optimized, cross-system collaborative control is achieved, and the energy-saving effect of the system is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0050] Figure 1 This is a flow chart of the all-round energy-saving air conditioning control method in Example 1.

[0051] Figure 2 This is a module diagram of the all-round energy-saving air conditioning control method in Example 1. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0055] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides an all-round energy-saving air conditioning control method, comprising the following steps:

[0056] S1, monitoring sensor data and uploading it to the central control center includes the following steps:

[0057] Activate all sensors (temperature, humidity, carbon dioxide concentration sensors) and monitoring equipment (infrared detection terminal) and monitoring equipment, and set the basic parameters of the sensors, including setting the temperature sensor collection interval (for example, collect data every 15 minutes), temperature range (generally set to 0℃ to 40℃ for indoor use), accuracy (usually ±0.5℃), set the humidity sensor collection interval to be the same as the temperature sensor, humidity range (generally set to 0% to 100%), accuracy (usually ±3%RH), set the carbon dioxide sensor collection interval, CO2 concentration range (generally set to 400ppm to 100ppm for indoor environment)

[0058] 2000ppm) with an accuracy of ±50ppm; collect sensor data on indoor temperature, humidity, carbon dioxide concentration, and whether there is human activity; remove outliers, fill in missing data, and smooth the collected data; store the processed data in the database of the central control device.

[0059] Furthermore, by collecting indoor temperature and humidity data, the system can understand in real time whether the indoor environment meets the standard of human comfort. Based on the real-time temperature and humidity data, the system can dynamically adjust the operating status of the air conditioner to ensure that the indoor environment is always kept within a comfortable range. For example, when the indoor temperature is too high, the system can start the air conditioner in advance to cool down; when the humidity is high, the dehumidification function can be enabled; by monitoring the carbon dioxide concentration, the system can determine whether the room needs ventilation. When the CO2 concentration exceeds a certain threshold, the system can automatically start the fresh air system or adjust the air conditioning mode to introduce fresh air. Maintaining good indoor air quality is not only beneficial to the health of personnel, but also can improve work efficiency. At the same time, timely ventilation can also avoid unnecessary air conditioning energy consumption; by detecting the activity status of personnel, the system can automatically shut down or reduce the air conditioning power when no one is in the state to avoid resource waste. When there are people, the air conditioner operation mode can be adjusted according to the number of people and activity intensity. By dynamically adjusting the air conditioner operation status, it can not only ensure the indoor environment is comfortable when there are people, but also save energy to the greatest extent and improve energy utilization efficiency.

[0060] S2. Using machine learning algorithms to analyze sensor data and identify user behavior patterns includes the following steps:

[0061] A day is divided into several time periods. Based on the user's air conditioning usage habits, the probability of the air conditioner being turned on in each time period is calculated. A clustering algorithm is used to identify the user's behavior patterns in different time periods to obtain clusters of users with similar behavior patterns.

[0062] Going further, a day is divided into 8 time periods, each of which is 3 hours, as follows:

[0063] 00:00-03:00: Late night, most users are resting.

[0064] 03:00-06:00: In the early morning hours, some early risers may start activities.

[0065] 06:00-09:00: Morning period, when most users start to get up and perform morning activities.

[0066] 09:00-12:00: Morning period, peak time for work or study.

[0067] 12:00-15:00: Noon period, lunch time and lunch break.

[0068] 15:00-18:00: Afternoon period, peak time for work or study.

[0069] 18:00-21:00: In the evening, after get off work or school, there are more family activities.

[0070] 21:00-24:00: Evening period, leisure time, gradually entering a resting state.

[0071] Furthermore, the expression of the air conditioner on probability is:

[0072]

[0073] Among them, P on (t) is the probability of the air conditioner being turned on at time t, D is the date dataset, d is the date, IR(d,t)=1 is the activity status of the person at date d and time t, |D| is the number of dates in the dataset, P on The value range of (t) is [0, 1]. A value close to 1 indicates that the user is likely to turn on the air conditioner at this moment, and a value close to 0 indicates that the possibility is small. {IR(d,t)＝1} It is an indicator function, which takes the value 1 when IR(d,t)=1 is equal to 1, otherwise it is 0.

[0074] The expression of user behavior pattern cluster is:

[0075]

[0076] Where C is the user behavior pattern cluster, c is one of the clusters, x is the multiple data points x contained in each cluster c, and each data point x records the sensor data (indoor temperature, humidity, carbon dioxide concentration) at a specific time point and whether the air conditioner is turned on. c is the center point of cluster c, It means to find C that minimizes the objective function.

[0077] Use a clustering algorithm to cluster the data points and group data points with similar characteristics into the same cluster. Each cluster represents a user behavior pattern. For example, one cluster contains a large number of data points where the air conditioner is turned on in the morning, which means that users tend to turn on the air conditioner in the morning. Another cluster may contain data points where the air conditioner is turned off in the evening, indicating that users tend to turn off the air conditioner in the evening. The goal is to minimize the differences within the cluster.

[0078] S3, based on the user behavior pattern and weather forecast data, predicting the user's future usage needs includes the following steps:

[0079] Get weather forecast data of outdoor temperature and humidity; based on the weather forecast data, calculate the weather impact factor on the user's tendency to turn on the air conditioner; combine the weather impact factor and the user behavior pattern cluster to predict the user's future tendency to turn on the air conditioner. The expression is:

[0080]

[0081] in, is the predicted probability of air conditioning on at time t, W f is the weather impact factor, P on (t) is the probability of the air conditioner being turned on at time t, C is the user behavior pattern cluster, c is a behavior pattern in the cluster, x is a data point, T x is the outdoor temperature at data point x, H x is the outdoor humidity in data point x, |c| is the number of data points in cluster c, T ref is the reference temperature, H ref is the reference humidity, and σ is the standard deviation of the impact of the deviation between the adjusted outdoor temperature and humidity and the reference temperature and humidity on the user's tendency to turn on the air conditioner.

[0082] Furthermore, the expression of the influencing factor of weather on the user's tendency to turn on the air conditioner is:

[0083]

[0084] Where T is the outdoor temperature and H is the outdoor humidity.

[0085] Furthermore, the impact of weather factors on users' tendency to turn on air conditioning is as follows:

[0086] The reference temperature and reference humidity are usually set to the temperature and humidity values ​​that users feel comfortable with. When the outdoor temperature and humidity deviate from the reference values, the user's tendency to turn on the air conditioner will increase. The calculation of the weather impact factor adopts the form of an exponential function, which means that when the outdoor temperature and humidity are far away from the reference value, the value of the weather impact factor will decrease rapidly, and vice versa. This exponential decay characteristic ensures that when outdoor conditions become extreme, the user's tendency to turn on the air conditioner will increase significantly.

[0087] S4. Dynamically adjusting the operating state of the air conditioner according to the predicted user behavior includes the following steps:

[0088] Based on the predicted user's tendency to turn on the air conditioner, the estimated time of the user's arrival is calculated; based on the user's estimated arrival time, the indoor temperature the user wants to reach, and the current indoor temperature, the time point when the air conditioner needs to be adjusted in advance is calculated; based on the predicted tendency to turn on the air conditioner, the current indoor temperature, the indoor temperature the user wants to reach, and the current outdoor temperature, the dynamic adjustment strategy of the air conditioner is calculated, and the expression is:

[0089]

[0090] Among them, S(t) is the dynamic adjustment strategy of the air conditioner, T tar is the indoor temperature that the user wants to achieve, T cur is the current indoor temperature, t a is the estimated arrival time of the user, t is the current time, and P max is the maximum opening tendency of the air conditioner, α is the coefficient of the outdoor temperature on the indoor temperature, T out is the current outdoor temperature.

[0091] When the current indoor temperature and the target temperature have the same sign (i.e., both are higher or lower than the target temperature) and the current outdoor temperature also has the same sign as the target temperature, the air conditioner does not need to be adjusted, so S(t) = 0;

[0092] For example, if T cur >T tar And T out >T ta , indicating that both the indoor and outdoor temperatures are higher than the target temperature, and the air conditioner does not need to be turned on.

[0093] or T cur <T tar And T out <T tar , indicating that both the indoor and outdoor temperatures are lower than the target temperature, and the air conditioner does not need to be turned on.

[0094] If the above conditions are not met, that is, the indoor temperature and outdoor temperature have different signs in relation to the target temperature, the air conditioner needs to be adjusted.

[0095] Furthermore, the estimated time of user arrival is calculated as follows:

[0096] Based on the user's behavior pattern cluster and the predicted tendency to turn on the air conditioner, select the time period with a higher tendency to turn on the air conditioner as the key time period; for each key time period, analyze the changing trend of the tendency to turn on the air conditioner; find the time period with the highest tendency to turn on the air conditioner; set a threshold for the tendency to turn on the air conditioner; if the tendency to turn on the air conditioner reaches or exceeds the threshold within a certain time period, it is considered that the user may arrive in this time period; if the tendency to turn on the air conditioner reaches or exceeds the threshold in multiple time periods, select the time period with the highest tendency to turn on the air conditioner as the estimated arrival time.

[0097] Furthermore, the expression for the time point at which the air conditioner needs to be adjusted in advance is:

[0098]

[0099] Among them, T startThe time point to start adjusting the air conditioner, R c is the cooling rate of the air conditioner, Δt is the time interval, which means the time required for the air conditioning system to actually start changing the indoor temperature from receiving the command, which is a preset fixed value.

[0100] S5. According to the current environmental conditions and user behavior patterns, selecting the best energy-saving mode includes the following steps:

[0101] Based on the current indoor temperature, humidity, carbon dioxide concentration and human activity status, the current environmental conditions are evaluated; based on the results of the environmental condition evaluation and the user behavior pattern cluster, the best energy-saving mode is selected; for the selected energy-saving mode, the corresponding operating parameters are set, such as cooling or heating power, fan speed, etc.; according to the set parameters of the energy-saving mode, the energy-saving mode is implemented; during the implementation of the energy-saving mode, the working mode and parameters of the air conditioner are dynamically adjusted according to the changes in the indoor environment (such as temperature rise, increase in the number of people, etc.).

[0102] Going further, the specific operations for evaluating the current environmental conditions are as follows:

[0103] The current indoor temperature, relative humidity and carbon dioxide concentration are measured by sensors to monitor whether there are human activities in the room; specific evaluation standards are formulated for indoor temperature, humidity, carbon dioxide concentration and human activity status based on human comfort standards and safety standards; a scoring system is set for each environmental parameter, and a score is given based on the deviation between the actual measured value and the standard value; the scores of various parameters are combined to obtain an overall environmental condition score; if the combined score is low, it indicates that the current environmental conditions are not good, and the air conditioning system may need to be adjusted to improve the indoor environment; if the score is high, it indicates that the current environmental conditions are good, and the energy-saving mode may be selected to reduce energy consumption.

[0104] Furthermore, the expression for selecting the best energy-saving mode is:

[0105]

[0106] Among them, M is the energy-saving mode, η is the air conditioning cooling rate adjustment coefficient, R cooling is the cooling rate of the air conditioner, β is the humidity adjustment coefficient, H tar is the indoor humidity that the user wants to achieve, H cur is the current indoor humidity, γ is the user behavior adjustment coefficient, P avg It is the average opening tendency in the user behavior pattern cluster.

[0107] The expression for adjusting the operating parameters of the air conditioner in energy-saving mode is:

[0108]

[0109] Where P is the cooling or heating power, P max is the maximum cooling or heating power of the air conditioner, P night It is the cooling or heating power in night mode.

[0110] S6. Integrate air conditioning and energy management systems to optimize overall energy efficiency, including the following steps:

[0111] The central control device establishes a communication interface between the air-conditioning system and the energy management system of the entire building; obtains the energy consumption of the entire building through the building's energy management system, including but not limited to the use of lighting, hot water supply and other equipment; predicts the load of the power grid based on historical data and real-time data; adjusts the operating status of the air-conditioning system based on the power grid load prediction results; dynamically adjusts the operating status of the air-conditioning system according to changes in the building's internal environment and power grid load prediction results to maximize overall energy efficiency.

[0112] Furthermore, the expression for the predicted grid load is:

[0113]

[0114] Where L(t) is the grid load at time t, N is the number of non-air-conditioning equipment, i is the index variable of non-air-conditioning equipment, and λ i is the load factor of the i-th non-air-conditioning equipment, E i (t) is the power consumption of the i-th non-air-conditioning equipment at time t, M is the number of air-conditioning equipment, θ is the load factor of the air-conditioning equipment, E j (t) is the power consumption of the jth air-conditioning equipment at time t.

[0115] Based on the grid load forecast results, the expression for adjusting the operating state of the air-conditioning system is:

[0116]

[0117] Among them, P adj P(t) is the power of the air conditioning system after adjustment at time t, P(t) is the power of the air conditioning system without adjustment at time t, L avg is the average load of the power grid, L max The maximum load of the power grid.

[0118] This embodiment also provides an all-round energy-saving air conditioning control system, including:

[0119] Data collection and upload module: monitors sensor data and uploads it to the central control device; user behavior pattern recognition module: uses machine learning algorithms to analyze sensor data and identify user behavior patterns; usage demand prediction module: predicts future user usage needs based on user behavior patterns and weather forecast data; dynamic operation status adjustment module: dynamically adjusts the operation status of the air conditioner according to predicted user behavior; energy-saving mode selection and implementation module: selects the best energy-saving mode according to current environmental conditions and user behavior patterns.

[0120] This embodiment also provides a computer device suitable for the case of an all-round energy-saving air-conditioning control method, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the all-round energy-saving air-conditioning control method proposed in the above embodiment.

[0121] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0122] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing all-round energy-saving air conditioning control as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0123] In summary, the present invention realizes comprehensive monitoring of the indoor environment and collection of high-quality data by monitoring sensor data and uploading it to the central control center; analyzes sensor data through machine learning algorithms, identifies user behavior patterns, and improves the accuracy of user behavior prediction; predicts user future usage needs by combining user behavior patterns and weather forecast data, and improves the accuracy of prediction; dynamically adjusts the operating status of the air conditioner according to the predicted user behavior, realizes refined management of the operating status of the air conditioner, and improves the response speed and energy-saving effect of the system; and optimizes the overall energy utilization efficiency by integrating the air conditioner with the energy management system, realizes cross-system collaborative control, and improves the energy-saving effect of the system.

[0124] Example 2

[0125] Referring to Table 1, which is the second embodiment of the present invention, in order to further verify the technical solution of the present invention, experimental simulation data of an all-round energy-saving air conditioning control method is provided.

[0126] First, activate all sensors and monitoring equipment, and set the basic parameters of the sensors, such as setting the sampling frequency to once every 5 minutes; collect sensor data on indoor temperature, humidity, carbon dioxide concentration, and whether there is human activity; pre-process the collected data, including removing outliers, filling missing data, and smoothing; store the processed data in the database of the central control device.

[0127] The day is divided into four time periods (morning, morning, afternoon, and evening), and the probability of the air conditioner being turned on in each time period is calculated; a clustering algorithm is used to identify the user's behavior patterns in different time periods to obtain clusters of users with similar behavior patterns.

[0128] Obtain weather forecast data of outdoor temperature and humidity; based on the weather forecast data, calculate the impact factor of weather on the user's tendency to turn on the air conditioner; combine the weather impact factor and the user behavior pattern cluster to predict the user's future tendency to turn on the air conditioner.

[0129] Based on the predicted user's tendency to turn on the air conditioner, calculate the estimated time of the user's arrival; based on the user's estimated arrival time, the indoor temperature the user wants to achieve, and the current indoor temperature, calculate the time point when the air conditioner needs to be adjusted in advance; based on the predicted tendency to turn on the air conditioner, the indoor temperature, the indoor temperature the user wants to achieve, and the current outdoor temperature, calculate the dynamic adjustment strategy of the air conditioner.

[0130] Based on the current indoor temperature, humidity, carbon dioxide concentration and personnel activity status, the current environmental conditions are evaluated; according to the results of the environmental condition evaluation and the user behavior pattern cluster, the best energy-saving mode is selected.

[0131] The central control device establishes a communication interface between the air-conditioning system and the energy management system of the entire building; obtains the energy consumption of the entire building through the building's energy management system; predicts the load of the power grid based on historical data and real-time data; and adjusts the operating status of the air-conditioning system based on the power grid load prediction results.

[0132] The details are shown in Table 1:

[0133] Table 1 Experimental record table

[0134] Parameter name First floor Second floor Third floor Fourth floor Fifth floor Overall average Indoor temperature 26.5 26.3 26.2 26.4 26.6 26.4 Indoor humidity 55.0％ 54.5％ 54.0％ 54.8％ 55.2％ 54.7％ CO2 concentration 700ppm 695ppm 690ppm 698ppm 702ppm 697ppm Personnel Activities 15 10 12 14 18 13.8 Open probability 0.7 0.65 0.6 0.68 0.75 0.67 Dynamic Adjustment 0.65 0.6 0.55 0.62 0.7 0.62 Energy saving mode 80％ 75％ 70％ 77％ 82％ 76.6％ Energy saving 12％ 11％ 10％ 11.5％ 13％ 11.4％

[0135] From the above analysis, it can be seen that this all-round energy-saving air conditioning control method can not only improve user comfort, but also greatly improve energy efficiency. Compared with existing technologies, it has significant innovation and advantages. For example, the dynamic adjustment strategy enables the air conditioner to start in time before the user arrives, avoiding unnecessary energy waste; and the selection of energy-saving mode can be flexibly adjusted according to actual conditions, further reducing energy consumption.

[0136] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A comprehensive energy-saving air conditioning control method, characterized in that: include, Monitor sensor data and upload it to the central control device; Use machine learning algorithms to analyze sensor data and identify user behavior patterns; Predict users’ future usage needs based on user behavior patterns and weather forecast data; Dynamically adjust the operating status of the air conditioner based on predicted user behavior; Select the best energy-saving mode based on current environmental conditions and user behavior patterns: Based on user behavior patterns and weather forecast data, predicting users' future usage needs includes the following steps: Get weather forecast data for outdoor temperature and humidity; Based on weather forecast data, calculate the impact factor of weather on users' tendency to turn on air conditioning; Combining weather influencing factors and user behavior pattern clusters, predict the user's future tendency to turn on the air conditioner. The expression is: ； in, For at the moment Predicted probability of air conditioning on, is the weather influencing factor, For at the moment The probability of the air conditioner being turned on, is the user behavior pattern cluster, is a behavior pattern in the cluster, is the data point, For data points The outdoor temperature in For data points The outdoor humidity in Cluster The number of data points in is the reference temperature, is the reference humidity, The standard deviation of the effect of the deviation between the outdoor temperature and humidity and the reference temperature and humidity on the user's tendency to turn on the air conditioner; Monitoring sensor data and uploading it to the central control center includes the following steps: Activate all sensors and monitoring devices and set basic parameters of sensors; Collect sensor data on indoor temperature, humidity, carbon dioxide concentration, and whether there are people moving around; The collected data are processed to remove outliers, fill in missing data and perform smoothing; storing the processed data in a database of a central control device; Using machine learning algorithms to analyze sensor data and identify user behavior patterns includes the following steps: Divide a day into several time periods, and calculate the probability of the air conditioner being turned on in each time period based on the user's air conditioner usage habits; Use clustering algorithms to identify user behavior patterns in different time periods and obtain clusters of users with similar behavior patterns; According to the predicted user behavior, dynamically adjusting the operating state of the air conditioner includes the following steps: Calculate the estimated time of user arrival based on the predicted user's tendency to turn on the air conditioner; Based on the user's estimated arrival time, the indoor temperature the user wants to reach, and the current indoor temperature, calculate the time point when the air conditioner needs to be adjusted in advance; Based on the predicted air conditioning turning-on tendency, the current indoor temperature, the indoor temperature that the user wants to achieve, and the current outdoor temperature, the dynamic adjustment strategy of the air conditioner is calculated. The expression is: ； in, Dynamic adjustment strategy for air conditioning, is the indoor temperature that the user wants to achieve. is the current indoor temperature, The estimated time of arrival of the user. is the current time, The maximum opening tendency of the air conditioner. is the coefficient of the outdoor temperature on the indoor temperature, is the current outdoor temperature.

2. The all-round energy-saving air conditioning control method according to claim 1, characterized in that: According to the current environmental conditions and user behavior patterns, selecting the best energy-saving mode includes the following steps: Evaluate current environmental conditions based on current indoor temperature, humidity, carbon dioxide concentration, and occupant activity status; Select the best energy-saving mode based on the results of environmental condition assessment and user behavior pattern clusters; For the selected energy-saving mode, set the corresponding operating parameters; The energy saving mode is implemented according to the setting parameters of the energy saving mode.

3. An all-round energy-saving air conditioning control system, based on the all-round energy-saving air conditioning control method according to any one of claims 1 and 2, characterized in that: include, Data collection and upload module, monitors sensor data and uploads it to the central control device; User behavior pattern recognition module, which uses machine learning algorithms to analyze sensor data and identify user behavior patterns; Usage demand prediction module, based on user behavior patterns and weather forecast data, predicts users' future usage needs; Dynamic operation status adjustment module, dynamically adjusts the operation status of the air conditioner according to the predicted user behavior; The energy-saving mode selection and implementation module selects the best energy-saving mode according to the current environmental conditions and user behavior patterns.

4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the all-round energy-saving air conditioning control method described in any one of claims 1 and 2 are implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the all-round energy-saving air conditioning control method described in any one of claims 1 and 2 are implemented.

Images