Temperature control method based on edge computing, edge computing node device and medium

Abstract

The application relates to the technical field of temperature monitoring, in particular to a temperature control method based on edge computing, an edge computing node device and a medium. The edge computing node device collects initial data of an environment where a terminal device is located for a specified duration every preset collection period, processes target data obtained by processing the initial data for the specified duration, and generates a temperature adjustment strategy based on the target data and an intelligent decision-making model obtained from a cloud server. The temperature adjustment strategy can be used for real-time data processing and decision-making, and a temperature control instruction carrying the temperature adjustment strategy can be rapidly sent to the terminal device, so that the terminal device can respond to the temperature control instruction in a short time and efficiently perform temperature adjustment.

Description

Technical Field

[0001] This application relates to the field of temperature monitoring technology, and in particular to a temperature control method based on edge computing, an edge computing node device, and a medium. Background Technology

[0002] Traditional temperature control methods either rely on preset control rules or static control strategies, or employ centralized control. Methods based on preset rules or static strategies lack adaptability to environmental changes and real-time demands, resulting in poor temperature control accuracy. Centralized control methods require transmitting all collected data to a cloud server for processing and decision-making before sending temperature control commands to individual terminal devices. However, latency in data transmission between the cloud server and terminal devices leads to slow response times and low efficiency in temperature control. Summary of the Invention

[0003] In view of the above, this application provides a temperature control method, edge computing node device and medium based on edge computing, which uses edge computing node device to collect data in real time and generates temperature adjustment strategy based on intelligent decision model, thereby enabling accurate and rapid temperature adjustment of terminal device.

[0004] A first aspect of this application provides a temperature control method based on edge computing, the method comprising: Initial data of the environment of the terminal device is collected every preset collection period for a specified duration; Obtain the target data from the initial data of the specified duration; A temperature regulation strategy is generated based on the target data using an intelligent decision-making model obtained from a cloud server. A temperature control command carrying the temperature regulation strategy is sent to the terminal device, so that the terminal device performs temperature regulation according to the temperature control command.

[0005] In an optional implementation, the initial data includes temperature data and multiple types of environmental data, and obtaining the target data from the initial data for the specified duration includes: Calculate the mean environmental data for each type of environmental data for the specified duration; Calculate the mean temperature data of the temperature data for the specified duration; Calculate the correlation coefficient between the mean environmental data and the mean temperature data for each type; Select a target correlation coefficient that is greater than a preset correlation coefficient threshold from among the multiple correlation coefficients; The temperature data and the multiple types of environmental data corresponding to the specified duration of the target correlation coefficient are determined as the target data.

[0006] In an optional implementation, generating a temperature regulation strategy based on the target data using an intelligent decision-making model obtained from a cloud server includes: The intelligent decision-making model is used to predict temperature change trends based on the target data. The temperature adjustment cycle is determined based on the temperature change trend. The temperature adjustment range is calculated based on the average temperature data and the preset target temperature range. The temperature regulation strategy is generated based on the temperature regulation cycle and the temperature regulation amplitude.

[0007] In an optional implementation, calculating the temperature adjustment range based on the average temperature data and the preset target temperature range includes: The average temperature data is compared with the upper and lower limits of the preset target temperature range to obtain the comparison results. Based on the comparison results, the temperature adjustment range is determined.

[0008] In an optional implementation, determining the temperature adjustment range based on the comparison result includes: When the comparison result is that the average temperature data is greater than the upper limit of the preset target temperature range, the first temperature adjustment range is determined based on the average temperature data and the upper limit of the preset target temperature range. When the comparison result is that the average temperature data is less than the lower limit of the preset target temperature range, the second temperature adjustment range is determined based on the average temperature data and the lower limit of the preset target temperature range. When the comparison result is that the average temperature data is less than the upper limit of the preset target temperature range and greater than the lower limit of the preset target temperature range, a third temperature adjustment range is determined.

[0009] In an optional implementation, determining the first temperature adjustment range based on the average temperature data and the upper limit of the preset target temperature range includes: Calculate the first difference between the mean temperature data and the upper limit of the preset target temperature range; Calculate the second difference between the mean temperature data and the temperature reference value, where the temperature reference value is the average of the upper and lower limits of the preset target temperature range; Calculate the first ratio between the first difference and the second difference; The first temperature adjustment range is determined based on the first ratio and the preset first adjustment coefficient.

[0010] In an optional implementation, the second temperature adjustment range is determined based on the average temperature data and the lower limit of the preset target temperature range. Calculate the third difference between the lower limit of the preset target temperature range and the mean temperature data; Calculate the fourth difference between the temperature baseline value and the mean temperature data; Calculate the second ratio between the third difference and the fourth difference; The second temperature adjustment range is determined based on the second ratio and the preset second adjustment coefficient.

[0011] In an optional implementation, the method further includes: Determine whether there is any abnormal temperature data in the temperature data for the specified duration; When it is determined that there is abnormal temperature data in the temperature data for the specified duration, the target alarm method is determined according to the abnormal temperature data and the preset temperature threshold segmentation interval, and an alarm is triggered according to the target alarm method. The preset temperature threshold segmentation range includes multiple temperature threshold ranges, and each temperature threshold range corresponds to an alarm mode.

[0012] This application provides an edge computing node device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the edge computing-based temperature control method.

[0013] A third aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described edge computing-based temperature control method.

[0014] In summary, the edge computing-based temperature control method, edge computing node device, and medium provided in this application collect initial data of the environment where the terminal device is located for a specified duration at preset collection cycles by the edge computing node device. The target data is obtained by processing the initial data for the specified duration and the intelligent decision-making model obtained from the cloud server is used to generate a temperature regulation strategy based on the target data. This allows for real-time data processing and decision-making, and the rapid sending of temperature control commands carrying the temperature regulation strategy to the terminal device. This enables the terminal device to respond to the temperature control commands and perform temperature regulation efficiently in a short time. Attached Figure Description

[0015] Figure 1This is a flowchart illustrating a temperature control method based on edge computing, as shown in an embodiment of this application. Figure 2 This application illustrates a flowchart of a method for generating temperature regulation strategies using an intelligent decision-making model; Figure 3 This is a schematic diagram of the structure of an edge computing node device shown in an embodiment of this application. Detailed Implementation

[0016] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations that include one or more of the listed items.

[0017] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0018] Reference Figure 1 As shown, Figure 1 This is a flowchart illustrating a temperature control method based on edge computing according to an embodiment of this application. The temperature control method based on edge computing is executed by an edge computing node device and may specifically include the following steps.

[0019] S11: Collect initial data of the environment of the terminal device for a specified duration every preset collection cycle.

[0020] Multiple edge computing nodes are pre-deployed in the area requiring temperature control. These nodes are connected to a cloud server, and each node is positioned near the edge of the terminal device. Each edge computing node is a device with computing capabilities, such as an edge server, gateway, router, or smart sensor. These nodes can perform local computing tasks, such as data filtering, data aggregation, real-time analysis, and decision-making.

[0021] Edge computing node devices can have a pre-set data collection cycle, such as timed collection every 10 minutes, to collect initial data about the environment in which the terminal device (e.g., an air conditioner, heater, etc.) is located. Edge computing node devices can also have a pre-specified duration, such as 1 minute, to collect initial data about the terminal's environment for that specified duration. For example, an edge computing node device collects initial data about the terminal device's environment for 1 minute every 10 minutes.

[0022] The initial data may include temperature data and multiple types of environmental data. These multiple types of environmental data may include, but are not limited to: temperature data, humidity data, air pressure data, light intensity data, sound data, and human activity data.

[0023] In some embodiments, edge computing node devices can be deployed using wireless sensor networks, and the edge computing node devices may include at least one sensor. The sensors may include temperature sensors, humidity sensors, barometric pressure sensors, people counting sensors, etc. Any sensor capable of accurately collecting the initial data can be included in the embodiments of this application, and is not listed individually here.

[0024] In an optional implementation, after collecting initial data on the environment of the terminal device for a specified duration at preset collection cycles, the method further includes: Determine whether there are abnormal average temperature data in the temperature data for the specified duration; When it is determined that there is abnormal temperature data in the temperature data for the specified duration, the target alarm mode is determined according to the abnormal temperature data and the preset temperature threshold segmentation interval, and an alarm is triggered according to the target alarm mode.

[0025] In some embodiments, when a sensor malfunctions or is not calibrated accurately, it can lead to incorrect temperature data readings. Or, when there is environmental interference such as circuit failure, short circuit, or external heat source, the temperature data may become abnormal. Therefore, edge computing node devices can use anomaly detection algorithms, such as statistical methods (e.g., mean, standard deviation), machine learning algorithms (e.g., support vector machine, random forest), or deep learning algorithms (e.g., neural network), to determine whether there is abnormal temperature data in the temperature data for a specified duration.

[0026] In some embodiments, the edge computing node device can pre-set temperature threshold intervals, which may include multiple temperature threshold intervals, each corresponding to an alarm method, with different temperature threshold intervals corresponding to different alarm methods. For example, the edge computing node device can pre-set a first temperature threshold interval, a second temperature threshold interval, and a third temperature threshold interval, wherein the first temperature threshold interval corresponds to a first alarm method, the second temperature threshold interval corresponds to a second alarm method, and the third temperature threshold interval corresponds to a third alarm method.

[0027] For example, assuming the first temperature threshold range is set to a temperature range of less than or equal to 18°C, if any temperature data within a specified duration is ≤18°C, the edge computing node device can trigger an alarm using the first alarm method, such as sending a low-temperature warning to relevant personnel and notifying them by phone. Assuming the second temperature threshold range is set to [35°C, 40°C], if any temperature data within a specified duration is ≤40°C and below 35°C, the edge computing node device can trigger an alarm using the second alarm method, such as sending a high-temperature warning to relevant personnel. Furthermore, assuming the third temperature threshold range is set to a temperature range greater than 40°C, if any temperature data within a specified duration is >40°C, the edge computing node device can trigger an alarm using the third alarm method, such as notifying relevant personnel by phone.

[0028] Through the aforementioned optional implementation methods, the edge computing node device compares abnormal temperature data with each temperature threshold range to determine which temperature threshold range the abnormal temperature data falls within, thereby determining which alarm method to use and then triggering an alarm based on the determined alarm method. Using different alarm methods enables relevant personnel to promptly detect temperature anomalies and take immediate action, facilitating early warning and rapid response to temperature anomalies, thus ensuring that the temperature remains within a safe range, preventing accidents, or reducing potential risks.

[0029] S12, Obtain target data from the initial data of the specified duration.

[0030] When the edge computing node device collects the initial data of the environment in which the terminal device is located, the initial data contains a lot of useless data, which will interfere with the temperature control of the terminal device. Therefore, the edge computing node device needs to process the initial data to obtain the target data. Temperature control based on the target data can improve the accuracy of temperature control.

[0031] In an optional implementation, obtaining the target data from the initial data of the specified duration includes: Calculate the mean environmental data for each type of environmental data for the specified duration; Calculate the mean temperature data of the temperature data for the specified duration; Calculate the correlation coefficient between the mean environmental data and the mean temperature data for each type; Determine a target correlation coefficient that is greater than a preset correlation coefficient threshold from among the multiple correlation coefficients; The temperature data for the specified duration and the environmental data corresponding to the target correlation coefficient are determined as the target data.

[0032] The multiple types of environmental data refer to the data in the initial data other than temperature data. Assuming the initial data includes: temperature data, humidity data, air pressure data, light intensity data, sound data, and human activity data, then the multiple types of environmental data are: humidity data, air pressure data, light intensity data, sound data, and human activity data.

[0033] Edge computing node devices collect multiple temperature data points over a specified duration. By calculating the average of these multiple temperature data points, the average temperature data can be obtained.

[0034] Edge computing node devices collect multiple environmental data points of each type over a specified duration, such as multiple humidity data points, multiple air pressure data points, multiple light intensity data points, multiple sound data points, and multiple human activity data points. By calculating the average of the multiple humidity data points, average humidity data can be obtained; by calculating the average of the multiple air pressure data points, average air pressure data can be obtained; by calculating the average of the multiple light intensity data points, average light intensity data can be obtained; by calculating the average of the multiple sound data points, average sound data can be obtained; and by calculating the average of the multiple human activity data points, average human activity data can be obtained.

[0035] Edge computing node devices can pre-set correlation coefficient thresholds and use mathematical software, programming languages, or statistical software packages to calculate the correlation coefficient between mean environmental data and mean temperature data for each type. The correlation coefficient is a statistic used to measure the degree of linear correlation between two variables.

[0036] In one optional implementation, the Pearson correlation coefficient between the mean environmental data and the mean temperature data for each type can be calculated. If the Pearson correlation coefficient is positive, it indicates that the two variables are positively correlated (i.e., when one increases, the other also increases, or when one decreases, the other also decreases); if the Pearson correlation coefficient is negative, it indicates that the two variables are negatively correlated (i.e., when one increases, the other decreases, or when one decreases, the other increases).

[0037] When the correlation coefficient between the mean environmental data and the mean temperature data of a certain type is greater than a preset correlation coefficient threshold, it indicates that the mean environmental data and the mean temperature data of that type are positively correlated, thus having a positive impact on temperature regulation. In this case, the calculated correlation coefficient is used as the target correlation coefficient, and the environmental data of that type for a specified duration is the target data. When the correlation coefficient between the mean environmental data and the mean temperature data of a certain type is less than a preset correlation coefficient threshold, it indicates that the mean environmental data and the mean temperature data of that type are negatively correlated, thus having a negative impact on temperature regulation. In this case, the environmental data of that type for a specified duration can be deleted. The target data also includes the temperature data for the specified duration.

[0038] For example, assuming a preset correlation coefficient threshold of 0.7, the temperature data collected within a specified duration are [25°C, 26°C, 24°C], the humidity data in the environmental data are [50%RH, 45%RH, 55%RH], the air pressure data are [1013hPa, 1012hPa, 1015hPa], the light intensity data are [1000 lux, 900 lux, 1100 lux], and the sound data are [60 dB, 55 dB, 65 dB]. When calculating the correlation coefficients between the mean humidity data and the mean temperature data [dB], the correlation coefficients between the mean air pressure data and the mean temperature data are 0.5, the correlation coefficients between the mean light intensity data and the mean temperature data are 0.87, the correlation coefficients between the mean sound data and the mean temperature data are 0.1, and the correlation coefficients between the mean human activity data and the mean temperature data are 0.75. Since the correlation coefficients between the mean humidity data and the mean temperature data (0.8), the correlation coefficients between the mean light intensity data and the mean temperature data (0.87), and the correlation coefficients between the mean human activity data and the mean temperature data (0.75) are greater than the preset correlation coefficient threshold of 0.7, the temperature data, humidity data, light intensity data, and human activity data collected within the specified duration are determined as the target data.

[0039] S13, using the intelligent decision-making model obtained from the cloud server, generate a temperature regulation strategy based on the target data.

[0040] The intelligent decision-making model is a machine learning model trained using machine learning algorithms (e.g., linear regression, decision tree, random forest, neural network, etc.) based on historical average temperature data and historical environmental data. The intelligent decision-making model is deployed on a cloud server. The cloud server can periodically or irregularly update the intelligent decision-making model to improve its performance.

[0041] Any edge computing node device that establishes a connection with the cloud server can download the intelligent decision-making model from the cloud server. When the cloud server updates the intelligent decision-making model, the edge computing node device can promptly learn of this and download the updated intelligent decision-making model from the cloud server.

[0042] In some embodiments, before generating a temperature regulation strategy based on the target data using an intelligent decision-making model, the target data can be preprocessed, for example, by data cleaning, noise removal, outlier removal, and missing value filling, to ensure the quality and consistency of the target data.

[0043] It should be understood that after preprocessing the target data, an intelligent decision-making model can be used to generate a temperature regulation strategy based on the preprocessed target data.

[0044] In an optional implementation, the specific process of generating a temperature regulation strategy based on the target data using an intelligent decision-making model obtained from a cloud server can be found in [reference needed]. Figure 2 And its related descriptions.

[0045] S14, a temperature control command carrying the temperature adjustment strategy is sent to the terminal device, so that the terminal device adjusts the temperature according to the temperature control command.

[0046] When the intelligent decision-making model generates a temperature regulation strategy, the edge computing node device will automatically generate a temperature control command based on the temperature regulation strategy and transmit the generated temperature control command to the terminal device, so that the terminal device can adjust the temperature according to the received temperature control command, thereby realizing temperature regulation and control.

[0047] See Figure 2 The diagram shown is a flowchart illustrating a method for generating a temperature regulation strategy using an intelligent decision-making model, as described in an embodiment of this application. The method for generating a temperature regulation strategy using an intelligent decision-making model includes: S131, the intelligent decision-making model is used to predict the temperature change trend based on the target data.

[0048] When the target data is obtained, the edge computing node device can use an intelligent decision model to extract one or more data statistical features (e.g., average, maximum, minimum, etc.) from each type of target data, and predict the rate of temperature change based on one or more data statistical features of each type of target data, thereby predicting the temperature change trend based on the rate of temperature change.

[0049] Edge computing node devices can preset a temperature change rate threshold. When the calculated temperature change rate is greater than the preset temperature change rate threshold, it indicates that the temperature change trend is relatively fast; when the calculated temperature change rate is less than the preset temperature change rate threshold, it indicates that the temperature change trend is relatively slow.

[0050] S132, determine the temperature adjustment cycle based on the temperature change trend.

[0051] Among them, the temperature change trends are different, and the temperature adjustment cycles are different.

[0052] When the temperature changes rapidly, a shorter temperature adjustment cycle can be set, allowing the temperature to be adjusted quickly in a short time. When the temperature changes slowly, a longer temperature adjustment cycle can be set, allowing the temperature to be adjusted over a longer period of time, resulting in a slower temperature adjustment.

[0053] For example, assuming the temperature change rate threshold is set to 5°C, a calculated temperature change rate of 7°C indicates a rapid temperature change trend, and the temperature can be adjusted every 10 minutes. A calculated temperature change rate of 1°C indicates a slow temperature change trend, and the temperature can be adjusted every hour.

[0054] S133, the temperature adjustment range is calculated based on the average temperature data and the preset target temperature range.

[0055] Temperature regulation range refers to the permissible temperature range or variation range when adjusting the temperature in a temperature control system. It represents the acceptable deviation range between the set temperature and the actual temperature.

[0056] The temperature adjustment range can be set according to specific application needs and system requirements. A smaller temperature adjustment range means greater sensitivity to temperature changes and higher adjustment precision, suitable for scenarios with stricter temperature requirements. For example, in laboratories or precision manufacturing equipment, very precise temperature control is required, so a smaller temperature adjustment range can be set. A larger temperature adjustment range means that some temperature fluctuations or changes are allowed, suitable for scenarios with relatively relaxed temperature control requirements. For example, in some ventilation systems or comfort environment control, temperature fluctuations within a certain range are allowed to provide a more comfortable indoor environment.

[0057] In an optional implementation, calculating the temperature adjustment range based on the average temperature data and the preset target temperature range includes: The average temperature data is compared with the upper and lower limits of the preset target temperature range to obtain the comparison results. Based on the comparison results, the temperature adjustment range is determined.

[0058] Among them, the edge computing node device can pre-determine the target temperature range based on an upper limit and a lower limit, and compare the average temperature data with the upper limit and lower limit of the preset target temperature range respectively.

[0059] The comparison results include: the average temperature data is greater than the upper limit of the preset target temperature range; the average temperature data is less than the lower limit of the preset target temperature range; the average temperature data is less than the upper limit of the preset target temperature range and greater than the lower limit of the preset target temperature range.

[0060] When the comparison result shows that the average temperature data is greater than the upper limit of the preset target temperature range, it indicates that the temperature is too high and cooling control is required. In this case, a first temperature adjustment range can be determined based on the average temperature data and the upper limit of the preset target temperature range, allowing the terminal device to use the first temperature adjustment range for temperature control. When the comparison result shows that the average temperature data is less than the lower limit of the preset target temperature range, it indicates that the temperature is too low and heating control is required. In this case, a second temperature adjustment range can be determined based on the average temperature data and the lower limit of the preset target temperature range, allowing the terminal device to use the second temperature adjustment range for temperature control. When the comparison result shows that the average temperature data is less than the upper limit of the preset target temperature range but greater than the lower limit of the preset target temperature range, it indicates that the average temperature data is within the target temperature range, requiring neither cooling nor heating control. In this case, a third temperature adjustment range can be determined, for example, an adjustment range of 0°C.

[0061] In an optional implementation, determining the first temperature adjustment range based on the average temperature data and the upper limit of the preset target temperature range includes: Calculate the first difference between the mean temperature data and the upper limit of the preset target temperature range; Calculate the second difference between the mean temperature data and the temperature reference value; Calculate the first ratio between the first difference and the second difference; The first temperature adjustment range is determined based on the first ratio and the preset first adjustment coefficient.

[0062] The temperature reference value is the average of the upper and lower limits of the preset target temperature range.

[0063] Edge computing node devices can be pre-set with a first adjustment coefficient. When the average temperature data is greater than the upper limit of the preset target temperature range, the preset first adjustment coefficient is automatically selected for calculation to determine the first temperature adjustment range.

[0064] For example, assuming the preset target temperature range is [18°C, 36°C], the upper limit is 36°C, and the temperature reference value is 27°C. Further assuming a preset first adjustment coefficient of 0.5, and an average temperature of 40°C, the first difference between the average temperature of 40°C and the upper limit of 35°C is calculated to be 4°C. The second difference between the average temperature of 40°C and the temperature reference value of 27°C is calculated to be 13°C. The first ratio between the first difference of 4°C and the second difference of 13°C is calculated to be 4 / 13. Based on the first ratio 4 / 13 and the preset first adjustment coefficient of 10, the first temperature adjustment amplitude is determined to be approximately 3. That is, the temperature decreases by 3°C each time the terminal device is adjusted.

[0065] In an optional implementation, determining the second temperature adjustment range based on the average temperature data and the lower limit of the preset target temperature range includes: Calculate the third difference between the lower limit of the preset target temperature range and the mean temperature data; Calculate the fourth difference between the temperature baseline value and the mean temperature data; Calculate the second ratio between the third difference and the fourth difference; The second temperature adjustment range is determined based on the second ratio and the preset second adjustment coefficient.

[0066] Edge computing node devices can be pre-set with a second adjustment coefficient. When the average temperature data is less than the lower limit of the preset target temperature range, the preset second adjustment coefficient is automatically selected for calculation to determine the second temperature adjustment range.

[0067] For example, assuming the preset target temperature range is [18°C, 36°C], the lower limit is 18°C, and the temperature reference value is 27°C. Further assuming a preset second adjustment coefficient of 10 and an average temperature of 15°C, the third difference between the lower limit (18°C) and the average temperature (15°C) is calculated to be 3°C. The fourth difference between the temperature reference value (27°C) and the average temperature (15°C) is calculated to be 12°C. The second ratio between the third difference (3°C) and the fourth difference (12°C) is calculated to be 1 / 4. Based on the first ratio 1 / 4 and the preset second adjustment coefficient of 10, the second temperature adjustment range is determined to be 2.5. That is, the temperature increases by 2.5°C each time the terminal device is adjusted.

[0068] The preset first adjustment coefficient can be the same as or different from the preset second adjustment coefficient, and can be set and adjusted according to specific application needs and system requirements. For example, when the average temperature data is greater than the upper limit of the preset target temperature range, a larger preset first adjustment coefficient can be set when storing fresh milk, since fresh milk requires a low-temperature environment. This means that the temperature can be lowered more significantly each time, thus quickly reducing the temperature to the preset target temperature range. Conversely, when the average temperature data is greater than the upper limit of the preset target temperature range, but in a densely populated environment, a smaller preset first adjustment coefficient can be set. This means that the temperature can be lowered less significantly each time, thus gradually reducing the temperature to the preset target temperature range, allowing people to gradually adapt to environmental changes.

[0069] S134, Generate the temperature regulation strategy based on the temperature regulation cycle and the temperature regulation amplitude.

[0070] For example, assuming the temperature changes rapidly and the corresponding temperature adjustment cycle is once every 10 minutes, with a temperature adjustment range of 4.5°C, the generated temperature adjustment strategy is: decrease the temperature by 4.5°C every 10 minutes until the temperature is within the preset target temperature range.

[0071] The generated temperature regulation strategy can include the temperature regulation period, the temperature regulation range, and whether the temperature is increased or decreased. This strategy allows control of the terminal device, adjusting the temperature range upwards or downwards at regular intervals. This enables phased temperature control of the terminal device, resulting in better stability of the ambient temperature. Sudden temperature changes can lead to instability in the control system, even causing temperature fluctuations or oscillations. Gradual temperature adjustments reduce the risk of system instability and ensure stable temperature control.

[0072] In some embodiments, after the terminal device implements temperature control according to the temperature control command, the temperature adjustment result executed by the terminal device according to the temperature control command can be fed back to the cloud server through the edge computing node device. This allows the cloud server to update the intelligent decision-making model and temperature adjustment strategy based on the temperature adjustment result of the terminal device, forming a closed-loop feedback and further optimizing the effect of cloud-edge collaboration between the cloud server and the edge computing node device. This collaborative mode can fully utilize the elasticity and high-performance characteristics of cloud computing, while providing real-time computing and decision-making capabilities at the edge, thereby enabling real-time temperature control.

[0073] Through the aforementioned optional implementation methods, by moving computing and data processing functions closer to the terminal device, and using intelligent decision-making models to generate temperature regulation strategies locally on the edge computing node device, the terminal device is controlled to adjust the temperature based on these strategies. This reduces data transmission latency, improves the speed and efficiency of temperature response, and enables more comprehensive and precise temperature control. Furthermore, it reduces the frequent communication requirements with the cloud server, thereby saving bandwidth resources and lowering data transmission costs.

[0074] See Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an edge computing node device shown in an embodiment of this application. In a preferred embodiment of this application, the edge computing node device 3 includes a memory 31, at least one processor 32, and at least one communication bus 33.

[0075] Those skilled in the art should understand that Figure 3 The structure of the edge computing node device shown does not constitute a limitation of the embodiments of this application. It can be a bus structure or a star structure. The edge computing node device 3 may also include more or fewer other hardware or software than shown, or different component arrangements.

[0076] In some embodiments, the edge computing node device 3 is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors, and embedded devices.

[0077] It should be noted that the edge computing node device 3 is only an example. Other existing or future products that are suitable for this application should also be included within the scope of protection of this application and are incorporated herein by reference.

[0078] In some embodiments, the memory 31 stores a computer program that, when executed by the at least one processor 32, implements all or part of the steps in the edge computing-based temperature control method described above. The memory 31 includes read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data. Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area. The stored program area may store the operating system, applications required for at least one function, etc.; the stored data area may store data created based on the use of blockchain nodes, etc. The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. A blockchain is essentially a decentralized database, a chain of data blocks linked using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain may include a blockchain underlying platform, a platform product service layer, and an application service layer, etc.

[0079] In some embodiments, the at least one processor 32 is the control unit of the edge computing node device 3, connecting various components of the edge computing node device 3 via various interfaces and lines. It executes programs or modules stored in the memory 31 and calls data stored in the memory 31 to perform various functions and process data of the edge computing node device 3. For example, when the at least one processor 32 executes a computer program stored in the memory, it implements all or part of the steps of the edge computing-based temperature control method described in this embodiment. The at least one processor 32 may be composed of integrated circuits, such as a single-packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips.

[0080] In some embodiments, the at least one communication bus 33 is configured to enable communication between the memory 31 and the at least one processor 32, etc. Although not shown, the edge computing node device 3 may also include a power supply (e.g., a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 32 via a power management device, thereby enabling functions such as charging, discharging, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The edge computing node device 3 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0081] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause an edge computing node device (which may be an edge server, gateway device, or network device, etc.) or processor to execute portions of the methods described in the various embodiments of this application.

[0082] This application embodiment also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements a temperature control method based on edge computing, the method comprising: Initial data of the environment of the terminal device is collected every preset collection period for a specified duration; Obtain the target data from the initial data of the specified duration; A temperature regulation strategy is generated based on the target data using an intelligent decision-making model obtained from a cloud server. A temperature control command carrying the temperature regulation strategy is sent to the terminal device, so that the terminal device performs temperature regulation according to the temperature control command.

[0083] In one optional implementation, the initial data includes temperature data and multiple types of environmental data, and the computer program, when executed by a processor, implements the acquisition of target data from the initial data for a specified duration, including: Calculate the mean environmental data for each type of environmental data for the specified duration; Calculate the mean temperature data of the temperature data for the specified duration; Calculate the correlation coefficient between the mean environmental data and the mean temperature data for each type; Determine a target correlation coefficient that is greater than a preset correlation coefficient threshold from among the multiple correlation coefficients; The temperature data for the specified duration and the environmental data corresponding to the target correlation coefficient are determined as the target data.

[0084] In an optional implementation, when the computer program is executed by a processor, it implements the generation of a temperature regulation strategy based on the target data using an intelligent decision-making model obtained from a cloud server, including: The intelligent decision-making model is used to predict temperature change trends based on the target data. The temperature adjustment cycle is determined based on the temperature change trend. The temperature adjustment range is calculated based on the average temperature data and the preset target temperature range. The temperature regulation strategy is generated based on the temperature regulation cycle and the temperature regulation amplitude.

[0085] In an optional implementation, when the computer program is executed by the processor, it calculates the temperature adjustment range based on the average temperature data and the preset target temperature range, including: The average temperature data is compared with the upper and lower limits of the preset target temperature range to obtain the comparison results. Based on the comparison results, the temperature adjustment range is determined.

[0086] In an optional implementation, when the computer program is executed by a processor, it implements the step of determining the temperature adjustment range based on the comparison result, including: When the comparison result is that the average temperature data is greater than the upper limit of the preset target temperature range, the first temperature adjustment range is determined based on the average temperature data and the upper limit of the preset target temperature range. When the comparison result is that the average temperature data is less than the lower limit of the preset target temperature range, the second temperature adjustment range is determined based on the average temperature data and the lower limit of the preset target temperature range. When the comparison result is that the average temperature data is less than the upper limit of the preset target temperature range and greater than the lower limit of the preset target temperature range, a third temperature adjustment range is determined.

[0087] In an optional implementation, when the computer program is executed by the processor, it implements the step of determining the first temperature adjustment range based on the average temperature data and the upper limit of the preset target temperature range, including: Calculate the first difference between the mean temperature data and the upper limit of the preset target temperature range; Calculate the second difference between the mean temperature data and the temperature reference value, where the temperature reference value is the average of the upper and lower limits of the preset target temperature range; Calculate the first ratio between the first difference and the second difference; The first temperature adjustment range is determined based on the first ratio and the preset first adjustment coefficient.

[0088] In an optional implementation, when the computer program is executed by a processor, it determines the second temperature adjustment range based on the average temperature data and the lower limit of the preset target temperature range, including: Calculate the third difference between the lower limit of the preset target temperature range and the mean temperature data; Calculate the fourth difference between the temperature baseline value and the mean temperature data; Calculate the second ratio between the third difference and the fourth difference; The second temperature adjustment range is determined based on the second ratio and the preset second adjustment coefficient.

[0089] In an optional implementation, the computer program, when executed by a processor, further implements: Determine whether there is any abnormal temperature data in the temperature data for the specified duration; When it is determined that there is abnormal temperature data in the temperature data for the specified duration, the target alarm method is determined according to the abnormal temperature data and the preset temperature threshold segmentation interval, and an alarm is triggered according to the target alarm method. The preset temperature threshold segmentation range includes multiple temperature threshold ranges, and each temperature threshold range corresponds to an alarm mode.

[0090] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A temperature control method based on edge computing, characterized in that, When applied to edge computing node devices, the method includes: Initial data of the environment in which the terminal device is located is collected every preset collection cycle for a specified duration. The initial data includes temperature data and multiple types of environmental data. Obtaining target data from initial data of the specified duration includes: Calculate the mean environmental data for each type of environmental data for the specified duration; Calculate the mean temperature data of the temperature data for the specified duration; Calculate the correlation coefficient between the mean environmental data and the mean temperature data for each type; Determine a target correlation coefficient that is greater than a preset correlation coefficient threshold from among the multiple correlation coefficients; The temperature data for the specified duration and the environmental data corresponding to the target correlation coefficient are determined as the target data; Using an intelligent decision-making model obtained from a cloud server, a temperature regulation strategy is generated based on the target data, including: The intelligent decision-making model is used to predict temperature change trends based on the target data. The temperature adjustment cycle is determined based on the temperature change trend. The temperature adjustment range is calculated based on the average temperature data and the preset target temperature range. The temperature regulation strategy is generated based on the temperature regulation cycle and the temperature regulation amplitude. A temperature control command carrying the temperature regulation strategy is sent to the terminal device, so that the terminal device performs temperature regulation according to the temperature control command.

2. The method according to claim 1, characterized in that, The calculation of the temperature adjustment range based on the average temperature data and the preset target temperature range includes: The average temperature data is compared with the upper and lower limits of the preset target temperature range to obtain the comparison results. Based on the comparison results, the temperature adjustment range is determined.

3. The method according to claim 2, characterized in that, Determining the temperature adjustment range based on the comparison results includes: When the comparison result is that the average temperature data is greater than the upper limit of the preset target temperature range, the first temperature adjustment range is determined based on the average temperature data and the upper limit of the preset target temperature range. When the comparison result is that the average temperature data is less than the lower limit of the preset target temperature range, the second temperature adjustment range is determined based on the average temperature data and the lower limit of the preset target temperature range. When the comparison result is that the average temperature data is less than the upper limit of the preset target temperature range and greater than the lower limit of the preset target temperature range, a third temperature adjustment range is determined.

4. The method according to claim 3, characterized in that, Determining the first temperature adjustment range based on the average temperature data and the upper limit of the preset target temperature range includes: Calculate the first difference between the mean temperature data and the upper limit of the preset target temperature range; Calculate the second difference between the mean temperature data and the temperature reference value, where the temperature reference value is the average of the upper and lower limits of the preset target temperature range; Calculate the first ratio between the first difference and the second difference; The first temperature adjustment range is determined based on the first ratio and the preset first adjustment coefficient.

5. The method according to claim 3 or 4, characterized in that, Determining the second temperature adjustment range based on the average temperature data and the lower limit of the preset target temperature range includes: Calculate the third difference between the lower limit of the preset target temperature range and the mean temperature data; Calculate the fourth difference between the temperature baseline value and the mean temperature data; Calculate the second ratio between the third difference and the fourth difference; The second temperature adjustment range is determined based on the second ratio and the preset second adjustment coefficient.

6. The method according to claim 1, characterized in that, The method further includes: Determine whether there is any abnormal temperature data in the temperature data for the specified duration; When it is determined that there is abnormal temperature data in the temperature data for the specified duration, the target alarm method is determined according to the abnormal temperature data and the preset temperature threshold segmentation interval, and an alarm is triggered according to the target alarm method. The preset temperature threshold segmentation range includes multiple temperature threshold ranges, and each temperature threshold range corresponds to an alarm mode.

7. An edge computing node device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the edge computing-based temperature control method according to any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the edge computing-based temperature control method according to any one of claims 1 to 6.

Images