Smart home equipment control system

Abstract

The invention relates to the technical field of smart home control, and discloses a smart home equipment control system, which comprises a sensor unit used for collecting environment data and outputting sensor feedback data; the equipment control unit is used for controlling the operation state of the intelligent household equipment according to the feedback data of the sensor, and the equipment control unit comprises an air conditioner controller, a humidifier controller and an illumination controller; and the fuzzy control and adaptive adjustment module is used for receiving feedback data of the sensor. By adopting the technical means of game theory optimization, multi-module cooperation, predictive control, self-adaptive adjustment, fuzzy control and the like, the cooperation efficiency and the resource utilization rate between smart home devices are remarkably improved, environment changes and user requirements can be adapted in real time, the device state can be accurately adjusted, energy waste is reduced, the comfort level and energy efficiency of the home environment are improved, and the user experience is improved. The problems of fixed rules, insufficient energy efficiency optimization, conflicts among devices and the like in the prior art are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart home control, and particularly to a smart home device control system. Background Art

[0002] With the rapid development of Internet of Things technology, smart home systems have gradually entered thousands of households. Modern home devices collect data through sensors and, in combination with a control unit, perform intelligent control on devices such as air conditioners, humidifiers, and lighting, greatly improving the convenience and comfort of home life. However, although the existing technologies perform well in some basic applications, there are still many deficiencies when facing the collaborative work of multiple devices and dynamic environmental changes, resulting in a decline in system performance and user experience.

[0003] First of all, existing smart home control systems usually rely on fixed control rules or simple feedback control algorithms, such as scenario-based or timing control. Although these methods are suitable for some static environments, they often cannot provide the optimal solution when multiple devices work together. For example, when temperature control and humidity control are carried out simultaneously, the system is unable to reasonably adjust the operating state of the devices, but may instead cause conflicts between the devices, resulting in unnecessary resource waste. Traditional methods lack flexibility and cannot dynamically adjust control strategies to meet the changes in the environment and user needs, leading to low efficiency and even affecting comfort.

[0004] Secondly, the systems of existing technologies often rely on preset rules and lack an adaptive mechanism, resulting in the system being unable to effectively adapt to the dynamic changes in the environment and user needs. For example, changes in weather, different time periods, or changes in the user's activity status will all affect the requirements of the home environment. Traditional smart home systems usually make adjustments based on a rule library or simple threshold control. When facing these dynamic changes, the system cannot respond in a timely manner, thus failing to provide the best user experience. The differences in user preferences and the diversity of environmental factors are often not fully considered.

[0005] Furthermore, there are significant deficiencies in the energy efficiency collaboration among devices in current smart home systems. Although some systems provide energy-saving modes, these energy-saving strategies are usually based on fixed rules or thresholds and lack optimization for the dynamic collaboration among devices. For devices that need to work together (such as air conditioners and humidifiers), their operating states often affect each other, but existing technologies are unable to effectively perform energy efficiency collaboration among the devices, resulting in low system efficiency. Conflicts between devices may lead to energy waste, or there may be a lack of optimal resource allocation during the adjustment process of the same device.

[0006] Finally, the control decisions in the prior art are usually generated based on simplified feedback mechanisms or static rules, lacking dynamic optimization of device states and environmental conditions. As the complexity of the home environment increases, the existing control systems fail to optimize the adjustment decisions in real time and cannot adaptively adjust according to the actual operating conditions of the devices and changes in the external environment, resulting in low energy efficiency and fluctuations in comfort. The accuracy and stability of device control are limited by rules and feedback control algorithms, and the system fails to fully utilize its due intelligent advantages.

[0007] In summary, the existing smart home systems have significant deficiencies in multi-device collaboration, dynamic environment adaptation, energy efficiency optimization, and adaptive adjustment, and cannot meet the growing demands for intelligence, personalization, and high efficiency in modern home environments. Therefore, to address the above problems, the present invention proposes a smart home device control system. Summary of the Invention

[0008] In view of the deficiencies of the prior art, the present invention provides a smart home device control system, which solves the problems of the existing smart home systems in multi-device collaboration, dynamic environment adaptation, energy efficiency optimization, and adaptive adjustment.

[0009] To achieve the above objectives, the present invention is realized through the following technical solutions: A smart home device control system includes:

[0010] A sensor unit for collecting environmental data and outputting sensor feedback data;

[0011] A device control unit for controlling the operating state of smart home devices according to the sensor feedback data, and the device control unit includes an air conditioner controller, a humidifier controller, and a lighting controller;

[0012] A fuzzy control and adaptive adjustment module for receiving the sensor feedback data, generating fuzzy inputs through a fuzzification process, inferring control instructions based on a fuzzy rule base, and adaptively adjusting the fuzzy rules according to the feedback;

[0013] A predictive control module for predicting the future operating state of the device and optimizing the control input so that the behavior of the device conforms to the predetermined objectives and meets the constraint conditions;

[0014] A device cooperation optimization module for optimizing the resource cooperation between multiple devices based on a game theory model;

[0015] A control decision and execution module for generating a final decision according to the control instructions output by the foregoing modules and transmitting it to the device control unit for execution.

[0016] Preferably, the fuzzy control and adaptive adjustment module includes:

[0017] A fuzzification unit, configured to convert the sensor feedback data into a fuzzy set;

[0018] A fuzzy inference unit, configured to perform inference on the fuzzy set based on a fuzzy rule base to generate a control instruction;

[0019] An adaptive adjustment unit, configured to adjust the fuzzy rules and membership functions according to the feedback.

[0020] Preferably, the predictive control module includes:

[0021] A state prediction unit, configured to predict the device state within a future period based on the current device state and sensor data;

[0022] An optimization unit, configured to minimize the device state error and control input by optimizing an objective function to generate a device control instruction.

[0023] Preferably, the objective function in the optimization unit is:

[0024] Minimize the sum of the device state error and control input within a future time period, and its expression is:

[0025]

[0026] Wherein, x i (t) is the state of device i at time t, x ref (t) is the desired device state, Q and R are weight matrices, respectively controlling the penalty degrees of the state error and control input, u i (t) is the control input of device i at time t, The objective of the optimization process is to minimize the control input u, u is the control input vector, N is the length of the prediction time window, is the square of the error between the device state x i (t) and the desired state x ref (t), and this error is multiplied by the weight matrix Q, is the square of the control input u i (t) at time t, multiplied by the weight matrix R.

[0027] Preferably, the device state error in the optimization unit is the difference between the device state and the desired state, and the penalty term of the control input is the change amount of the control input.

[0028] Preferably, the device cooperation optimization module includes:

[0029] A cooperative game model unit, configured to analyze the competition and cooperation relationships among devices based on a game theory model to determine an optimal cooperation strategy;

[0030] A collaborative decision-making unit for calculating the Nash equilibrium according to a game model and generating an optimal control strategy for each device.

[0031] Preferably, the control decision and execution module includes:

[0032] A decision generation unit for integrating the output results of the fuzzy control, predictive control, and device collaboration optimization module into a final control decision;

[0033] An execution unit for adjusting the operating state of the home appliances according to the generated control decision.

[0034] Preferably, the sensor unit includes:

[0035] A temperature sensor for monitoring the indoor temperature;

[0036] A humidity sensor for monitoring the indoor humidity;

[0037] A light sensor for monitoring the indoor light intensity.

[0038] Preferably, the fuzzy rule base in the fuzzy control and adaptive adjustment module includes:

[0039] A set of corresponding rules between device state conditions and control instructions, which describe the operating state of the device in the form of "if - then", and the fuzzy rules are dynamically adjusted according to the historical data of device operation and user feedback;

[0040] The dynamic adjustment of the fuzzy rules is realized by an adaptive adjustment unit, which updates the membership function parameters in the rules according to the real-time control error feedback to optimize the flexibility and accuracy of the device control strategy.

[0041] The present invention also discloses a communication method for the smart home device control system described above. The smart home device control system realizes remote communication with smart home devices through a wireless communication module and controls the devices through a mobile terminal or a voice recognition system.

[0042] The present invention provides a smart home device control system. It has the following beneficial effects:

[0043] 1. By adopting a game theory-optimized device collaboration model, the present invention achieves the optimization of the collaboration strategy among multiple devices, improves the overall resource utilization efficiency of the home system. Compared with the traditional solutions based on preset rules or single feedback control in the prior art, the traditional methods often ignore the mutual influence between devices, resulting in resource waste or device operation conflicts. Through the game theory model, the present invention can intelligently adjust the control strategy of each device in multi-device collaboration, ensure the coordination between devices, and improve the energy efficiency and operation stability of the home system.

[0044] 2. The present invention introduces a predictive control and adaptive adjustment mechanism, which can predict the device state in real time and dynamically adjust the control strategy according to the changing environmental data. Compared with the existing fixed-rule control methods, it can more flexibly adapt to environmental changes such as temperature and humidity changes and changes in user needs. Traditional systems usually rely only on scenario modes or threshold control and are difficult to cope with dynamic changes and personalized needs, resulting in insufficient comfort. The adaptive adjustment ability of the present invention enables the system to provide a better user experience in a complex home environment.

[0045] 3. The present invention adopts a technical solution combining fuzzy control and adaptive adjustment, achieving the effect of autonomous real-time optimization of control decisions. Traditional smart home systems usually lack sufficient adaptive ability and cannot perform optimized control based on real-time data and device states. Therefore, unnecessary energy waste or control errors will occur. However, the present invention can accurately adjust according to the environment and device states by fuzzifying the input data and dynamically adjusting the fuzzy rules, improving the comfort and energy-saving effect of the home environment.

[0046] 4. By integrating the control strategies of multiple modules, the present invention achieves the technical effect of significantly reducing the energy consumption of home devices. Different from the existing fixed energy-saving modes or simple energy efficiency control, in the process of device collaborative optimization, the present invention not only considers the individual needs of devices but also optimizes the interaction between devices, giving full play to the maximization of resource utilization. In practical applications, the system can accurately adjust according to the actual environment and device states, effectively reducing energy waste and ensuring the best energy efficiency of the home system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a framework diagram of the system of the present invention;

[0048] Figure 2 is a flowchart of the system of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0049] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0050] Please refer to the attached Figure 1 - attached Figure 2 , the embodiments of the present invention provide a smart home device control system, including:

[0051] A sensor unit for collecting environmental data and outputting sensor feedback data;

[0052] A device control unit for controlling the operating state of smart home devices according to the sensor feedback data. The device control unit includes an air conditioner controller, a humidifier controller, and a lighting controller;

[0053] In this embodiment, the sensor unit mainly includes a temperature sensor, a humidity sensor, and a light sensor. These sensors can collect various information of the home environment in real time and forward the data to the control system.

[0054] Temperature sensor: The temperature sensor is used to monitor the indoor temperature in real time and feedback the temperature data to the control system. According to the feedback of the temperature sensor, the system can perform environmental control. Specifically, when the temperature is too high, the control system will adjust the temperature setting of the air conditioner to lower the indoor temperature; when the temperature is too low, the control system may start the heating device to ensure a suitable temperature. The real-time feedback of temperature is crucial for adjusting the air conditioning system and heating device to ensure environmental comfort.

[0055] Humidity sensor: The humidity sensor is used to monitor the indoor humidity. Too high humidity may cause discomfort, and too low humidity will affect air quality and comfort. Through the humidity sensor, the system can monitor humidity changes and control the humidifier device according to real-time data. When the humidity is below the set value, the system will start the humidifier to increase the indoor humidity; when the humidity is above the set value, the system can reduce the working intensity of the humidifier to prevent excessive humidity.

[0056] Light sensor: The light sensor monitors the indoor light intensity. The intensity of indoor light directly affects user comfort and energy efficiency. According to the real-time collected light intensity data, the system can adjust the brightness of lighting devices. For example, the system can automatically dim the indoor lights during the day or when there is natural light, and automatically increase the light brightness at night or when the light is dim. Through the real-time data of the light sensor, the system can dynamically adjust the indoor light to achieve the dual goals of energy saving and comfort.

[0057] In this implementation, each sensor of the sensor unit can monitor and feedback the corresponding environmental data in real time. The system performs intelligent control of the environment based on the data feedback from these sensors. This intelligent adjustment is completed by the device control unit, which automatically adjusts the working states of the air conditioner, humidifier, and lighting devices according to the data feedback from the sensors.

[0058] According to the sensor feedback data, the control system optimizes the operating state of the device through a formula. Taking temperature control as an example, assume the device state is x i (t), and the desired temperature is x ref(t), the optimization goal is to make the actual temperature of the device as close as possible to the desired temperature. The specific optimization objective function can be expressed as:

[0059]

[0060] where x i (t) is the state of device i at time t, x ref (t) is the desired device state, Q and R are weight matrices that respectively control the penalty degrees of the state error and the control input, u i (t) is the control input of device i at time t, The goal of the optimization process is to minimize the control input u. u is the control input vector, N is the length of the predicted time window, is the square of the error between the device state x i (t) and the desired state x ref (t), and this error is multiplied by the weight matrix Q, is the square of the control input u i (t) at time t, multiplied by the weight matrix R.

[0061] This optimization objective function realizes the precise control of the device state and the efficient utilization of resources by minimizing the cost of the device state error and the control input.

[0062] The device control unit is responsible for adjusting the operating state of the home appliances according to the real-time data provided by the sensor unit. Specifically, the air conditioner controller adjusts the set temperature of the air conditioner according to the data provided by the temperature sensor, the humidifier controller adjusts the humidity setting according to the humidity sensor data, and the lighting controller adjusts the indoor lighting brightness according to the light sensor data. In this way, the device control unit can respond immediately according to environmental changes to ensure that the home environment is always in a comfortable state.

[0063] Specifically, the air conditioner controller adjusts the temperature setting so that the temperature matches the target temperature x ref (t) set by the user; the humidifier controller adjusts the humidity output according to the feedback of the humidity sensor to make the humidity reach the set comfortable value; the lighting controller adjusts the light brightness according to the intensity of the indoor light to optimize the environmental lighting.

[0064] During the device control process, the control system updates the control instructions in real time according to the feedback information and adjusts the device operation. In this way, the device control unit can effectively respond to different environmental conditions and user needs to ensure the comfort and energy conservation of the home environment.

[0065] The fuzzy control and adaptive adjustment module is used to receive the sensor feedback data, generate fuzzy inputs through the fuzzification process, infer control instructions based on the fuzzy rule base, and adaptively adjust the fuzzy rules according to the feedback.

[0066] In this embodiment, the fuzzy control and adaptive adjustment module includes a fuzzification unit, a fuzzy inference unit, and an adaptive adjustment unit. They work together to ensure that the system can efficiently and accurately adjust the device state under various environmental conditions.

[0067] The fuzzification unit converts the original environmental data transmitted from the sensor unit (such as temperature sensors, humidity sensors, light sensors, etc.) into fuzzy sets. In actual operation, the original data such as temperature and humidity are usually precise values, and the fuzzification process maps these precise values into fuzzy sets. For example, assuming the original data from the temperature sensor is 27°C, the system converts it into the fuzzy set of "high temperature" through the membership function, and defines the membership degrees of "low temperature", "suitable temperature", and "high temperature" according to the temperature range (such as 20 - 30°C).

[0068] The function of the fuzzy inference unit is to infer the control instructions based on the fuzzy rule base for the fuzzified input data. The fuzzy rule base generally includes a set of "if - then" form rules to describe the relationship between the device state and the control behavior. For example, the rules may be: "If the temperature is high, then the air conditioner cools" or "If the humidity is low, then start the humidifier". These rules infer the corresponding control instructions based on the current fuzzy input values. The inference process is based on the membership degrees between fuzzy sets to determine the specific actions that the device should take.

[0069] The adaptive adjustment unit adjusts the fuzzy rules and membership functions in real - time according to the control error (such as temperature error, humidity error, etc.). When there is an error between the actual state and the target state of the device (such as the air conditioner fails to adjust the temperature to the set value), the system will automatically adjust the parameters of the membership function. For example, when the system detects that the air conditioner temperature fails to meet the target, the control strategy will reset the control threshold by adjusting the membership degree of the "warm" fuzzy set in the rule to improve the response flexibility and accuracy of the system.

[0070] In this embodiment, the fuzzy rule base contains a set of corresponding rules that describe the relationship between the device operating state and the control instructions. The rules adopt the "if - then" structure, clearly defining how the device responds to different environmental changes. The following is a simplified example of the rule base:

[0071] Rule 1: If the temperature is "high temperature", then the air conditioner should "reduce the temperature";

[0072] Rule 2: If the humidity is "low humidity", then the humidifier should "increase the humidity";

[0073] Rule 3: If the light is "strong light", the illumination should be "lowered in brightness".

[0074] Rule 4: If the temperature is "low temperature", the heater should "increase the temperature".

[0075] The dynamic adjustment function of the fuzzy rules is realized by the adaptive adjustment unit. When the actual operation effect of the device fails to meet the expectation, the system adjusts the parameters of the fuzzy rules and membership functions according to the real-time control error feedback. Specifically, when the error value is greater than a certain preset threshold, the system modifies the parameters of the membership function to make the definitions of fuzzy sets such as "high temperature" or "low humidity" more sensitive, thereby improving the control accuracy.

[0076] To further illustrate the implementation of fuzzy control and adaptive adjustment, the following provides the formula derivation process and parameter definitions.

[0077] The optimization objective function is:

[0078]

[0079] where, x i (t) is the state of device i at time t, x ref (t) is the desired device state, Q and R are weight matrices that respectively control the penalty degrees of the state error and control input, u i (t) is the control input of device i at time t, The goal of the optimization process is to minimize the control input u, u is the control input vector, N is the length of the prediction time window, for the device state x i (t) and the square of the error between the desired state x ref (t), and this error is multiplied by the weight matrix Q, for the square of the control input u i (t) at time t, multiplied by the weight matrix R.

[0080] The role of the optimization objective function is to minimize the error of the device state and avoid excessive changes in the control input during this process. The device state x i (t) will try to approach the desired state x ref (t) will be maintained within a reasonable range.

[0081] Inference process and dynamic adjustment: Preliminary inference: Assume that the current temperature feedback by the temperature sensor is 27 °C, and the system fuzzifies it into the "high temperature" fuzzy set through the membership function, and the membership degree is:

[0082]

[0083] where, Thigh is the high - temperature threshold, ΔT is the temperature change range, μ high (s 1 (t)) is the output of this formula, representing the membership degree of the temperature sensor measurement value s 1 (t) belonging to the "high - temperature" fuzzy set at time t.

[0084] Control instruction generation: Based on the temperature fuzzy set and the fuzzy rule base, the inference unit generates control instructions. For example, if "high - temperature" is detected, the temperature setting of the air conditioner will be lowered. The generated control instructions will be passed to the air - conditioner controller to perform temperature adjustment. The operation max(0,...) ensures that the membership degree μ high (s 1 (t)) is not less than 0, that is, if the calculated membership degree is less than 0 (for example, when the temperature is significantly lower than the high - temperature range), then 0 is taken; if the calculation result is positive, the value is retained.

[0085] Adaptive adjustment: Assume the actual temperature is 27°C and the desired temperature is 22°C. At this time, the control error e(t)=x i (t)-x ref (t)=27°C - 22°C = 5°C. When the control error exceeds the preset threshold, the system adjusts the membership function parameters through the adaptive adjustment unit to optimize the control strategy. By adjusting the sensitivity of the membership function, the system can control the air - conditioner temperature more precisely.

[0086] The predictive control module is used to predict the future operating state of the device and optimize the control input, so that the behavior of the device conforms to the predetermined goal and meets the constraint conditions;

[0087] In this embodiment, the main function of the state prediction unit is to predict the state change of the device within a future period based on the current state x i (t) of the device and the sensor feedback data s(t). The prediction process is based on the dynamic model of the device, combined with historical data and current input, to deduce the future behavior of the device. For example, assume the current device state of the system is x ac (t) (such as the temperature state of the air conditioner), the system will combine the environmental changes to predict the change trend of the air - conditioner temperature within a future period (such as 10 minutes).

[0088] State prediction usually uses the dynamic equation of the system to model, which can be linear or non - linear, depending on the complexity of the system. For example, for an air - conditioner system, the device state prediction may adopt the following dynamic model:

[0089] x ac (t + 1)=Ax ac (t)+Bs(t);

[0090] Among them, A is the state transition matrix, B is the input matrix, and s(t) is the data feedback by the sensor (such as outdoor temperature, humidity, etc.). The task of the state prediction unit is to use these models to predict the state of the device within multiple future time steps at each moment.

[0091] Based on the state prediction, the optimization unit generates a control input to minimize the cost between the device state error and the control input. The optimization process generates an optimal control strategy by solving an optimization objective function.

[0092] The expression of the optimization objective function is:

[0093]

[0094] Among them, x i (t) is the state of device i at time t, x ref (t) is the desired device state, Q and R are weight matrices, which control the penalty degrees of the state error and the control input respectively, u i (t) is the control input of device i at time t, The goal of the optimization process is to minimize the control input u, u is the control input vector, N is the length of the prediction time window, is the square of the error between the device state x i (t) and the desired state x ref (t), and this error is multiplied by the weight matrix Q, is the square of the control input u i (t) at time t, multiplied by the weight matrix R.

[0095] Inference process of the optimization objective:

[0096] Device state error: At each time step t, the system calculates the error e(t) between the current device state and the desired state, and takes it as part of the optimization objective. The device state error is:

[0097] e(t) = x i (t) - x ref (t);

[0098] This error reflects the difference between the device and the user-set target, and the goal is to minimize this error as much as possible.

[0099] Penalty term of the control input: To avoid excessive changes in the control input, the system smooths the device control through the penalty term. For example, the greater the change in the control input, the greater the penalty the system will impose to avoid excessive fluctuations in the control input. The penalty term of the control input is: This ensures that the adjustment process of the device is not too drastic and remains within a reasonable range of change. For example, if the temperature setting of an air conditioner suddenly changes from 24°C to 18°C, the system will impose a greater penalty on this drastic change to avoid energy waste.

[0100] Objective function optimization: The system calculates the optimal control input by minimizing the state error and control input penalty terms in the objective function. The goal of the optimization process is to generate a control input u i (t) such that the device state is as close as possible to the desired state, and the change in the control input remains smooth. The optimization objective function ensures the smooth operation and efficient response of the device by balancing the device state error and control input penalty.

[0101] For example, if the desired temperature is 22°C and the current temperature of the air conditioner is 25°C, the optimization objective will calculate the optimal temperature setting value u ac (t) such that the air conditioner can smoothly adjust the temperature to the target value.

[0102] Constraint relationship of the objective function:

[0103] In practical applications, the control input and state of the device are subject to certain physical constraints. During the optimization process, it is necessary to ensure that the control input and device state are within the given physical range. For example:

[0104] The range of the temperature control input u ac (t) may be limited by the operating temperature of the air conditioner (e.g., minimum temperature 18°C, maximum temperature 30°C).

[0105] The range of the humidity control input u ac (t) may be limited by the output capacity of the humidifier.

[0106] For lighting equipment, the control input of brightness may also be physically limited by the maximum and minimum brightness.

[0107] When solving for the optimal control input, the optimization unit will consider these physical constraints. For example, the temperature setting u ac (t) of the air conditioner must satisfy 18 ≤ u ac (t) ≤ 30.

[0108] These constraint relationships can be represented by the following inequalities:

[0109] u min ≤ u i (t) ≤ u max ;

[0110] where, u min and u maxThey are the minimum and maximum values of the device control input respectively, ensuring that the device operates within a safe and efficient range.

[0111] The device cooperation optimization module is used to optimize the resource cooperation among multiple devices based on the game theory model;

[0112] In this embodiment, the device cooperation optimization module includes a cooperative game model unit and a cooperation decision unit. The two work together to analyze the interactions between devices based on the theoretical framework of game theory, and finally generate the optimal control strategies for each device.

[0113] The main function of the cooperative game model unit is to analyze the competitive and cooperative relationships among multiple devices through the game theory model. Multiple devices in the home system (such as air conditioners, humidifiers, lighting systems, etc.) may compete or affect each other in resource usage. For example, when an air conditioner and a humidifier work simultaneously, they may consume the same part of the energy, or there may be interference in adjusting the indoor temperature and humidity. Through the game theory model, this unit analyzes the interactions between these devices and determines the optimal cooperation strategy among the devices.

[0114] The basic framework of the game model is: each device makes a decision on the selection of its control strategy based on its own utility function, and at the same time needs to consider the decisions of other devices. Assume that each device i has a utility function U i , which represents the utility of this device under the decisions of other devices. The goal in game theory is to find the optimal strategy for each device so that the utility of each device is maximized considering the decisions of other devices.

[0115] For example, assume that the control strategy of device i is σ i (t), and its utility function is U i (σ 1 (t),…,σ n (t)), where U i is the utility function of the i-th device, representing the utility value obtained by device i under a specific strategy combination, and σ 1 (t),…,σ n (t) are the control strategies of n devices in the system at time t. The game model will calculate the optimal control strategy for each device so that the utility of each device is maximized given the strategies of other devices.

[0116] The main task of the cooperation decision unit is to calculate the Nash equilibrium according to the game model, and then generate the optimal control strategy for each device. The Nash equilibrium is an important concept in game theory, indicating that in a game, when the strategy selected by each participant is optimal and no participant can obtain a better result by changing their own strategy, the game reaches an equilibrium state.

[0117] In the implementation of the present invention, the collaborative decision-making unit finds a stable Nash equilibrium by solving the game model among devices and generates the optimal control strategy for each device. The core of Nash equilibrium calculation lies in finding the stable state where, under the joint action of the control strategies of all devices, each device cannot improve its utility by changing its own strategy.

[0118] Suppose the utility function of device i is U i (σ 1 (t),…,σ n (t)), where σ i (t) is the control strategy of device i at time t, and σ j (t) is the control strategies of other devices. The optimal strategy of device i satisfies the following conditions:

[0119]

[0120] That is to say, the optimal strategy of device i is the strategy that maximizes its utility function U j (t) when considering the strategies σ i of other devices fixed.

[0121] Formalization and examples of the game model:

[0122] In a home system, assume that device 1 is an air conditioner, device 2 is a humidifier, and device 3 is a lighting system. Each device hopes to maximize its own utility. The utility function of device i may be related to factors such as its operating energy consumption, user comfort, and environmental conditions. For example, the utility function of the air conditioner can be expressed as the contribution of temperature adjustment to comfort minus the cost of energy consumption; the utility function of the humidifier can be the balance between the comfort contribution of humidity adjustment and energy consumption.

[0123] Constraint relationships of the objective function:

[0124] There may be a series of constraint conditions among the devices in the game model. These constraint conditions may come from the physical limitations of the devices, energy consumption limitations, or other external constraints (such as user preferences, environmental conditions, etc.). When optimizing the game model, these constraints need to be considered to ensure that the control strategies of the devices can not only maximize the utility but also meet the constraints.

[0125] For example, the temperature setting T ac (t) of the air conditioner must be within a reasonable range:

[0126] T min ≤T ac (t)≤T max ;

[0127] Humidifier humidity setting H humid (t) also has an upper and lower limit:

[0128] H min ≤H humid (t)≤H max ;

[0129] Brightness of lighting equipment L light (t) May also be limited by maximum power and comfort requirements:

[0130] L min ≤L light (t)≤L max ;

[0131] These constraints will be incorporated into the game model to ensure that the optimal strategy for all devices not only maximizes utility but also complies with physical and external constraints.

[0132] The control decision and execution module is used to generate the final decision based on the control instructions output by the above modules and transmit it to the device control unit for execution.

[0133] In this embodiment, the control decision and execution module includes a decision generation unit and an execution unit, which work together to convert various control results in the system into specific device operations.

[0134] The main function of the decision generation unit is to integrate the output results from the fuzzy control, predictive control and equipment collaboration optimization modules to generate a comprehensive and coordinated final control decision. Specifically, the fuzzy control module provides preliminary control instructions inferred from environmental data, the predictive control module predicts the future state of the equipment and provides corresponding optimized control instructions, and the equipment collaboration optimization module optimizes the collaboration strategy between multiple devices through game theory. Based on this information, the decision generation unit will integrate the control instructions of each module to form the final equipment operation instructions.

[0135] For example, suppose the air conditioner, humidifier, and lighting system need to be adjusted simultaneously to achieve the user's comfort goal. The fuzzy control module generates control instructions for the air conditioner based on the current environmental data (such as temperature, humidity, and light intensity), the predictive control module calculates future air conditioner temperature adjustment recommendations based on the temperature prediction model, and the device collaborative optimization module ensures that the operation of the air conditioner and humidifier does not conflict. The decision generation unit integrates this information and generates a comprehensive control decision to ensure that the operating status of the equipment is consistent with user needs.

[0136] The execution unit is responsible for adjusting the operating state of home appliances according to the final control decision output by the decision-making unit. Specifically, the execution unit transmits the final control decision to the device control unit, and the device control unit adjusts the behavior of the device according to these instructions, such as changing the temperature setting of the air conditioner, adjusting the humidity output of the humidifier, or changing the brightness of the lighting system.

[0137] The task of the execution unit is to ensure that the device is adjusted according to the optimized decision, and this adjustment can be accurately and timely reflected in the device operation. For example, when the air conditioner temperature setting is adjusted to a new value, the execution unit will directly interact with the air conditioner device to ensure that the air conditioner immediately changes the temperature setting to match the new control strategy.

[0138] Suppose the user requires the system to maintain the indoor temperature at 22°C, the humidity between 40% and 60%, and the light intensity moderate in summer. The system obtains real-time data from the sensors: the current indoor temperature is 27°C, the humidity is 55%, and the light intensity is moderate. The fuzzy control module will first infer that the air conditioner needs to lower the temperature, the humidifier should maintain the current working state, and the lighting should maintain the current brightness. The predictive control module further analyzes the temperature change trend and predicts that the air conditioner may need to further cool down. The device cooperation optimization module analyzes the cooperation strategy between the air conditioner and the humidifier based on the game theory model to ensure that the operations of the two do not cause over-regulation.

[0139] Finally, the decision-making unit will form a comprehensive control instruction based on the outputs of fuzzy control, predictive control, and device cooperation optimization. After receiving this instruction, the execution unit will adjust the temperature setting of the air conditioner to ensure that the indoor temperature gradually drops to the target value, and the humidifier and lighting equipment operate stably. The adjustments of all devices are based on the comprehensive control decision, enabling the various devices to coordinate with each other to achieve the comfortable environment expected by the user.

[0140] Objective function and constraint relationships:

[0141] The generation of control decisions also needs to consider constraint conditions to ensure the stability and efficient operation of the system. The following are some possible constraint relationships:

[0142] Limitations of device control inputs: The control inputs of each device (such as temperature setting, humidity setting, etc.) are subject to physical limitations. For example, the temperature setting of the air conditioner cannot be lower than a certain minimum value or exceed a certain maximum value; the humidity setting of the humidifier has a maximum output capacity; the brightness of the lighting equipment is also limited by power.

[0143] Energy efficiency constraints: The system needs to optimize energy consumption while meeting user requirements. For example, the simultaneous operation of the air conditioner and the humidifier may result in excessive energy consumption. The system needs to maximize the energy efficiency of device cooperation while optimizing comfort.

[0144] User Preferences: The operating strategy of the device also needs to be adjusted according to the personalized needs of the user. For example, the user may prefer lower temperature or humidity, and the system needs to dynamically adjust control decisions based on these preferences.

[0145] To cooperate with the use of a smart home device control system of the present invention, this embodiment also discloses a communication method for auxiliary use of the system. The smart home device control system realizes remote communication with smart home devices through a wireless communication module, and controls the devices through a mobile terminal or a voice recognition system.

[0146] Working Principle: When the smart home device control system starts to run, it first obtains real-time data from the environment. Sensors such as temperature, humidity, and light continuously monitor the home environment, and all the collected information is transmitted to the control system. The system first performs fuzzification processing on these data, converting specific environmental parameters into fuzzy sets. For example, the temperature sensor reading is converted into a fuzzy description such as "high temperature" or "low temperature". These fuzzified input data enter the fuzzy control module, and the system makes inferences based on a series of preset rules. Through the "if-then" structure of the rule base, the system generates preliminary control instructions. These control instructions determine the preliminary operation mode of the device.

[0147] Over time, the operating status of the device and user feedback continuously affect the control strategy. The system dynamically optimizes the fuzzy rules through an adaptive adjustment mechanism. This adjustment is not fixed but relies on real-time feedback. For example, when the temperature is too high or too low, the system automatically senses and adjusts the control strategy to make the environment more in line with the user's needs. The predictive control module will predict the future behavior of the device based on the current state. Through model prediction, the system calculates the future operating status of the device and optimizes the control input according to the prediction results. The optimization goal is to minimize the device state error and control input to ensure the accuracy of device operation and energy utilization efficiency. The coordinated operation of multiple devices needs to consider their interactions. In a home environment, the operation of devices such as air conditioners, humidifiers, and lighting may affect each other. The game optimization module analyzes the competition and cooperation between devices through a game theory model. This module ensures that devices can work together to avoid resource waste and finally calculates the optimal operation strategy through game theory. After the generated control decision is processed by the control decision and execution module, the instruction is transmitted to the device control unit. The device control unit adjusts the operating status of each home device, such as adjusting the air conditioner temperature, humidifier humidity, or light brightness. The execution results of all devices are fed back into the system, and the system readjusts the control strategy according to the new environmental data. This forms a continuous feedback loop system to ensure that the system always maintains the best state in a changing environment. The system also allows users to perform remote control through a mobile terminal or a voice recognition system. The wireless communication module connects the device to the user device to provide real-time interaction and adjustment, enabling users to adjust various parameters of the home environment at any time.

[0148] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A smart home device control system, characterized in that: include: A sensor unit, used for collecting environmental data and outputting sensor feedback data; A device control unit, used to control the operating state of smart home devices according to sensor feedback data, the device control unit includes an air conditioning controller, a humidifier controller and a lighting controller; The fuzzy control and adaptive adjustment module is used to receive sensor feedback data, generate fuzzy inputs through the fuzzification process, and infer control instructions based on the fuzzy rule base, and adaptively adjust the fuzzy rules according to the feedback; Predictive control module, used to predict the future operating state of the equipment and optimize the control input so that the behavior of the equipment meets the predetermined goals and satisfies the constraints; Device collaboration optimization module, used to optimize resource collaboration among multiple devices based on game theory models; The control decision and execution module is used to generate the final decision based on the control instructions output by the above modules and transmit it to the device control unit for execution.

2. A smart home device control system according to claim 1, characterized in that: The fuzzy control and adaptive adjustment module includes: A fuzzification unit, used to convert sensor feedback data into fuzzy sets; A fuzzy reasoning unit, used to reason about fuzzy sets based on a fuzzy rule base and generate control instructions; The adaptive adjustment unit is used to adjust the fuzzy rules and membership functions according to the feedback.

3. A smart home device control system according to claim 1, characterized in that: The prediction control module comprises: A state prediction unit, used to predict the state of the device in the future based on the current device state and sensor data; The optimization unit is used to minimize the device state error and control input by optimizing the objective function and generate device control instructions.

4. A smart home device control system according to claim 3, characterized in that: The optimization objective function in the optimization unit is: In the future period, the sum of the device state error and the control input is minimized, and its expression is: Among them, x i (t) is the state of device i at time t, x ref (t) is the desired device state, Q and R are weight matrices, which control the degree of penalty for state error and control input, respectively, and u i (t) is the control input of device i at time t, The goal of the optimization process is to minimize the control input u, where u is the control input vector and N is the length of the predicted time window. is the device status x i (t) and the expected state x ref (t), and this error is multiplied by the weight matrix Q, The control input u i (t squared at time t, multiplied by the weight matrix R.

5. The smart home device control system according to claim 3, characterized in that: The device state error in the optimization unit is the difference between the device state and the expected state, and the penalty term of the control input is the change in the control input.

6. The smart home device control system according to claim 1, characterized in that: The device collaboration optimization module includes: Collaborative game model unit, used to analyze the competition and cooperation relationship between devices based on the game theory model and determine the optimal collaboration strategy; The collaborative decision-making unit is used to calculate the Nash equilibrium according to the game model and generate the optimal control strategy for each device.

7. The smart home device control system according to claim 1, characterized in that: The control decision and execution module includes: A decision generation unit, which is used to integrate the output results of the fuzzy control, predictive control and equipment collaborative optimization modules into the final control decision; The execution unit is used to adjust the operating state of the home appliance according to the generated control decision.

8. The smart home device control system according to claim 1, characterized in that: The sensor unit comprises: Temperature sensor, used to monitor indoor temperature; Humidity sensor, used to monitor indoor humidity; Light sensor, used to monitor indoor light intensity.

9. The smart home device control system according to claim 1, characterized in that: The fuzzy rule base in the fuzzy control and adaptive adjustment module includes: A set of rules for the correspondence between device status conditions and control instructions, wherein the rules describe the operating status of the device in an "if-then" form, and the fuzzy rules are dynamically adjusted according to the historical data of device operation and user feedback; The dynamic adjustment of the fuzzy rules is achieved through an adaptive adjustment unit, which updates the membership function parameters in the rules according to real-time control error feedback to optimize the flexibility and accuracy of the device control strategy.

10. A communication method for a smart home device control system according to any one of claims 1 to 9, characterized in that: The smart home device control system realizes remote communication with smart home devices through a wireless communication module, and controls the devices through a mobile terminal or a voice recognition system.

Images