An intelligent energy-saving control method, device and system for air conditioning based on the Internet of Things

Abstract

The present application relates to the technical field of intelligent air conditioning regulation, and specifically to an intelligent energy-saving control method, device and system for air conditioning based on the Internet of Things, the method comprising: collecting a temperature control sequence of a control area of ​​a central air conditioner; dividing temperature change data pairs according to the numerical change characteristics of the temperature control sequence to obtain indoor temperature change rates; eliminating indoor temperature change rates according to the difference in indoor temperature change rates of all adjacent temperature change data pairs to obtain an indoor temperature change rate sequence; obtaining trend prediction weights of each element according to the local change trend of each element in the indoor temperature change rate sequence, predicting the temperature of the control area of ​​the central air conditioner, and controlling the energy consumption of the central air conditioner. The present application can improve the energy-saving control accuracy of the central air conditioner.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent air conditioning regulation, and specifically to an intelligent energy-saving control method, device and system for air conditioning based on the Internet of Things. Background Art

[0002] Central air conditioners are devices used to adjust indoor temperature, humidity, air flow and air quality, and achieve energy saving through advanced temperature control, timer switch, human body sensing, frequency conversion technology, etc. They can automatically adjust the temperature according to the temperature difference between indoor and outdoor, avoid ineffective operation, and improve energy efficiency through remote control and self-learning functions. Central air conditioners can adjust the operating speed of the compressor according to actual needs, achieve more precise temperature control, reduce unnecessary energy consumption, and achieve green energy saving.

[0003] Traditional intelligent air conditioning adjustment generally uses the EMA algorithm to predict the required cooling load in different areas, and automatically adjusts the operating power of the central air conditioning compressor based on real-time monitoring and prediction data, so as to reduce the energy consumption of the central air conditioning. However, due to the different weather, sunlight, human activities, ventilation, humidity and other environmental factors at different times in the room, the temperature change rate in different unit time is different. When using the EMA algorithm for prediction, the use of a fixed smoothing coefficient cannot capture the changing characteristics of the temperature rate, resulting in inaccurate prediction of indoor temperature data, which reduces the energy-saving control accuracy of the central air conditioning. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide an intelligent energy-saving control method, device and system for air conditioners based on the Internet of Things. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides an intelligent energy-saving control method for air conditioners based on the Internet of Things, the method comprising the following steps:

[0006] Collect the temperature of the control area of ​​the central air conditioner at each sampling time to form a temperature control sequence;

[0007] The temperature change data pairs are divided according to the numerical change characteristics of the temperature control sequence, and the indoor temperature change rate of each temperature change data pair is obtained by combining the time difference between the elements in each temperature change data pair; the indoor temperature change rate is eliminated according to the difference of the indoor temperature change rate of all adjacent temperature change data pairs to obtain the indoor temperature change rate sequence; according to the local change trend of each element in the indoor temperature change rate sequence, the trend prediction weight of each element is obtained;

[0008] According to the time difference between the elements in the temperature change data corresponding to all elements in the indoor temperature change rate sequence and the trend prediction weight, the adjustment smoothing coefficient is obtained; the adjustment smoothing coefficient is substituted into the EMA algorithm, and the temperature of the control area of ​​the central air-conditioning is predicted according to the temperature control sequence to control the energy consumption of the central air-conditioning.

[0009] Furthermore, the indoor temperature change rate of each temperature change data pair includes:

[0010] Perform curve fitting on the temperature control sequence to obtain the temperature control fitting curve; obtain each extreme point on the temperature control fitting curve; combine any two adjacent extreme points into a temperature change data pair; for each temperature change data pair, obtain the indoor temperature change rate of the temperature change data pair according to the temperature difference corresponding to the two extreme points in the temperature change data pair and the time interval between the extreme points.

[0011] Furthermore, the indoor temperature change rate of the temperature change data pair is constructed as follows: the indoor temperature change rate of the temperature change data pair is recorded as CL, Where CL represents the indoor temperature change rate of the temperature change data pair; V and V′ represent the temperatures corresponding to the first and second extreme points in the temperature change data pair, respectively; L and L′ represent the collection time corresponding to the first and second extreme points in the temperature change data pair, respectively.

[0012] Furthermore, the method for obtaining the indoor temperature change rate sequence is:

[0013] Arrange the indoor temperature change rates of all temperature change data pairs in chronological order; record the indoor temperature change rate of any temperature change data pair as target data, and obtain a preset neighborhood window centered on the target data;

[0014] Calculate the means of all elements located on the left side and on the right side of the target data in the neighborhood window respectively, and record them as the first mean and the second mean; calculate the differences between the first mean and the second mean and the target data respectively, and record them as the first difference and the second difference; take the minimum value between the first difference and the second difference as the local temperature difference degree of the target data;

[0015] After eliminating the indoor temperature change rates with local temperature differences greater than a preset threshold, all indoor temperature change rates are arranged in chronological order to obtain an indoor temperature change rate sequence.

[0016] Furthermore, the trend prediction weight of each element is obtained according to the local change trend of each element in the indoor temperature change rate sequence, including:

[0017] The indoor temperature change rate sequence is decomposed by using a time series decomposition algorithm to obtain a trend sequence; a curve fitting is performed on the trend sequence to obtain a trend fitting curve; the derivative of each element in the trend sequence at the corresponding point on the fitting curve is obtained and recorded as the rate change trend of each element;

[0018] Any element in the trend sequence is recorded as the target element; the number of elements in the trend sequence with the same value as the target element is obtained, which is recorded as the number of occurrences of the target element; the trend prediction weight of the target element is obtained according to the number of occurrences and rate change trend of the target element.

[0019] Furthermore, the method for obtaining the trend prediction weight of the target element includes:

[0020] The trend synchronization degree of the target element is obtained according to the number of occurrences and the rate change trend of the target element; the trend synchronization degree is positively correlated with the number of occurrences and negatively correlated with the absolute value of the rate change trend; the normalized value of the trend synchronization degree of the target element is used as the trend prediction weight of the target element.

[0021] Furthermore, the method for obtaining the adjustment smoothing coefficient includes:

[0022] Obtain the time difference between two extreme points in the temperature change data pair corresponding to each element in the indoor temperature change rate sequence; calculate the product of the time difference and the trend prediction weight of each element in the indoor temperature change rate sequence; calculate the normalized value of the sum of the products of all elements in all indoor temperature change rate sequences as the adjustment smoothing coefficient.

[0023] Furthermore, the method for controlling the energy consumption of the central air conditioner comprises:

[0024] The adjusted smoothing coefficient is used as the smoothing coefficient in the EMA algorithm to predict the temperature control sequence and obtain the control area temperature of the central air conditioner at the next moment; according to the difference between the control area temperature of the central air conditioner at the next moment and the preset standard temperature, the energy consumption of the central air conditioner is controlled.

[0025] In a second aspect, an embodiment of the present application provides an intelligent energy-saving control device for air conditioners based on the Internet of Things, and the intelligent energy-saving control device for air conditioners includes:

[0026] The air conditioning data acquisition module is used to collect the temperature of the control area of ​​the central air conditioning at each sampling time to form a temperature control sequence;

[0027] The data feature analysis module is used to divide the temperature change data pairs according to the numerical change characteristics of the temperature control sequence, and obtain the indoor temperature change rate of each temperature change data pair by combining the time difference between the elements in each temperature change data pair; eliminate the indoor temperature change rate according to the difference of the indoor temperature change rate of all adjacent temperature change data pairs to obtain the indoor temperature change rate sequence; according to the local change trend of each element in the indoor temperature change rate sequence, obtain the trend prediction weight of each element;

[0028] The air conditioning data prediction and control module is used to obtain the adjustment smoothing coefficient according to the time difference between the elements in the temperature change data corresponding to all elements in the indoor temperature change rate sequence and the trend prediction weight; the adjustment smoothing coefficient is substituted into the EMA algorithm, and the temperature of the control area of ​​the central air conditioner is predicted according to the temperature control sequence to control the energy consumption of the central air conditioner.

[0029] In a third aspect, an embodiment of the present application further provides an intelligent energy-saving control system for air conditioning based on the Internet of Things, the system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the steps of any one of the above methods when executing the computer program.

[0030] It can be seen from the above embodiments that the air-conditioning intelligent energy-saving control method, device and system based on the Internet of Things provided in the embodiments of the present application have at least the following beneficial effects:

[0031] Aiming at the problem that different light intensities at different times affect the characteristics of temperature change rate, resulting in inaccurate indoor temperature prediction by the EMA algorithm with a fixed smoothing coefficient, the temperature change in the temperature control area of ​​the central air conditioner is affected by light, and the indoor temperature change rate is obtained by the fluctuation of the element values ​​in the temperature control sequence over time, and the degree of influence of light on the indoor temperature is determined; the periodic influence of the intensity of sunlight on the temperature rate monitored by the indoor sensor during the day is further analyzed, the indoor temperature change rate is calculated, and the non-periodic fluctuations caused by environmental factors or human activities are eliminated to improve the trend prediction accuracy of the indoor temperature change rate; further, the trend prediction weight of each element is obtained according to the trend change of the elements in the indoor temperature change rate sequence, so that the trend prediction weight of the element that conforms to the trend change law is greater; finally, the smoothing coefficient in the EMA algorithm is dynamically adjusted according to the trend prediction weight, and the temperature of the control area of ​​the central air conditioner is predicted, so that the EMA algorithm can better adapt to the changing characteristics of the indoor temperature and improve the accuracy of the prediction. According to the prediction results, the intelligent adjustment of the operating power of the compressor is controlled to improve the energy-saving control accuracy of the central air conditioner. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0033] Figure 1 A flowchart of a method for intelligent energy-saving control of air conditioners based on the Internet of Things provided in one embodiment of the present application;

[0034] Figure 2 A schematic diagram of the structure of an intelligent energy-saving control device for air conditioning based on the Internet of Things is provided for one embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to further explain the technical means and effects adopted by this application to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of an intelligent energy-saving control method, device and system for air conditioning based on the Internet of Things proposed in this application, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0036] Unless otherwise specified and limited, terms such as "comprises", "comprising" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such articles or devices. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the article or device including the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items. All technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application.

[0037] The following is a detailed description of a specific solution of an air-conditioning intelligent energy-saving control method, device and system based on the Internet of Things provided by the present application in conjunction with the accompanying drawings.

[0038] See also Figure 1 , which shows a flowchart of a method for intelligent energy-saving control of air conditioners based on the Internet of Things provided by an embodiment of the present application, the method comprising the following steps:

[0039] S1, collects the temperature of the control area of ​​the central air conditioner at each sampling time to form a temperature control sequence.

[0040] A specific implementation scenario of the embodiment of the present application is the intelligent adjustment and control scenario of the central air conditioner. In the intelligent adjustment scenario of the central air conditioner, in order to ensure the comfort of the indoor temperature, the temperature, wind speed and air volume of the central air conditioner are usually adjusted adaptively according to the ambient temperature. Therefore, it is necessary to set a temperature sensor to obtain the temperature of the central air conditioner control area.

[0041] At present, the intelligent regulation of air conditioners generally uses the EMA algorithm to predict the ambient temperature in the future, and automatically adjusts the operating power of the central air conditioner compressor based on the real-time monitoring and predicted temperature data. However, due to the different light intensity at different times in the room, the temperature change rate in different unit time is different, resulting in inaccurate prediction of indoor temperature data, affecting the control accuracy of the central air conditioner. Therefore, it is necessary to analyze the changes in indoor temperature data over a period of time, obtain the law of temperature change rate, and dynamically adjust the operating frequency of the compressor.

[0042] Specifically, for each control area corresponding to the indoor unit of the central air conditioner, the temperature of the control area of ​​the central air conditioner is obtained through a temperature sensor. The historical sensor data of the current time is obtained. The total length of the historical data is 5 minutes, and the sampling frequency is to collect data once every 1 second. The sequence composed of the temperatures of the control area of ​​the central air conditioner at all sampling times is recorded as the temperature control sequence. Due to environmental factors and other factors, the sensor may have data missing during the data collection and transmission process. Since the temperature data exists continuously, there will be no sharp rise or fall of a single data. Therefore, this application adopts the mean interpolation method to complete the missing data of the temperature sequence.

[0043] S2, dividing the temperature change data pairs according to the numerical change characteristics of the temperature control sequence, and combining the time difference between the elements in each temperature change data pair to obtain the indoor temperature change rate of each temperature change data pair.

[0044] The intensity of the temperature change in the temperature control area of ​​the central air conditioner indoor unit is affected by light. The temperature rises faster in areas with stronger light. The greater the value of the cooling load required in the indoor unit temperature control area, the higher the frequency of the central air conditioner compressor should be, so that the temperature in the indoor unit temperature control area remains in a stable range.

[0045] The temperature control intensity of the central air conditioner is affected by light. The main reason is that changes in sunlight will cause the indoor temperature to rise or fall. Therefore, the degree of influence of light on indoor temperature can be determined by the fluctuation of the element values ​​in the temperature control sequence over time.

[0046] Specifically, curve fitting is performed on the temperature control sequence to obtain a temperature control fitting curve; each extreme point on the temperature control fitting curve is obtained; any two adjacent extreme points are combined into a temperature change data pair; for each temperature change data pair, the indoor temperature change rate of the temperature change data pair is obtained according to the temperature difference corresponding to the two extreme points in the temperature change data pair and the time interval between the extreme points;

[0047] The indoor temperature change rate of the temperature change data pair is recorded as CL, Where CL represents the indoor temperature change rate of the temperature change data pair; V and V′ represent the temperatures corresponding to the first and second extreme points in the temperature change data pair, respectively; L and L′ represent the collection time corresponding to the first and second extreme points in the temperature change data pair, respectively.

[0048] It should be noted that the methods for curve fitting of the sequence include least squares method, polynomial fitting, etc., which can be selected by the implementer according to the actual situation, and this application does not impose any restrictions. In this embodiment, the collected temperature control sequence is used as the input of the least squares method to obtain the temperature control fitting curve.

[0049] When sunlight shines directly into a room, the increase in its intensity will significantly increase the indoor temperature. The degree of temperature rise is proportional to the intensity of sunlight. As the temperature gradually rises, the time it takes for the room to reach the temperature threshold set by the central air-conditioning system will be shortened. The larger the value of the indoor temperature change rate calculated, the more frequently the central air-conditioning compressor needs to start to maintain a comfortable indoor environment, resulting in higher energy consumption.

[0050] S3, eliminating the indoor temperature change rates according to the differences in the indoor temperature change rates of all adjacent pairs of temperature change data to obtain an indoor temperature change rate sequence.

[0051] When the intensity of sunlight increases, the temperature rate monitored by the indoor sensor will rise. In this case, the measured temperature rise rate is the real indoor temperature. Due to human activities, the air will flow, which will cause the data measured by the temperature sensor to change to a certain extent, causing the calculated indoor temperature change rate to fluctuate. The temperature change caused by human activities belongs to a local small range of temperature changes. When adjusting and controlling the indoor ambient temperature, it is necessary to exclude the impact of local temperature changes caused by human activities. The state of this part of local temperature change is short-lived, which will cause abnormal fluctuations in the indoor temperature change rate for a short time. Therefore, according to the local differences in the changing trends of the indoor temperature change rate of all continuous temperature change data pairs, the abnormal fluctuation values ​​of the indoor temperature change rate are identified and eliminated.

[0052] First, the indoor temperature change rates of all temperature change data pairs are arranged in chronological order; the indoor temperature change rate of any temperature change data pair is recorded as the target data, and a preset neighborhood window centered on the target data is obtained;

[0053] Calculate the means of all elements located on the left side and on the right side of the target data in the neighborhood window respectively, and record them as the first mean and the second mean;

[0054] It should be noted that the indoor temperature change rate is arranged in chronological order from left to right. The left side of the target data is the data that is collected before the target data; the right side of the target data is the data that is collected after the target data. When there is a lack of elements on the left or right side of the target data, the value of the target data is used to fill it.

[0055] Further, the differences between the first mean, the second mean and the target data are calculated respectively, which are recorded as the first difference and the second difference; the minimum value between the first difference and the second difference is taken as the local temperature difference degree of the target data;

[0056] In this embodiment, the difference between the two variables is to calculate the absolute value of the difference between the two variables; the indoor temperature change rates of all temperature change data pairs are arranged in chronological order to form an indoor temperature change rate sequence, and the local temperature difference degree Fhe of the i-th element in the indoor temperature change rate sequence is i The calculation formula is: i =min(|Cl i -LCl i |,|Cl i -RCl i |), where Fhe i It represents the local temperature difference of the i-th element in the indoor temperature change rate sequence; min() represents the minimum function; Cli represents the i-th element in the indoor temperature change rate sequence; LCli and RCli represent the first mean and second mean in the neighborhood window of the i-th element in the indoor temperature change rate sequence, respectively.

[0057] Furthermore, in order to eliminate the influence of abnormal fluctuations in local temperature differences, data with large local temperature differences are eliminated. Specifically, elements with local temperature differences greater than a preset threshold W are eliminated, and all indoor temperature change rates are arranged in chronological order to obtain an indoor temperature change rate sequence.

[0058] In this embodiment, the mean μ and variance σ of the local temperature difference of all elements in the indoor temperature change rate sequence are calculated, and a threshold value W=μ+2σ is preset.

[0059] When the indoor temperature is in a normal heating state, its heating rate sequence usually shows a steady growth trend. In this case, the data points in the sequence are often not much different from the data of their left and right neighbors. This means that the difference between each data point and the mean of its left and right neighbors is small, so the value of the calculated local temperature difference is small, indicating that the temperature change of the data point is consistent with the surrounding trend, without significant abnormal fluctuations, and the measurement of the heating rate is true and reliable.

[0060] S4, according to the local change trend of each element in the indoor temperature change rate sequence, the trend prediction weight of each element is obtained.

[0061] In the morning of a day, the intensity of sunlight will increase with time, so the rate of indoor temperature rise will become faster and faster per unit time, so the indoor temperature rate will have a certain increasing tendency. On the contrary, in the afternoon of a day, the indoor temperature rate will decrease and have a downward trend. Therefore, the changing characteristics of indoor temperature can be judged by the trend of elements in the indoor temperature change rate sequence.

[0062] Specifically, the time series decomposition algorithm is used to decompose the indoor temperature change rate series to obtain the trend series;

[0063] In this embodiment, the STL decomposition algorithm in the time series decomposition algorithm is used to decompose the indoor temperature change rate series, wherein the specific implementation process of the STL decomposition algorithm is a well-known technology and will not be repeated here.

[0064] The element values ​​in the trend sequence indicate the changing characteristics of the temperature rate. Therefore, the changing trend can be further obtained based on the continuous changes in the element values.

[0065] Perform curve fitting on the trend sequence to obtain a trend fitting curve; obtain the derivative of each element in the trend sequence at the corresponding point on the fitting curve, and record it as the rate change trend of each element;

[0066] The more times the value of the same element appears in the indoor temperature change rate sequence, the more synchronized the indoor temperature change rate of the element is with other elements, that is, the more obvious the temperature change characteristics of the corresponding indoor temperature change rate are; in order to improve the prediction accuracy of the temperature control sequence, the trend prediction weight is calculated in combination with the rate change trend of each element.

[0067] Any element in the trend sequence is recorded as the target element; the number of elements in the trend sequence with the same value as the target element is obtained, which is recorded as the number of occurrences of the target element; according to the number of occurrences and rate change trend of the target element, the trend prediction weight of the target element is obtained;

[0068] The trend synchronization degree of the target element is obtained according to the number of occurrences and the rate change trend of the target element; the trend synchronization degree is positively correlated with the number of occurrences and negatively correlated with the absolute value of the rate change trend; the normalized value of the trend synchronization degree of the target element is used as the trend prediction weight of the target element.

[0069] It should be noted that a positive correlation indicates that there is a same-direction change relationship between the independent variable and the dependent variable, that is, the larger the independent variable is, the larger the dependent variable is; a negative correlation indicates that there is an opposite-direction change relationship between the independent variable and the dependent variable, that is, the smaller the independent variable is, the larger the dependent variable is; the specific manifestations of the positive correlation and the negative correlation are determined by actual applications and are not particularly limited in this application.

[0070] As an embodiment of the present application, the sum of the rate change trend and the preset adjustment factor d=1 is calculated, and the ratio of the number of occurrences of the target element to the sum is used as the trend synchronization degree of the target element;

[0071] As other embodiments of the present application, an exponential function value with the natural constant e as the base and the opposite number of the rate change trend as the exponent can be calculated; the product of the exponential function value and the number of occurrences of the target element is used as the trend synchronization degree of the target element.

[0072] The more times the element value with the same value as the target element appears in the trend sequence, the smaller the absolute value of the rate change trend is, which means that the indoor temperature change is more stable, and the trend prediction weight corresponding to the indoor temperature change rate is greater. When predicting the temperature data, the time span of the temperature change data pair corresponding to the indoor temperature change rate should be considered.

[0073] S5, obtains the adjustment smoothing coefficient according to the time difference between the elements in the temperature change data corresponding to all elements in the indoor temperature change rate sequence and the trend prediction weight; substitutes the adjustment smoothing coefficient into the EMA algorithm, predicts the temperature of the control area of ​​the central air conditioner according to the temperature control sequence, and controls the energy consumption of the central air conditioner.

[0074] When the EMA algorithm predicts the indoor temperature with central air conditioning, the temperature data oscillates repeatedly within a certain range, and the fixed smoothing coefficient is not well adapted to the increase and decrease rate of the indoor temperature. Therefore, it is necessary to adjust the smoothing coefficient according to the trend prediction weight of the indoor temperature change rate to predict the indoor temperature data.

[0075] First, the time interval between two extreme points in the temperature change data pair corresponding to each element in the indoor temperature change rate sequence is obtained; the product of the time difference and the trend prediction weight of each element in the indoor temperature change rate sequence is calculated; and the normalized value of the sum of the products of all elements in all indoor temperature change rate sequences is calculated as the adjustment smoothing coefficient.

[0076] When the temperature control sequence shows obvious periodic characteristics, it usually means that the temperature data oscillates repeatedly in a certain pattern. In this case, the calculated time difference will be relatively large because there are more temperature change points in each cycle. This periodic strengthening leads to an increase in the trend prediction weight, making the calculated adjustment smoothing coefficient larger.

[0077] The adjusted smoothing coefficient is used as the smoothing coefficient of the EMA algorithm to predict the temperature control sequence and obtain the predicted value of the temperature of the control area of ​​the central air conditioner at the next moment. The EMA algorithm is a well-known technology and the specific calculation steps are not repeated here.

[0078] Based on the temperature prediction value at the next moment obtained above, in order to maintain the indoor temperature at the standard temperature of 25°C which is most suitable for the human body, the frequency modulation technology is used to calculate the required cooling capacity according to the predicted temperature value, and the power of the central air conditioner is controlled. Since the calculation process of the cooling capacity is a well-known technology, the specific calculation process will not be repeated.

[0079] See also Figure 2 , Figure 2 1 is a schematic diagram of the structure of an air conditioner intelligent energy-saving control device based on the Internet of Things provided in an embodiment of the present application. In this embodiment, each unit included in the terminal is used to execute each step in an embodiment corresponding to an air conditioner intelligent energy-saving control method based on the Internet of Things. Figure 2 The air-conditioning intelligent energy-saving control device includes: an air-conditioning data acquisition module, a data feature analysis module, and an air-conditioning data prediction control module.

[0080] The air conditioning data acquisition module is used to collect the temperature of the control area of ​​the central air conditioning at each sampling time to form a temperature control sequence;

[0081] The data feature analysis module is used to divide the temperature change data pairs according to the numerical change characteristics of the temperature control sequence, and obtain the indoor temperature change rate of each temperature change data pair by combining the time difference between the elements in each temperature change data pair; eliminate the indoor temperature change rate according to the difference of the indoor temperature change rate of all adjacent temperature change data pairs to obtain the indoor temperature change rate sequence; according to the local change trend of each element in the indoor temperature change rate sequence, obtain the trend prediction weight of each element;

[0082] The air conditioning data prediction and control module is used to obtain the adjustment smoothing coefficient according to the time difference between the elements in the temperature change data corresponding to all elements in the indoor temperature change rate sequence and the trend prediction weight; the adjustment smoothing coefficient is substituted into the EMA algorithm, and the temperature of the control area of ​​the central air conditioner is predicted according to the temperature control sequence to control the energy consumption of the central air conditioner.

[0083] Based on the same inventive concept as the above method, an embodiment of the present application also provides an intelligent energy-saving control system for air conditioning based on the Internet of Things, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-mentioned intelligent energy-saving control methods for air conditioning based on the Internet of Things.

[0084] It is to be understood that the sequence of the embodiments of the present application described above is for description only and does not represent the advantages and disadvantages of the embodiments. The above describes specific embodiments of the present specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0086] The above content is only an implementation method of the present application and is not intended to limit the scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the protection scope of the present application.

Claims

1. An intelligent energy-saving control method for air conditioners based on the Internet of Things, characterized in that: The method comprises the following steps: Collect the temperature of the control area of ​​the central air conditioner at each sampling time to form a temperature control sequence; The temperature change data pairs are divided according to the numerical change characteristics of the temperature control sequence, and the indoor temperature change rate of each temperature change data pair is obtained by combining the time difference between the elements in each temperature change data pair; the indoor temperature change rate is eliminated according to the difference of the indoor temperature change rate of all adjacent temperature change data pairs to obtain the indoor temperature change rate sequence; according to the local change trend of each element in the indoor temperature change rate sequence, the trend prediction weight of each element is obtained; According to the time difference between the elements in the temperature change data corresponding to all elements in the indoor temperature change rate sequence and the trend prediction weight, the adjustment smoothing coefficient is obtained; the adjustment smoothing coefficient is substituted into the EMA algorithm, and the temperature of the control area of ​​the central air-conditioning is predicted according to the temperature control sequence to control the energy consumption of the central air-conditioning.

2. The method for intelligent energy-saving control of air conditioner based on Internet of Things as claimed in claim 1, characterized in that: The indoor temperature change rate of each temperature change data pair includes: Perform curve fitting on the temperature control sequence to obtain the temperature control fitting curve; obtain each extreme point on the temperature control fitting curve; combine any two adjacent extreme points into a temperature change data pair; for each temperature change data pair, obtain the indoor temperature change rate of the temperature change data pair according to the temperature difference corresponding to the two extreme points in the temperature change data pair and the time interval between the extreme points.

3. The method for intelligent energy-saving control of air conditioner based on Internet of Things as claimed in claim 2, characterized in that: The construction process of the indoor temperature change rate of the temperature change data pair is as follows: the indoor temperature change rate of the temperature change data pair is recorded as CL, Where CL represents the indoor temperature change rate of the temperature change data pair; V and V′ represent the temperatures corresponding to the first and second extreme points in the temperature change data pair, respectively; L and L′ represent the collection time corresponding to the first and second extreme points in the temperature change data pair, respectively.

4. The method for intelligent energy-saving control of air conditioner based on Internet of Things as claimed in claim 1, characterized in that: The method for obtaining the indoor temperature change rate sequence is: Arrange the indoor temperature change rates of all temperature change data pairs in chronological order; record the indoor temperature change rate of any temperature change data pair as target data, and obtain a preset neighborhood window centered on the target data; The means of all elements located on the left side and on the right side of the target data in the preset neighborhood window are calculated respectively, and recorded as the first mean and the second mean; the differences between the first mean and the second mean and the target data are calculated respectively, and recorded as the first difference and the second difference; the minimum value between the first difference and the second difference is taken as the local temperature difference degree of the target data; After eliminating the indoor temperature change rates with local temperature differences greater than a preset threshold, all indoor temperature change rates are arranged in chronological order to obtain an indoor temperature change rate sequence.

5. The intelligent energy-saving control method for air conditioner based on Internet of Things as claimed in claim 1, characterized in that: The trend prediction weight of each element is obtained according to the local change trend of each element in the indoor temperature change rate sequence, including: The indoor temperature change rate sequence is decomposed by using a time series decomposition algorithm to obtain a trend sequence; a curve fitting is performed on the trend sequence to obtain a trend fitting curve; the derivative of each element in the trend sequence at the corresponding point on the fitting curve is obtained and recorded as the rate change trend of each element; Any element in the trend sequence is recorded as the target element; the number of elements in the trend sequence with the same value as the target element is obtained, which is recorded as the number of occurrences of the target element; the trend prediction weight of the target element is obtained according to the number of occurrences and rate change trend of the target element.

6. The method for intelligent energy-saving control of air conditioner based on Internet of Things as claimed in claim 5, characterized in that: The method for obtaining the trend prediction weight of the target element includes: The trend synchronization degree of the target element is obtained according to the number of occurrences and the rate change trend of the target element; the trend synchronization degree is positively correlated with the number of occurrences and negatively correlated with the absolute value of the rate change trend; the normalized value of the trend synchronization degree of the target element is used as the trend prediction weight of the target element.

7. The method for intelligent energy-saving control of air conditioner based on Internet of Things as claimed in claim 1, characterized in that: The method for obtaining the adjustment smoothing coefficient includes: Obtain the time difference between two extreme points in the temperature change data pair corresponding to each element in the indoor temperature change rate sequence; calculate the product of the time difference and the trend prediction weight of each element in the indoor temperature change rate sequence; calculate the normalized value of the sum of the products of all elements in all indoor temperature change rate sequences as the adjustment smoothing coefficient.

8. The method for intelligent energy-saving control of air conditioner based on Internet of Things as claimed in claim 1, characterized in that: The method for controlling the energy consumption of a central air conditioner comprises: The adjusted smoothing coefficient is used as the smoothing coefficient in the EMA algorithm to predict the temperature control sequence and obtain the control area temperature of the central air conditioner at the next moment; according to the difference between the control area temperature of the central air conditioner at the next moment and the preset standard temperature, the energy consumption of the central air conditioner is controlled.

9. An intelligent energy-saving control device for air conditioners based on the Internet of Things, characterized in that: The air conditioner intelligent energy-saving control device comprises: The air conditioning data acquisition module is used to collect the temperature of the control area of ​​the central air conditioning at each sampling time to form a temperature control sequence; The data feature analysis module is used to divide the temperature change data pairs according to the numerical change characteristics of the temperature control sequence, and obtain the indoor temperature change rate of each temperature change data pair by combining the time difference between the elements in each temperature change data pair; eliminate the indoor temperature change rate according to the difference of the indoor temperature change rate of all adjacent temperature change data pairs to obtain the indoor temperature change rate sequence; according to the local change trend of each element in the indoor temperature change rate sequence, obtain the trend prediction weight of each element; The air conditioning data prediction and control module is used to obtain the adjustment smoothing coefficient according to the time difference between the elements in the temperature change data corresponding to all elements in the indoor temperature change rate sequence and the trend prediction weight; the adjustment smoothing coefficient is substituted into the EMA algorithm, and the temperature of the control area of ​​the central air conditioner is predicted according to the temperature control sequence to control the energy consumption of the central air conditioner.

10. An intelligent energy-saving control system for air conditioning based on the Internet of Things, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of an intelligent energy-saving control method for air conditioning based on the Internet of Things as described in any one of claims 1 to 8 are implemented.

Images