Air conditioner energy-saving control method and system based on cloud real-time streaming

Abstract

The invention discloses an air conditioner energy-saving control method and system based on cloud real-time streaming, and the method comprises the following steps: evaluating the refrigerating capacity of equipment based on the historical operation data of a user, and obtaining the target temperature of the operation according to the refrigerating capacity value under the same working condition or the severe working condition; training a load model based on the historical operation data of all users, and applying the model according to the current working condition of the user to obtain a room load value of the current working condition and the optimal starting frequency of the current compressor; and based on the preset time interval, the change trend of the indoor temperature and the change trend of the inner disc temperature are calculated, the current room load is combined, the compressor target operation frequency is calculated, and a compressor target operation frequency instruction is issued to the local air conditioner.

Description

Technical Field

[0001] The present invention relates to the field of smart home control management, and in particular to an air conditioning energy-saving control method and system based on cloud real-time streaming. Background Art

[0002] With the continuous progress of social economy and science and technology, people's requirements for the comfort of living conditions are increasing day by day, and the adjustment quality of air-conditioning systems is also constantly improving. However, this also leads to a gradual increase in the proportion of air-conditioning system energy consumption in total life energy consumption. At present, the factory setting parameters of air-conditioning equipment are fixed. Usually, the environmental parameters in the space area are dynamically changing, and users often adjust the control settings of air-conditioning equipment accordingly. Therefore, how to achieve energy conservation and emission reduction while meeting users' personalized management needs for air-conditioning equipment has become an urgent problem to be solved.

[0003] Specifically, the invention patent application with patent publication number CN118757960A discloses "Air conditioning compressor frequency control method, readable storage medium and air conditioning system". By calibrating the operating parameters of the air conditioner when it was last shut down or calibrating the room parameters to obtain the calibrated temperature and calibrated compressor frequency, the compressor can be controlled in advance to enter an efficient operating state to achieve air conditioning energy saving.

[0004] However, this patent only relies on the operating parameters of the last shutdown, because the working conditions of each startup are different, which has certain limitations. For example, in the invention patent application with patent publication number CN116817424A, "An air conditioning energy-saving control system and method based on artificial intelligence" is disclosed, which sorts out information and classifies all effective operating parameter setting switching behaviors that appear in all historical equipment control events, captures the characteristics of users when operating the target air-conditioning equipment, and obtains information that meets the conditions from all characteristics that switch from high loss to low loss, and then uses it as the operating parameters of the current air-conditioning, but this patent cannot adapt to changes in user working conditions and modifies the air-conditioning parameters set by the user. For another example, in the invention patent application with patent publication number CN118111091A, "Air-conditioning control method, device, equipment, storage medium and program product" is disclosed. By using parameters corresponding to multiple target influencing factors related to room load to train the basic model, each sample load parameter is labeled with room area to obtain area prediction, and then a more accurate target adjustment coefficient is obtained according to the actual room area to adjust the compressor frequency, thereby achieving accurate temperature condition effects. This patent can calculate the adjustment coefficient by area, but it cannot effectively solve the overshoot phenomenon and save energy. It is difficult to get the accurate room area and load. Summary of the invention

[0005] The purpose of the present invention is to provide an air conditioning energy-saving control method and system based on cloud real-time streaming, in order to solve the above technical problems.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An air conditioning energy-saving control method based on cloud real-time streaming includes the following steps:

[0008] Evaluate the cooling capacity of the equipment based on the user's historical operating data, and obtain the target temperature for this operation based on the cooling capacity under the same or worse working conditions;

[0009] The load model is trained based on the historical operation data of all users, and then the model is used according to the user's current working conditions to obtain the room load value of the current working conditions and the optimal startup frequency of the current compressor;

[0010] Based on the preset time interval, the changing trend of the indoor temperature and the changing trend of the internal disk temperature are calculated. Combined with the current room load, the compressor target operating frequency is calculated, and the compressor target operating frequency instruction is sent to the local air conditioner.

[0011] In some embodiments, the cooling capacity of the equipment is evaluated based on the user's historical operating data, and the target temperature of this operation is obtained according to the cooling capacity value under the same working conditions or worse working conditions; including: obtaining the user's historical usage data when running in non-AI mode, and the air-conditioning equipment is turned on and off once as a device control of the target device by the user; the last stable indoor temperature during each device control process is used as the cooling capacity value under the grade equipment control condition, and all qualified capacity values ​​are stored in the redis database to construct a capacity value database; after turning on the device, the user will use the current working conditions and the set indoor temperature and wind speed as conditions to obtain the temperature that can be achieved this time as the target temperature from the capacity value database.

[0012] In some embodiments, the load model is trained based on the historical operating data of all users, and the model is applied according to the user's current working condition to obtain the room load value of the current working condition and the current optimal startup frequency of the compressor; including: using the IOT historical operating data of the air conditioner in non-AI mode, combined with the actual working principle of the air conditioner, determining the IOT data filtering method, preliminarily screening the required data sets, regularly training the load judgment algorithm model, and obtaining the load level of each air conditioner under different working conditions, and combining the indoor and outdoor ambient temperatures and user usage habits to screen out the optimal startup compressor frequency under different historical working conditions, and store the results in the redis database.

[0013] In some embodiments, the method of calculating the change trend of the indoor temperature and the change trend of the internal disk temperature based on the preset time interval, and calculating the compressor target operating frequency in combination with the current room load, and sending the compressor target operating frequency instruction to the local air conditioner includes:

[0014] The range near the target temperature is divided into several intervals according to the gradient algorithm. Within a fixed scheduled time interval, the target frequency value is calculated comprehensively according to the differences between each interval, combined with the indoor temperature trend, the current indoor load value and the internal disk temperature trend, and then the compressor target operating frequency is issued.

[0015] In some embodiments, sending the compressor target operating frequency includes:

[0016] S1: cumulatively calculate the indoor temperature change trend and the internal disk temperature change trend. The temperature change within the period is linearly fitted by y=kx+b, and the slope k is calculated by the least square method; where x is temperature, y is temperature change, and k is slope;

[0017] S2: Determine whether the preset time interval has been reached. If not, continue to execute S1. If it has been reached, proceed to the next process.

[0018] S3: Determine the temperature difference range;

[0019] S4: Calculate the interval where the current temperature difference value is located;

[0020] S5: Determine the temperature trend based on the indoor temperature slope k1 and the inner disk temperature slope w1;

[0021] S6: Calculate whether the compressor needs to be frequency-reduced or frequency-increased based on the current indoor load, the indoor temperature slope and the internal disk temperature slope in the current time interval and the previous two time intervals, and obtain the target operating frequency of the compressor;

[0022] S7: Send the compressor target operating frequency S7.

[0023] In some embodiments, S5: temperature trend determination based on indoor temperature slope k1 and inner disk temperature slope w1; including:

[0024] If the indoor temperature slope decreases, it means the temperature is falling. When the room load is low, the compressor frequency will be reduced. If the load is medium or high and the slope of the internal temperature decreases, it means the temperature is falling. Otherwise, the compressor frequency remains unchanged.

[0025] In some embodiments, S5: temperature trend determination based on indoor temperature slope k1 and inner disk temperature slope w1; including:

[0026] The rising slope of indoor temperature indicates a heating trend. When the room load is low at this time, the compressor frequency will be increased. When the load is medium or high and the slope of the internal disk temperature rises, that is, the internal disk heating trend is present, the compressor frequency will be increased. Otherwise, the compressor frequency remains unchanged.

[0027] In some embodiments, when the indoor temperature slope remains unchanged, it means that the temperature has not changed in the current preset time interval. At this time, it is necessary to combine the indoor temperature change trend of the previous two preset time intervals and the internal disk temperature change trend in the current time interval to determine whether to increase or decrease the frequency and issue an instruction.

[0028] This embodiment also provides an air conditioning energy-saving control system based on cloud real-time streaming, which is used to implement the method described above, including:

[0029] The real-time data receiving module is used to report to the IoT platform every minute or when the device status changes. The IoT platform then pushes the status of the device with the AI ​​switch turned on to the AI ​​decision center for AI energy-saving control;

[0030] The capacity value building module is used to receive IoT data for real-time calculation, obtain the cooling capacity values ​​of users under different working conditions and store them in the database;

[0031] The load identification module is used to train the load judgment algorithm model based on IOT historical data, and to obtain the load level under different working conditions and the optimal startup frequency of the compressor;

[0032] The AI ​​decision center module is used to obtain the target temperature and startup frequency according to the working conditions after the equipment is started up and the preset set temperature and wind speed, and to operate at the startup frequency until the indoor temperature reaches the temperature value and then enter real-time frequency control;

[0033] The request sending module is used to send the startup frequency when starting up, and to send the calculated compressor target operating frequency at preset time intervals after real-time frequency control.

[0034] The beneficial effects that may be brought about by the air conditioning energy-saving control method and system based on cloud real-time streaming disclosed in this application include but are not limited to:

[0035] The present invention will use the historical operation data of air conditioner IOT to measure the cooling capacity of air conditioner under user working conditions, and combine the actual working principle of air conditioner to screen the data set to train the load judgment algorithm model, obtain the load type of each device, and combine the indoor and outdoor ambient temperature and user usage habits to screen out the optimal startup frequency under different working conditions. When the equipment is turned on, the target temperature and the optimal startup frequency are obtained in combination with the current working load level, ambient temperature, windshield, etc. When the indoor temperature is near the target temperature, the temperature difference between the indoor temperature and the target temperature is controlled in real time based on the temperature gradient level to achieve the purpose of energy saving and comfort, and can provide more accurate frequency and temperature control.

[0036] The present invention is beneficial to the energy saving of air conditioners, and can adapt to old equipment installed in the user's home, while ensuring the working conditions of each device. By identifying the load of the equipment in each room and combining the capacity value of the air conditioner obtained from historical data, the effective compressor operating frequency and target operating temperature are obtained, and the relationship between the coil temperature change trend and the indoor temperature change trend is combined to accurately control the compressor operating frequency, achieving effective energy saving and emission reduction effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] like Figure 1 The figure shows the framework principle diagram of the air conditioning energy-saving control system based on cloud real-time streaming.

[0038] like Figure 2 The figure shows the flow chart of air conditioning energy-saving control system based on cloud real-time streaming

[0039] like Figure 3 The figure shows the real-time frequency control process of AI air conditioner. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present application more clear, the present application is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.

[0041] On the contrary, the present application covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present application as defined by the claims. Further, in order to make the public have a better understanding of the present application, some specific details are described in detail in the detailed description of the present application below. Those skilled in the art can fully understand the present application without the description of these details.

[0042] The following is a detailed description of an air conditioning energy-saving control method and system based on cloud real-time streaming involved in the embodiments of the present application. It is worth noting that the following embodiments are only used to explain the present application and do not constitute a limitation on the present application.

[0043] like Figure 1-3 As shown, an air conditioning energy-saving control method based on cloud real-time streaming includes the following steps:

[0044] Evaluate the cooling capacity of the equipment based on the user's historical operating data, and obtain the target temperature for this operation based on the cooling capacity under the same or worse working conditions;

[0045] The load model is trained based on the historical operation data of all users, and then the model is used according to the user's current working conditions to obtain the room load value of the current working conditions and the optimal startup frequency of the current compressor;

[0046] Based on the preset time interval, the changing trend of the indoor temperature and the changing trend of the internal disk temperature are calculated. Combined with the current room load, the compressor target operating frequency is calculated, and the compressor target operating frequency instruction is sent to the local air conditioner.

[0047] The control method mentioned in the present invention requires user authorization before use, and has two parameters: AI switch and AI enable switch. After the AI ​​switch is turned on, the cloud enters the AI ​​control mode. When the AI ​​switch is turned off, the local PID of the air conditioner performs control. After AI enable is turned on, the air conditioner exits PID (the core technology for temperature regulation in the air conditioning system) control, and the cloud performs real-time frequency control based on real-time streaming data. After AI enable is turned off, the local PID of the air conditioner performs control.

[0048] Get the target temperature. Use the historical operation data of the air conditioner IOT (not in AI mode) to measure the cooling capacity of the air conditioner under user conditions.

[0049] The air conditioner is operated from the start to the shutdown. The historical equipment control events generated by the user on the target air conditioner are extracted. Including indoor temperature, outdoor temperature, day and night information, set temperature, set wind speed. The indoor temperature that can be stably operated under these conditions is the capacity value of the air conditioner under this working condition, and is stored in the capacity value redis database. After the device turns on the AI ​​switch, the capacity value database is queried according to the current ambient temperature, set temperature, and wind speed when it is turned on. If the conditions are not met, the capacity value with worse conditions is taken. For example: the outdoor temperature is higher, the wind speed is lower, and the set temperature is lower. When the key state changes, the capacity value needs to be checked again (one of the set temperature, set wind speed, sleep mode change, day and night switching). When the capacity value is checked again, the indoor and outdoor temperatures at the time of startup are used as conditions. After obtaining the capacity value, the capacity value is compared with the set temperature, and the target temperature is obtained according to the rules.

[0050] In some embodiments, the cooling capacity of the equipment is evaluated based on the user's historical operating data, and the target temperature of this operation is obtained according to the cooling capacity value under the same working conditions or worse working conditions; including: obtaining the user's historical usage data when running in non-AI mode, and the air-conditioning equipment is turned on and off once as a device control of the target device by the user; the last stable indoor temperature during each device control process is used as the cooling capacity value under the grade equipment control condition, and all qualified capacity values ​​are stored in the redis database to construct a capacity value database; after turning on the device, the user will use the current working conditions and the set indoor temperature and wind speed as conditions to obtain the temperature that can be achieved this time as the target temperature from the capacity value database.

[0051] In some embodiments, the load model is trained based on the historical operating data of all users, and the model is applied according to the user's current working condition to obtain the room load value of the current working condition and the current optimal startup frequency of the compressor; including: using the IOT historical operating data of the air conditioner in non-AI mode, combined with the actual working principle of the air conditioner, determining the IOT data filtering method, preliminarily screening the required data sets, regularly training the load judgment algorithm model, and obtaining the load level of each air conditioner under different working conditions, and combining the indoor and outdoor ambient temperatures and user usage habits to screen out the optimal startup compressor frequency under different historical working conditions, and store the results in the redis database.

[0052] Get room load. Use IOT historical operation data of air conditioners in non-AI mode, combined with the actual working principle of air conditioners, determine IOT data filtering methods, preliminarily screen required data sets, train load judgment algorithm models, and obtain load levels (low, medium, high) of each air conditioner under different working conditions. Combined with indoor and outdoor ambient temperatures, user usage habits, etc., screen out the optimal compressor frequency when starting up under different historical working conditions, and store the results in the redis database.

[0053] Get the optimal startup frequency. When the air conditioner is turned on, the trained load judgment model and the optimal startup frequency database are used to infer the load level, and then the optimal frequency of the compressor for the current startup is obtained by combining the ambient temperature, wind speed and other conditions.

[0054] The compressor shuts down due to overshoot. The cloud determines based on the actual flow data that the equipment compressor shuts down due to overshoot. After the machine is turned on, it will directly run at the lowest operating frequency of the compressor.

[0055] Real-time frequency control. After starting up, the compressor runs at the optimal frequency. When the temperature difference between the indoor temperature and the target temperature reaches the target temperature, the real-time frequency control is entered. The cloud controls the frequency of the air conditioner compressor according to the real-time frequency control rules to achieve energy saving and comfort, and the frequency control and indoor temperature control are more accurate.

[0056] In some embodiments, the method of calculating the change trend of the indoor temperature and the change trend of the internal disk temperature based on the preset time interval, and calculating the compressor target operating frequency in combination with the current room load, and sending the compressor target operating frequency instruction to the local air conditioner includes:

[0057] The range near the target temperature is divided into several intervals according to the gradient algorithm. Within a fixed scheduled time interval, the target frequency value is calculated comprehensively according to the differences between each interval, combined with the indoor temperature trend, the current indoor load value and the internal disk temperature trend, and then the compressor target operating frequency is issued.

[0058] In some embodiments, sending the compressor target operating frequency includes:

[0059] S1: cumulatively calculate the indoor temperature change trend and the internal disk temperature change trend. The temperature change within the period is linearly fitted by y=kx+b, and the slope k is calculated by the least square method; where x is temperature, y is temperature change, and k is slope;

[0060] S2: Determine whether the preset time interval has been reached. If not, continue to execute S1. If it has been reached, proceed to the next process.

[0061] S3: Determine the temperature difference range;

[0062] S4: Calculate the interval where the current temperature difference value is located;

[0063] S5: Determine the temperature trend based on the indoor temperature slope k1 and the inner disk temperature slope w1;

[0064] S6: Calculate whether the compressor needs to be frequency-reduced or frequency-increased based on the current indoor load, the indoor temperature slope and the internal disk temperature slope in the current time interval and the previous two time intervals, and obtain the target operating frequency of the compressor;

[0065] S7: Send the compressor target operating frequency S7.

[0066] In some embodiments, S5: temperature trend determination based on indoor temperature slope k1 and inner disk temperature slope w1; including:

[0067] If the indoor temperature slope decreases, it means the temperature is falling. When the room load is low, the compressor frequency will be reduced. If the load is medium or high and the slope of the internal temperature decreases, it means the temperature is falling. Otherwise, the compressor frequency remains unchanged.

[0068] The rising slope of indoor temperature indicates a heating trend. When the room load is low at this time, the compressor frequency will be increased. When the load is medium or high and the slope of the internal disk temperature rises, that is, the internal disk heating trend is present, the compressor frequency will be increased. Otherwise, the compressor frequency remains unchanged.

[0069] When the indoor temperature slope remains unchanged, it means that the temperature has not changed in the current preset time interval. At this time, it is necessary to combine the indoor temperature change trend of the previous two preset time intervals and the internal disk temperature change trend in the current time interval to determine whether to increase or decrease the frequency and issue a command.

[0070] This embodiment also provides an air conditioning energy-saving control system based on cloud real-time streaming, which is used to implement the method described above, including:

[0071] The real-time data receiving module is used to report to the IoT platform every minute or when the device status changes. The IoT platform then pushes the status of the device with the AI ​​switch turned on to the AI ​​decision center for AI energy-saving control;

[0072] The capacity value building module is used to receive IoT data for real-time calculation, obtain the cooling capacity values ​​of users under different working conditions and store them in the database;

[0073] The load identification module is used to train the load judgment algorithm model based on IOT historical data, and to obtain the load level under different working conditions and the optimal startup frequency of the compressor;

[0074] The AI ​​decision center module is used to obtain the target temperature and startup frequency according to the working conditions after the equipment is started up and the preset set temperature and wind speed, and to operate at the startup frequency until the indoor temperature reaches the temperature value and then enter real-time frequency control;

[0075] The request sending module is used to send the startup frequency when starting up, and to send the calculated compressor target operating frequency at preset time intervals after real-time frequency control.

[0076] The following is a detailed description of the Redis database as a storage medium to store the capacity value and the boot frequency. The specific application of the present invention is as follows:

[0077] 1. The air conditioner will report the full status to the IoT platform on a regular basis, and the IoT platform will push the message to the real-time stream AI decision center through Kafka. When key status fields (such as indoor temperature, mode, wind speed, etc.) change, the device will report immediately.

[0078] 2. AI performance identification: In the cloud, we first use the historical data and real-time data of the device running in non-AI mode, use multivariate regression prediction, and set the temperature and wind speed according to the indoor temperature, outdoor temperature, day and night information. The indoor temperature that can be stably operated under these conditions is the capacity value of the air conditioner under this condition, and it is stored in the capacity value redis database. This result is calculated and updated in real time.

[0079] 3. AI load identification: Utilize the IOT historical operation data of the air conditioner in non-AI mode, combined with the actual working principle of the air conditioner, determine the IOT data filtering method, preliminarily screen the required data set, regularly train the load judgment algorithm model, and obtain the load level (low, medium, high) of each air conditioner under different working conditions. Combined with indoor and outdoor ambient temperature, user usage habits (such as wind speed), etc., screen out the optimal compressor frequency when starting up under different historical working conditions, and store the results in the redis database.

[0080] 4. After the equipment is turned on and the oil return is completed, the air conditioner energy saving control is carried out in real time on the cloud. Air conditioner oil return: refers to the process from the discharge of lubricating oil to the return of the compressor. The compressor relies on lubricating oil to reduce internal friction and wear and maintain efficient operation. The lack of an oil return mechanism will cause damage to the compressor and affect the stable operation of the system.

[0081] 5. Target temperature. According to the operating conditions of the equipment at that time (mode, wind speed, set temperature, indoor and outdoor temperature, etc.), the capability value database built by AI performance recognition is queried for the capability value of the air conditioner at that time as the target temperature, which is the final target indoor temperature of the equipment operation.

[0082] 6. Temperature difference: indoor temperature - target temperature.

[0083] 7. Temperature value: The pre-set value from the target temperature. For example: 1 degree. The target temperature is 26℃, and the temperature value is 27℃.

[0084] 8. Reach temperature. The temperature difference is less than or equal to the set temperature.

[0085] 9. After completing the above steps, enter the AI ​​air conditioning decision-making data process.

[0086] a. Whether the power-on status D1;

[0087] b. When the machine is turned on, the data is checked to see if it is valid D2, and when the machine is turned off, the process ends. ; Data detection is valid (AI

[0088] All the parameters required for optimization have values, and it is cooling mode at this time, and the user turns on the AI ​​switch), determine whether it is necessary to obtain the target temperature D3, if it is invalid, end this process;

[0089] c. When the set temperature, set wind speed, sleep mode, day and night change, the target temperature D4 needs to be obtained, otherwise the target temperature does not need to be obtained;

[0090] d. When there is a target temperature, determine whether it is necessary to obtain the power-on frequency D6; if necessary, re-obtain the power-on frequency D7, otherwise, do not obtain the power-on frequency;

[0091] e. Determine whether the indoor temperature minus the target temperature reaches temperature D8

[0092] ① Temperature reached: immediately enter real-time frequency control D9;

[0093] ② Temperature not reached: Determine whether there is a power-on frequency D10. If there is a power-on frequency, run according to the power-on frequency D11. Otherwise, run according to PID control.

[0094] f. This process ends, and the next data comes and the cycle is executed again.

[0095] 10. After entering the real-time frequency control, the target temperature range is divided into several intervals according to the gradient algorithm, such as A, B, C, D, and E. After the fixed reservation time interval is reached, the target frequency value is calculated comprehensively according to the difference between each interval, combined with the indoor temperature trend, the current indoor load value, and the internal disk temperature trend, and then the compressor target operating frequency is issued.

[0096] 11. The process after entering real-time frequency control is as follows:

[0097] a. Cumulative calculation of indoor temperature change trend and inner disk temperature change trend S1. The temperature change within the period can be linearly fitted by y=kx+b, and the slope k is calculated by the least square method. Note: The form of y=kx+b is a common method in statistics and data analysis. This equation describes the linear relationship between two variables (here y and x), where x is the temperature (indoor temperature or inner disk temperature), y is the temperature change, k is the slope, which means the average change of y for each unit increase of x, and b is the intercept, which means the value of y when x=0.

[0098] b. Determine whether the preset time interval S2 is reached. If not, continue with S1, and enter the next process after reaching it;

[0099] c. Determine the temperature difference range S3.

[0100] d. The temperature difference value at this time is in interval S4.

[0101] e. Temperature trend judgment S5. Indoor temperature slope k1, internal disk temperature slope w1. The slope is stored in the cache.

[0102] f. Calculate the compressor target frequency value S6. According to the current indoor load, the indoor temperature slope and the internal disk temperature slope in the current time interval and the previous two time intervals, calculate whether the compressor needs to reduce or increase the frequency at this time, and obtain the compressor's target operating frequency.

[0103] g. Send the compressor target operating frequency S7.

[0104] 12. When the indoor temperature slope decreases, it means there is a cooling trend. When the room load is low at this time, the compressor frequency will be reduced. When it is medium or high load and the slope of the internal disk temperature decreases, that is, there is a cooling trend of the internal disk (the cooling of the internal disk is accompanied by a decrease in the indoor temperature), the compressor frequency will be reduced. Otherwise, the compressor frequency remains unchanged.

[0105] 13. The rising slope of indoor temperature indicates a heating trend. When the room load is low, the compressor frequency will be increased. When the load is medium or high and the slope of the internal disk temperature rises, that is, the internal disk heating trend (the heating of the internal disk is accompanied by the heating of the indoor temperature), the compressor frequency will be increased. Otherwise, the compressor frequency remains unchanged.

[0106] 14. When the indoor temperature slope remains unchanged, it means that the temperature has not changed in the current preset time interval. At this time, it is necessary to combine the indoor temperature change trend of the previous two preset time intervals and the internal disk temperature change trend in the current time interval to determine whether to increase or decrease the frequency and issue a command.

[0107] 15. When sending the compressor frequency, according to the frequency hopping point range of the compressor and the frequency increase and decrease trend, send the final frequency value that bypasses the frequency hopping range.

[0108] 16. When the indoor temperature does not reach the target temperature for several consecutive preset time intervals, the compressor target operating frequency value must be recalculated.

[0109] 17. The way to calculate the compressor operating frequency varies when the temperature difference is within a certain range. The larger the temperature difference, the greater the frequency change. This allows the compressor to approach the target temperature faster and operate stably at this temperature to achieve energy saving.

[0110] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An air conditioning energy-saving control method based on cloud real-time streaming, characterized in that: The following steps are involved: Evaluate the cooling capacity of the equipment based on the user's historical operating data, and obtain the target temperature for this operation based on the cooling capacity under the same or worse working conditions; The load model is trained based on the historical operation data of all users, and then the model is used according to the user's current working conditions to obtain the room load value of the current working conditions and the optimal startup frequency of the current compressor; Based on the preset time interval, the changing trend of the indoor temperature and the changing trend of the internal disk temperature are calculated. Combined with the current room load, the compressor target operating frequency is calculated and the compressor target operating frequency instruction is sent to the local air conditioner.

2. The air conditioning energy saving control method based on cloud real-time streaming according to claim 1 is characterized in that: The method evaluates the cooling capacity of the equipment based on the user's historical operating data, and obtains the target temperature of this operation according to the cooling capacity value under the same working condition or worse working condition; including: obtaining the historical usage data of the user in non-AI mode, and the air-conditioning equipment is operated by the user once from the start to the shutdown; the last stable indoor temperature in each equipment operation process is used as the cooling capacity value under the equipment control condition, and all qualified capacity values ​​are stored in the redis database to construct a capacity value database; after turning on the equipment, the user will obtain the temperature that can be achieved this time as the target temperature based on the current working condition and the set indoor temperature and wind speed as conditions from the capacity value database.

3. The air conditioning energy saving control method based on cloud real-time streaming according to claim 1 is characterized in that: The method trains a load model based on the historical operating data of all users, and applies the model according to the user's current working condition to obtain the room load value of the current working condition and the current optimal startup frequency of the compressor; including: utilizing the IOT historical operating data of the air conditioner in the non-AI mode, combining with the actual working principle of the air conditioner, determining the IOT data filtering method, preliminarily screening the required data sets, regularly training the load judgment algorithm model, obtaining the load level of each air conditioner in different working conditions, and combining the indoor and outdoor ambient temperatures and user usage habits to screen out the optimal startup compressor frequency under different historical working conditions, and storing the results in the redis database.

4. The air conditioning energy saving control method based on cloud real-time streaming according to claim 1 is characterized in that: The method calculates the change trend of the indoor temperature and the change trend of the internal temperature based on the preset time interval, calculates the target operating frequency of the compressor in combination with the current room load, and sends the target operating frequency instruction of the compressor to the local air conditioner, including: The range near the target temperature is divided into several intervals according to the gradient algorithm. Within a fixed scheduled time interval, the target frequency value is calculated comprehensively according to the differences between each interval, combined with the indoor temperature trend, the current indoor load value and the internal disk temperature trend, and then the compressor target operating frequency is issued.

5. The air conditioning energy saving control method based on cloud real-time streaming according to claim 4 is characterized in that: The target operating frequency of the compressor is sent as follows: S1: cumulatively calculate the indoor temperature change trend and the internal disk temperature change trend. The temperature change within the period is linearly fitted by y=kx+b, and the slope k is calculated by the least square method; where x is temperature, y is temperature change, and k is slope; S2: Determine whether the preset time interval has been reached. If not, continue to execute S1. If it has been reached, proceed to the next process. S3: Determine the temperature difference range; S4: Calculate the interval where the current temperature difference value is located; S5: Determine the temperature trend based on the indoor temperature slope k1 and the inner disk temperature slope w1; S6: Calculate whether the compressor needs to be frequency-reduced or frequency-increased based on the current indoor load, the indoor temperature slope and the internal disk temperature slope in the current time interval and the previous two time intervals, and obtain the target operating frequency of the compressor; S7: Send the compressor target operating frequency S7.

6. The air conditioning energy saving control method based on cloud real-time streaming according to claim 5 is characterized in that: S5: Determine the temperature trend based on the indoor temperature slope k1 and the internal disk temperature slope w1; including: If the indoor temperature slope decreases, it means the temperature is falling. When the room load is low, the compressor frequency will be reduced. If the load is medium or high and the slope of the internal temperature decreases, it means the temperature is falling. Otherwise, the compressor frequency remains unchanged.

7. The air conditioning energy saving control method based on cloud real-time streaming according to claim 5 is characterized in that: S5: Determine the temperature trend based on the indoor temperature slope k1 and the internal disk temperature slope w1; including: The rising slope of indoor temperature indicates a heating trend. When the room load is low at this time, the compressor frequency will be increased. When the load is medium or high and the slope of the internal disk temperature rises, that is, the internal disk heating trend is present, the compressor frequency will be increased. Otherwise, the compressor frequency remains unchanged.

8. The air conditioning energy saving control method based on cloud real-time streaming according to claim 5 is characterized in that: S5: Determine the temperature trend based on the indoor temperature slope k1 and the internal disk temperature slope w1; including: when the indoor temperature slope remains unchanged, it means that the temperature has not changed in the current preset time interval. At this time, it is necessary to combine the indoor temperature change trend of the previous two preset time intervals and the internal disk temperature change trend in the current time interval to determine whether to increase or decrease the frequency and issue an instruction.

9. An air conditioning energy-saving control system based on cloud real-time streaming, characterized in that: The method for implementing any one of claims 1 to 8 comprises: The real-time data receiving module is used to report to the IoT platform every minute or when the device status changes. The IoT platform then pushes the status of the device with the AI ​​switch turned on to the AI ​​decision center for AI energy-saving control; The capacity value building module is used to receive IoT data for real-time calculation, obtain the cooling capacity values ​​of users under different working conditions and store them in the database; The load identification module is used to train the load judgment algorithm model based on IOT historical data, and to obtain the load level under different working conditions and the optimal startup frequency of the compressor; The AI ​​decision center module is used to obtain the target temperature and startup frequency according to the working conditions after the equipment is started up and the preset set temperature and wind speed, and to operate at the startup frequency until the indoor temperature reaches the temperature value and then enter real-time frequency control; The request sending module is used to send the startup frequency when starting up, and to send the calculated compressor target operating frequency at preset time intervals after real-time frequency control.

Images