A method and system for dynamic energy consumption adjustment of smart devices based on a smart gateway

Abstract

This invention discloses a method and system for dynamic energy consumption adjustment of smart devices based on a smart gateway. The method includes the following steps: S1: Data acquisition and synchronization: The network link parameter monitoring module collects device operating status data and environmental data from the smart device layer in real time. After verifying the validity of the data, it transmits it to the smart gateway for spatiotemporal alignment. This invention introduces a smart gateway as a control hub, combining edge computing, AI prediction, and device collaboration mechanisms to construct a multi-module linked dynamic energy consumption adjustment system. It can dynamically adjust device operating parameters based on environmental conditions, device collaboration relationships, and prediction results, avoiding high-power operation in low-risk scenarios and achieving system-level energy saving. At the same time, it extends the battery life of battery-powered devices and reduces maintenance costs. The system supports unified scheduling of multiple types of smart devices, adapting to various scenarios such as homes and businesses, and core decisions are completed locally, protecting user privacy and security.

Description

Technical Field

[0001] This invention relates to the fields of smart home and Internet of Things (IoT) technology, and in particular to a method and system for dynamic energy consumption adjustment of smart devices based on a smart gateway. Background Technology

[0002] With the rapid development of IoT and smart home technologies, a large number of smart devices have been gradually deployed in home and commercial settings, including gas detectors, air quality detectors, smart curtains, smart door locks, home appliances, audio-visual equipment, and energy management equipment. These devices typically use smart gateways as the control hub to achieve unified access, management, and linkage control.

[0003] However, existing smart devices generally operate in a fixed mode with fixed operating frequency, fixed sampling strategy, and fixed communication cycle in terms of energy consumption management. That is, regardless of changes in external environmental conditions, device collaboration relationships, or security risk levels, the device always maintains a preset power consumption level. This approach has the following shortcomings: 1. Serious energy waste: Even in environments with stable conditions and low safety risks, the equipment still maintains high-frequency sampling and communication, resulting in unnecessary energy consumption; 2. Limited device battery life: For battery-powered smart devices, the fixed power consumption mode will significantly shorten the battery life cycle and increase the device maintenance cost; 3. Lack of collaborative optimization: Different smart devices operate independently without a system-level energy consumption coordination and adjustment mechanism, making it impossible to maximize overall energy-saving benefits; 4. Insufficient adaptability: It lacks the ability to adapt energy consumption adjustment based on environmental changes, equipment linkage relationships and prediction results, making it difficult to adapt to diverse usage scenarios and changing needs.

[0004] In summary, this application proposes a method and system for dynamic energy consumption adjustment of smart devices based on a smart gateway. Summary of the Invention

[0005] Based on the technical problems existing in the background technology, the present invention proposes a method and system for dynamic adjustment of energy consumption of smart devices based on a smart gateway.

[0006] This invention proposes a method for dynamically adjusting the energy consumption of smart devices based on a smart gateway, comprising the following steps: S1: Data Acquisition and Synchronization: The network link parameter monitoring module collects device operation status data and environmental data from the smart device layer in real time. After completing the data validity verification, it transmits the data to the smart gateway for spatiotemporal alignment. S2: Device Collaboration Relationship Analysis: The data analysis module receives data synchronized from the smart gateway, sorts out the linkage logic and relationship between various devices, clarifies the device collaborative working scenario, and outputs the analysis results to the edge energy consumption prediction and scheduling module. S3: Demand and Risk Prediction: The edge energy consumption prediction and scheduling module calls the locally deployed AI prediction model and combines it with the optimization parameters issued by the cloud AI model training platform to predict the trend of environmental change and the characteristics of energy consumption change, and output the "perceived demand level" and "safety risk level" for a period of time in the future. S4: Strategy Generation and Judgment: The strategy generation module receives the prediction results from the edge energy consumption prediction and scheduling module, determines whether each device needs to maintain or increase its high-intensity operation, and generates corresponding energy consumption adjustment strategies. S5: Strategy Distribution and Execution: The smart gateway distributes the energy consumption adjustment strategies generated by the strategy generation module to the corresponding smart devices. After receiving the instructions, the smart devices automatically adjust their working parameters and execute the adjusted power consumption operation mode. S6: Feedback and Dynamic Adjustment: The transmission feedback module collects the execution feedback data of the smart device in real time and feeds it back to the dynamic adjustment module; the dynamic adjustment module combines the feedback data with the user's manual feedback to adjust the weights of the comprehensive evaluation model and optimize the subsequent adjustment strategy; at the same time, the edge energy consumption prediction and scheduling module continuously corrects the prediction model based on the feedback data. S7: Model Iteration and Optimization: The cloud-based AI model training platform regularly aggregates anonymized data uploaded by various smart gateways, iterates and optimizes the AI ​​prediction model, and distributes the optimized model parameters to each smart gateway to achieve continuous iteration of "local decision-making - cloud optimization".

[0007] Preferably, in step S4, when determining whether each device needs to maintain or increase its high-intensity operating state, if it is determined to be high safety risk or high perception demand, an adjustment strategy of "maintaining or increasing the operating frequency, sampling frequency or operating power" is generated; if it is determined to be low safety risk and low perception demand, an adjustment strategy of "reducing the sampling frequency, communication frequency or operating power" is generated.

[0008] Preferably, in step S1, the data collected by the network link parameter monitoring module includes, but is not limited to, device operating mode, current power consumption, operating parameters, indoor temperature and humidity, door and window opening and closing status, and outdoor meteorological data. The data validity verification includes, but is not limited to, whether the detection data is within a reasonable physical range and whether the device is offline.

[0009] Preferably, in S3, the AI ​​prediction model adopts either LSTM or Transformer time series model, and the prediction dimensions include environmental change trends, energy consumption change characteristics, perception demand level, and safety risk level.

[0010] Preferably, the high-safety-risk scenarios include, but are not limited to, the risk of gas leakage when doors and windows are closed, and the monitoring of sudden changes in outdoor air quality; the low-safety-risk scenarios include, but are not limited to, gas monitoring when doors and windows are open, and pollution monitoring under long-term good air quality.

[0011] Preferably, in step S6, users submit manual feedback through the feedback interface provided by the device, and the dynamic adjustment module adjusts the weights of the corresponding network parameters appropriately based on the user feedback, so that the adjustment strategy is more in line with the user's usage habits.

[0012] This invention also proposes a smart device energy consumption dynamic adjustment system based on a smart gateway, including a smart device layer, a smart gateway, a network link parameter monitoring module, a data analysis module, an edge energy consumption prediction and scheduling module, a strategy generation module, a dynamic adjustment module, a transmission feedback module, and a cloud-based AI model training platform.

[0013] Preferably, the intelligent device layer includes multiple types of intelligent devices with adjustable power consumption, including but not limited to sensing devices, execution and control devices, home appliances, audio-visual entertainment devices and energy management devices. All devices support parameter adjustment of working mode, sampling frequency, communication frequency or operating power. The intelligent gateway serves as the device access and scheduling hub, responsible for connecting to all devices in the intelligent device layer, receiving device status data and environmental data, executing energy consumption adjustment commands issued by the strategy generation module, and achieving unified scheduling. The network link parameter monitoring module is used to collect device operation status data and environmental data of the intelligent device layer in real time, and to complete the data validity verification. The data analysis module is used to classify and process the collected data, sort out the linkage logic and correlation between various devices, and clarify the collaborative working scenarios of the devices.

[0014] Preferably, the edge energy consumption prediction and scheduling module is deployed locally on the smart gateway, calls the AI ​​prediction model, and combines the optimization parameters sent from the cloud to predict the energy consumption change trend, perception demand level and security risk level in the future period of time; The strategy generation module is used to generate personalized energy consumption adjustment strategies for each smart device based on the prediction results of the edge energy consumption prediction and scheduling module and in combination with preset rules. The dynamic adjustment module is used to dynamically adjust the weights of the comprehensive evaluation model based on the real-time status changes fed back by the network link parameter monitoring module and user feedback information, thereby optimizing the energy consumption regulation strategy. The transmission feedback module is used to receive instruction execution feedback data from the smart device in real time, and to feed back the device operating status change information to the edge energy consumption prediction and scheduling module to form a closed-loop control. The cloud-based AI model training platform is used to aggregate anonymized data from multiple scenarios, train and optimize energy consumption and environmental prediction models, and periodically send updated model parameters to the smart gateway to ensure prediction accuracy.

[0015] Compared with existing technologies, the beneficial effects of this invention are: 1. By introducing a smart gateway as the control center and combining edge computing, AI prediction and device collaboration mechanisms, a multi-module linkage dynamic energy consumption adjustment system was constructed. It can dynamically adjust the device operating parameters based on environmental conditions, device collaboration relationships and prediction results, avoid high power consumption operation in low-risk scenarios, realize dynamic adaptive adjustment of smart device energy consumption, significantly reduce overall energy consumption, extend device battery life, reduce maintenance costs, and achieve system-level energy saving while ensuring the normal functioning of the device. 2. The system supports unified scheduling of multiple types of smart devices, adapts to various scenarios such as home and business, and completes core decisions locally, protecting user privacy and security, and has strong practicality and promotional value. 3. Through user feedback and cloud-based iterative optimization, the adjustment strategy is made more in line with actual usage needs, and has a wide range of application scenarios and promotional value.

[0016] This invention introduces a smart gateway as the control center, combining edge computing, AI prediction, and device collaboration mechanisms to construct a multi-module linked dynamic energy consumption adjustment system. This system can dynamically adjust device operating parameters based on environmental conditions, device collaboration relationships, and prediction results, avoiding high-power operation in low-risk scenarios and achieving system-level energy saving. Simultaneously, it extends the battery life of battery-powered devices and reduces maintenance costs. The system supports unified scheduling of multiple types of smart devices, adapting to various scenarios such as homes and businesses. Core decisions are made locally, protecting user privacy and security. Through user feedback and cloud-based iterative optimization, the adjustment strategy becomes more aligned with actual usage needs, making it suitable for a wide range of applications and promotional value. Attached Figure Description

[0017] Figure 1 This is a system block diagram of a smart device energy consumption dynamic adjustment system based on a smart gateway proposed in this invention; Figure 2 This is a flowchart of a method for dynamically adjusting the energy consumption of smart devices based on a smart gateway, as proposed in this invention. Detailed Implementation

[0018] The present invention will be further explained below with reference to specific embodiments. Example

[0019] Reference Figure 2 This embodiment proposes a method for dynamically adjusting the energy consumption of smart devices based on a smart gateway, including the following steps: S1: Data Acquisition and Synchronization: The network link parameter monitoring module collects device operation status data and environmental data from the smart device layer in real time. After completing the data validity verification, it transmits the data to the smart gateway for spatiotemporal alignment. The network link parameter monitoring module collects data including but not limited to device operating mode, current power consumption, operating parameters, indoor temperature and humidity, door and window opening and closing status, and outdoor weather data. Data validity verification includes but is not limited to whether the detection data is within a reasonable physical range and whether the device is offline. S2: Device Collaboration Relationship Analysis: The data analysis module receives data synchronized from the smart gateway, sorts out the linkage logic and relationship between various devices, clarifies the device collaborative working scenario, and outputs the analysis results to the edge energy consumption prediction and scheduling module. S3: Demand and Risk Prediction: The edge energy consumption prediction and scheduling module calls the locally deployed AI prediction model and combines it with the optimization parameters issued by the cloud AI model training platform to predict the trend of environmental change and the characteristics of energy consumption change, and output the "perceived demand level" and "safety risk level" for a period of time in the future. The predicted output for the future period is preferably the air quality trend and gas leak risk for the next two hours. The AI ​​prediction model uses either LSTM or Transformer time series model, and the prediction dimensions include environmental change trends, energy consumption change characteristics, perception demand level and safety risk level. S4: Strategy Generation and Judgment: The strategy generation module receives the prediction results from the edge energy consumption prediction and scheduling module, determines whether each device needs to maintain or increase its high-intensity operation, and generates corresponding energy consumption adjustment strategies. When determining whether each device needs to maintain or increase its high-intensity operating state, if it is determined to be high safety risk or high perception demand, an adjustment strategy of "maintaining or increasing the operating frequency, sampling frequency or operating power" is generated; if it is determined to be low safety risk and low perception demand, an adjustment strategy of "reducing the sampling frequency, communication frequency or operating power" is generated. High-safety-risk scenarios include, but are not limited to, gas leakage risk when doors and windows are closed, and monitoring when outdoor air quality changes abruptly; low-safety-risk scenarios include, but are not limited to, gas monitoring when doors and windows are open, and pollution monitoring under long-term good air quality. Specifically, during high-safety-risk scenarios, an adjustment strategy is generated that "the gas detector reports every 10 seconds and the air purifier's operating power is adjusted to high" is generated, while during low-safety-risk scenarios, an adjustment strategy is generated that "the gas detector's reporting frequency is adjusted from once every 10 seconds to once every 60 seconds and the air purifier's operating power is reduced to medium". S5: Strategy Distribution and Execution: The smart gateway distributes the energy consumption adjustment strategies generated by the strategy generation module to the corresponding smart devices. After receiving the instructions, the smart devices automatically adjust their working parameters and execute the adjusted power consumption operation mode. S6: Feedback and Dynamic Adjustment: The transmission feedback module collects the execution feedback data of the smart device in real time and feeds it back to the dynamic adjustment module; the dynamic adjustment module combines the feedback data with the user's manual feedback to adjust the weights of the comprehensive evaluation model and optimize the subsequent adjustment strategy; at the same time, the edge energy consumption prediction and scheduling module continuously corrects the prediction model based on the feedback data. The modified prediction model is as follows: if a user indicates through the feedback interface that "the air purifier's fan speed is insufficient", the dynamic adjustment module will increase the weight of the air purifier's "operating power" parameter and generate an optimization strategy of "adjusting the air purifier's operating power to a medium-high level". User feedback is submitted manually through the feedback interface provided by the device. The dynamic adjustment module adjusts the weights of the corresponding network parameters appropriately based on user feedback, making the adjustment strategy more in line with user habits. S7: Model Iteration and Optimization: The cloud-based AI model training platform regularly aggregates anonymized data uploaded by various smart gateways, iteratively optimizes the AI ​​prediction model, and distributes the optimized model parameters to each smart gateway to achieve continuous iteration of "local decision-making - cloud optimization" to improve prediction accuracy.

[0020] The method for dynamic energy consumption adjustment of smart devices based on smart gateways supports collaborative energy saving in multiple scenarios, including the following examples: Gas detectors work in tandem with smart curtains: the gas detector reduces its reporting frequency when the window is open, and automatically resumes high-frequency detection when the window is closed or at night; Air quality detectors work in conjunction with meteorological data: reduce sampling frequency when air quality is predicted to be consistently good, and restore high-frequency monitoring when the trend is abnormal; Multi-device integrated scheduling: Reduce the network heartbeat frequency of smart door locks when no one is around at night, and reduce the operating power of air purifiers when the air quality is consistently good.

[0021] Reference Figure 1 The present invention also proposes a smart device energy consumption dynamic adjustment system based on a smart gateway, including a smart device layer, a smart gateway, a network link parameter monitoring module, a data analysis module, an edge energy consumption prediction and scheduling module, a strategy generation module, a dynamic adjustment module, a transmission feedback module, and a cloud AI model training platform; The smart device layer includes various types of smart devices with adjustable power consumption, including but not limited to sensing devices, execution and control devices, home appliances, audio-visual entertainment devices, and energy management devices. All devices support the adjustment of parameters such as working mode, sampling frequency, communication frequency, or operating power. The smart gateway serves as the central hub for device access and scheduling, responsible for connecting to all devices in the smart device layer, receiving device status data and environmental data, executing energy consumption adjustment commands issued by the policy generation module, and achieving unified scheduling. The network link parameter monitoring module is used to collect real-time device operation status data (such as working mode, current power consumption, and operating parameters) and environmental data (such as indoor temperature and humidity, door and window opening and closing status, and outdoor weather data) from the smart device layer, and to perform data validity verification. The data analysis module is used to classify and process the collected data, sort out the linkage logic and relationship between various devices, and clarify the collaborative working scenarios of the devices; The edge energy consumption prediction and scheduling module is deployed locally on the smart gateway. It calls the AI ​​prediction model and combines the optimization parameters issued by the cloud to predict the energy consumption trend, perceived demand level and security risk level in the future. The strategy generation module is used to generate personalized energy consumption adjustment strategies for each smart device based on the prediction results of the edge energy consumption prediction and scheduling module and in combination with preset rules. The dynamic adjustment module is used to dynamically adjust the weights of the comprehensive evaluation model based on real-time status changes reported by the network link parameter monitoring module and user feedback information, thereby optimizing the energy consumption regulation strategy. The transmission feedback module is used to receive instruction execution feedback data from smart devices in real time and feed back information on changes in device operating status to the edge energy consumption prediction and scheduling module to form closed-loop control. The cloud-based AI model training platform is used to aggregate anonymized data from multiple scenarios, train and optimize energy consumption and environmental prediction models, and regularly send updated model parameters to the smart gateway to ensure prediction accuracy.

[0022] This embodiment introduces a smart gateway as the control center, combining edge computing, AI prediction, and device collaboration mechanisms to construct a multi-module linked dynamic energy consumption adjustment system. This system can dynamically adjust device operating parameters based on environmental conditions, device collaboration relationships, and prediction results, avoiding high-power operation in low-risk scenarios and achieving system-level energy saving. Simultaneously, it extends the battery life of battery-powered devices and reduces maintenance costs. The system supports unified scheduling of multiple types of smart devices, adapting to various scenarios such as homes and businesses. Core decisions are made locally, protecting user privacy and security. Through user feedback and cloud-based iterative optimization, the adjustment strategy becomes more aligned with actual usage needs, making it suitable for a wide range of applications and promotional value.

[0023] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the technical scope disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for dynamically adjusting the energy consumption of intelligent devices based on a smart gateway, characterized in that, Includes the following steps: S1: Data Acquisition and Synchronization: The network link parameter monitoring module collects device operation status data and environmental data from the smart device layer in real time. After completing the data validity verification, it transmits the data to the smart gateway for spatiotemporal alignment. S2: Device Collaboration Relationship Analysis: The data analysis module receives data synchronized from the smart gateway, sorts out the linkage logic and relationship between various devices, clarifies the device collaborative working scenario, and outputs the analysis results to the edge energy consumption prediction and scheduling module. S3: Demand and Risk Prediction: The edge energy consumption prediction and scheduling module calls the locally deployed AI prediction model and combines it with the optimization parameters issued by the cloud AI model training platform to predict the trend of environmental change and the characteristics of energy consumption change, and output the "perceived demand level" and "safety risk level" for a period of time in the future. S4: Strategy Generation and Judgment: The strategy generation module receives the prediction results from the edge energy consumption prediction and scheduling module, determines whether each device needs to maintain or increase its high-intensity operation, and generates corresponding energy consumption adjustment strategies. S5: Strategy Distribution and Execution: The smart gateway distributes the energy consumption adjustment strategies generated by the strategy generation module to the corresponding smart devices. After receiving the instructions, the smart devices automatically adjust their working parameters and execute the adjusted power consumption operation mode. S6: Feedback and Dynamic Adjustment: The transmission feedback module collects the execution feedback data of the smart device in real time and feeds it back to the dynamic adjustment module; the dynamic adjustment module combines the feedback data with the user's manual feedback to adjust the weights of the comprehensive evaluation model and optimize the subsequent adjustment strategy; at the same time, the edge energy consumption prediction and scheduling module continuously corrects the prediction model based on the feedback data. S7: Model Iteration and Optimization: The cloud-based AI model training platform regularly aggregates anonymized data uploaded by various smart gateways, iteratively optimizes the AI ​​prediction model, and distributes the optimized model parameters to each smart gateway to achieve continuous iteration of "local decision-making - cloud optimization".

2. The method for dynamically adjusting the energy consumption of intelligent devices based on an intelligent gateway according to claim 1, characterized in that, In S4, when determining whether each device needs to maintain or increase its high-intensity operating state, if it is determined to be high safety risk or high perception demand, an adjustment strategy of "maintaining or increasing the operating frequency, sampling frequency or operating power" is generated; if it is determined to be low safety risk and low perception demand, an adjustment strategy of "reducing the sampling frequency, communication frequency or operating power" is generated.

3. The method for dynamically adjusting the energy consumption of intelligent devices based on an intelligent gateway according to claim 1, characterized in that, In S1, the data collected by the network link parameter monitoring module includes, but is not limited to, device operating mode, current power consumption, operating parameters, indoor temperature and humidity, door and window opening and closing status, and outdoor meteorological data. Data validity verification includes, but is not limited to, whether the detection data is within a reasonable physical range and whether the device is offline.

4. The method for dynamically adjusting the energy consumption of intelligent devices based on an intelligent gateway according to claim 1, characterized in that, In S3, the AI ​​prediction model adopts either LSTM or Transformer time series model, and the prediction dimensions include environmental change trends, energy consumption change characteristics, perception demand level and safety risk level.

5. The method for dynamically adjusting the energy consumption of intelligent devices based on an intelligent gateway according to claim 2, characterized in that, The high-risk safety scenarios include, but are not limited to, the risk of gas leakage when doors and windows are closed, and monitoring when outdoor air quality changes abruptly; the low-risk safety scenarios include, but are not limited to, gas monitoring when doors and windows are open, and pollution monitoring under long-term good air quality.

6. The method for dynamically adjusting the energy consumption of intelligent devices based on an intelligent gateway according to claim 1, characterized in that, In step S6, users submit manual feedback through the feedback interface provided by the device. The dynamic adjustment module adjusts the weights of the corresponding network parameters appropriately based on the user feedback, making the adjustment strategy more in line with user habits.

7. A smart device energy consumption dynamic adjustment system based on a smart gateway, used to implement the method described in any one of claims 1-6, characterized in that, It includes a smart device layer, a smart gateway, a network link parameter monitoring module, a data analysis module, an edge energy consumption prediction and scheduling module, a strategy generation module, a dynamic adjustment module, a transmission feedback module, and a cloud-based AI model training platform.

8. The intelligent device energy consumption dynamic adjustment system based on an intelligent gateway according to claim 7, characterized in that, The intelligent device layer includes various types of intelligent devices with adjustable power consumption, including but not limited to sensing devices, execution and control devices, home appliances, audio-visual entertainment devices, and energy management devices. All devices support parameter adjustments for working mode, sampling frequency, communication frequency, or operating power. The intelligent gateway serves as the device access and scheduling hub, responsible for connecting to all devices in the intelligent device layer, receiving device status data and environmental data, executing energy consumption adjustment commands issued by the strategy generation module, and achieving unified scheduling. The network link parameter monitoring module is used to collect device operation status data and environmental data of the intelligent device layer in real time, and to complete the data validity verification. The data analysis module is used to classify and process the collected data, sort out the linkage logic and correlation between various devices, and clarify the collaborative working scenarios of the devices.

9. The intelligent device energy consumption dynamic adjustment system based on an intelligent gateway according to claim 7, characterized in that, The edge energy consumption prediction and scheduling module is deployed locally on the smart gateway. It calls the AI ​​prediction model and combines the optimization parameters sent from the cloud to predict the energy consumption trend, perception demand level and security risk level in the future. The strategy generation module is used to generate personalized energy consumption adjustment strategies for each smart device based on the prediction results of the edge energy consumption prediction and scheduling module and in combination with preset rules. The dynamic adjustment module is used to dynamically adjust the weights of the comprehensive evaluation model based on the real-time status changes fed back by the network link parameter monitoring module and user feedback information, thereby optimizing the energy consumption regulation strategy. The transmission feedback module is used to receive instruction execution feedback data from the smart device in real time, and to feed back the device operating status change information to the edge energy consumption prediction and scheduling module to form a closed-loop control. The cloud-based AI model training platform is used to aggregate anonymized data from multiple scenarios, train and optimize energy consumption and environmental prediction models, and periodically send updated model parameters to the smart gateway to ensure prediction accuracy.

Images