Intelligent energy-saving control system of Internet of Things equipment

Abstract

The invention discloses an intelligent energy-saving control system of Internet of Things equipment, which relates to the technical field of Internet of Things and comprises an infrastructure module, a data integration module, a communication network module, a cloud platform and edge computing module, a use interface module and a system integration and test module. Wherein the data integration module is used for processing and integrating data from different sensors and actuators, and the communication network module is used for realizing communication between equipment and communication between the equipment and a cloud platform. The system can accurately identify energy-saving opportunities and optimize energy management strategies through the data fusion and analysis engine module, can continuously improve control strategies and adapt to constantly changing environments and user requirements through the self-learning control algorithm module, can reduce the maintenance cost through the predictive maintenance and fault diagnosis module, and improves the maintenance efficiency. The reliability of the equipment is improved, the service life of the equipment is prolonged, high-security communication is realized through the quantum encryption communication module, and the security of data transmission is protected.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an intelligent energy-saving control system for Internet of Things equipment. Background Art

[0002] IoT devices are physical devices that can connect to the Internet and communicate with other devices or systems through the network. Intelligent energy-saving control of IoT devices refers to the use of IoT technology to monitor and manage various devices to achieve optimal use and conservation of energy.

[0003] The existing intelligent energy-saving control system requires manual intervention to adjust the control strategy, and cannot automatically adjust according to environmental changes and user behavior, which reduces the intelligence level of the system. It also lacks a communication security mechanism and is vulnerable to network attacks and data leakage risks. In addition, when the system fails, it cannot detect and handle potential equipment failures in a timely manner. It lacks predictive maintenance and fault diagnosis functions, which increases maintenance costs and prolongs system downtime. Therefore, we propose an intelligent energy-saving control system for IoT devices to solve the above problems.

[0004] The above information disclosed in this background technology is only used to increase the understanding of the background technology of the present invention and therefore, it may include information that does not constitute the prior art known to ordinary technicians in this field. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent energy-saving control system for Internet of Things devices to solve the current market problems raised by the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent energy-saving control system for IoT devices, comprising a basic equipment module, a data integration module, a communication network module, a cloud platform and edge computing module, a user interface module, and a system integration and testing module;

[0008] The data integration module processes and integrates data from different sensors and actuators; the communication network module realizes communication between devices and between devices and the cloud platform; the cloud platform and the edge computing module store data and process complex calculations; the interface module provides an interactive interface and supports touch screen operation and voice control; the system integration and testing module is used to ensure that all parts of the system work together and conduct tests, including automated test scripts and simulation tools, to ensure the stability and reliability of the system;

[0009] It also includes an energy management optimization module, which uses linear programming and dynamic programming and implements parameter optimization based on machine learning to automatically adjust control parameters;

[0010] It also includes a security mechanism module to implement multi-level security protection, including physical security, network security and data security, regularly and automatically update system firmware to fix known security vulnerabilities, and implement intrusion detection system (IDS) and intrusion prevention system (IPS).

[0011] As a further optimization solution of the present invention, the basic equipment module includes a multifunctional intelligent sensor node module, a dynamic execution unit module, an autonomous drone monitoring system module, and a nanosensor network module;

[0012] Among them, the multifunctional intelligent sensor node module collects environmental data and performs edge computing; the dynamic execution unit module adjusts the equipment status according to the control instructions; the autonomous drone monitoring system module remotely monitors and collects data, covering large and difficult-to-reach areas. In the autonomous drone monitoring system module, an image recognition algorithm based on deep learning is added. The algorithm formula is f(x)=σ(W·x+b), where f(x) is the output of the neural network, x is the input feature, W is the weight matrix, b is the bias vector, and σ is the activation function. At the same time, a path planning algorithm based on deep learning is also added. The algorithm adopts the following formula: Where Path is the optimal path, f is the flight cost function, x i is a point on the path;

[0013] Nanosensor network modules monitor the internal status of devices and provide health and performance indicators;

[0014] The data integration module includes a data fusion and analysis engine module, a self-learning control algorithm module, and a predictive maintenance and fault diagnosis module;

[0015] The data fusion and analysis engine module processes and fuses multi-source data to optimize energy management; the self-learning control algorithm module automatically adjusts the control strategy according to user behavior and environmental patterns. In the data fusion and analysis engine module, a prediction model based on time series analysis is introduced, using the following formula y t =φ1y t-1 +φ2y t-2 +···+φ p y t-p +ε t , where y t is the energy consumption at time t, φ i is the autoregressive coefficient, p is the model order, ε t It is white noise;

[0016] The predictive maintenance and fault diagnosis module predicts equipment failures and performs maintenance in advance.

[0017] As a further optimization solution of the present invention, the communication network module includes a hybrid communication network module and a quantum encryption communication module;

[0018] The hybrid communication network module provides a data transmission network; the quantum encryption communication module protects the security of data transmission. In the quantum encryption communication module, the quantum key distribution (QKD) protocol is used, using the following formula K = H (E k (P)), where K is the key, E k is the encryption function, P is the plaintext, H is the hash function, and in the quantum encryption communication module, a quantum random number generator is used to generate the encryption key. The key generation formula is: K is the generated key, X i is the output bit of the quantum random number generator.

[0019] As a further optimization solution of the present invention, the cloud platform and edge computing module include a distributed cloud platform module and an edge computing cluster module;

[0020] Among them, the distributed cloud platform module performs distributed storage and calculation of data. In the cloud platform and edge computing modules, an anomaly detection algorithm based on machine learning is implemented for real-time monitoring and identification of system anomalies. The anomaly score is calculated using the following formula: score is the anomaly score, is the weight, x i is the eigenvalue, μ i is the average value of the feature. At the same time, a load balancing algorithm based on machine learning is implemented in the cloud platform and edge computing module to optimize the allocation of computing resources. The specific formula is as follows: Load is the optimal load distribution, L i is the load of the ith node, C i is the processing capacity of the ith node;

[0021] The edge computing cluster module processes real-time data and shares the burden of the cloud platform.

[0022] As a further optimization scheme of the present invention, the multifunctional intelligent sensor node module includes a sensor, a microcontroller, a communication interface, and a power management. In the multifunctional intelligent sensor node module, a signal denoising algorithm based on wavelet transform is added, and the algorithm formula is: where d k is the signal after wavelet transformation, x(n) is the original signal, ψ is the wavelet function, j is the scale parameter, k is the translation parameter, t k is the translation vector;

[0023] The dynamic execution unit module includes intelligent switches, regulating valves, servo motors, and actuator controllers; the autonomous drone monitoring system module includes drones, cameras, sensors, flight control systems, and data transmission devices; the nanosensor network module includes nanosensors, data transmission units, and power management.

[0024] As a further optimization scheme of the present invention, the data fusion and analysis engine module includes a data processing algorithm, a machine learning model, and an analysis tool. In the data fusion and analysis engine module, a clustering-based data analysis algorithm is introduced to identify and classify device data. The algorithm formula is: Where distance is the distance from the data point to the cluster center, x i is the data point, μ is the cluster center, and a classification algorithm based on support vector machine (SVM) is introduced to classify device data. The specific formula is: f(x) is the decision function, α i is the Lagrange multiplier, K(x,x i ) is the kernel function, b is the bias term;

[0025] The self-learning control algorithm module includes learning algorithm, decision logic, and pattern recognition; the predictive maintenance and fault diagnosis module includes fault prediction model, diagnostic tools, and maintenance suggestion generation system.

[0026] As a further optimization scheme of the present invention, the hybrid communication network module includes a wired communication device, a wireless communication device, and a network management software. In the hybrid communication network module, a traffic management algorithm based on a software defined network (SDN) is added to dynamically adjust the network traffic, specifically using the following formula: Among them, flow is the flow rate, r i is the residual bandwidth of the path, c i is the total bandwidth of the path. At the same time, in the hybrid communication network module, a routing optimization algorithm based on Markov decision process (MDP) is added, specifically,

[0027] V(s)=max a (r(s,a)+γ∑ s' P(s'|s,a)V(s')), where V(s) is the value function of state s, r(s,a) is the immediate reward of action a in state s, γ is the discount factor, and P(s'|s,a) is the transition probability from state s to state s';

[0028] The quantum encryption communication module includes quantum key distribution equipment, encryption and decryption algorithms, and security protocols.

[0029] As a further optimization scheme of the present invention, the distributed cloud platform module includes a server cluster, a storage system, and a cloud service management tool. In the distributed cloud platform module, a hash algorithm is used to implement a data storage algorithm based on blockchain, specifically H new =H old + hash(T), where H new is the new hash value, H old is the old hash value, T is the transaction data, hash is the hash function, and in the distributed cloud platform module, a distributed machine learning algorithm based on federated learning is implemented to train the global model while protecting data privacy. The specific model formula is: Where θ is the model parameter, l is the loss function, and are the features and labels of the jth sample of the i-th client, respectively;

[0030] The edge computing cluster module includes edge servers, edge storage, and edge computing software.

[0031] As a further optimization scheme of the present invention, the objective function and constraint conditions of the linear programming can be expressed as:

[0032] Minimizec c T x Subject to Ax≤b, where c is the objective function coefficient vector, x is the decision variable vector, A is the coefficient matrix, and b is the constant vector;

[0033] Implement machine learning based parameter optimization to automatically adjust control parameters by using a genetic algorithm, where the fitness function and parameter update can be expressed as, f(x)x new =x old +α·Δf(x old ), where f(x) is the fitness function, x is the parameter vector, α is the learning rate, Δf(x old ) is the gradient of the fitness function;

[0034] Implement multi-layered security, including physical security, network security, and data security, to protect the system from external attacks and internal threats. This can be achieved by using intrusion detection systems (IDS) and intrusion prevention systems (IPS), and implementing encrypted communications to ensure the security of data transmission. This can be achieved by using the Advanced Encryption Standard (AES) algorithm, where the encryption process can be expressed as,

[0035] Ciphertext = AES Key(Plaintext), where Plaintext is the original data, Key is the encryption key, and Ciphertext is the encrypted data. Digital signature is implemented to ensure the integrity and source authentication of data. This can be achieved by using the RSA signature algorithm. The signature generation and verification process can be expressed as

[0036] Signature = RSA PrivateKey (Hash(Message))Valid=RSA Public Key (Signature), where Message

[0037] is the original message, Hash is the hash function, PrivateKey and PublicKey are the private key and public key respectively, Signature is the generated signature, and Valid is the verification result

[0038] As a further optimization scheme of the present invention, in the energy management optimization algorithm, the objective function of linear programming is minimize / maximizec T x, the constraint is Ax≤b;

[0039] Among them, c is the objective function coefficient vector, x is the decision variable vector, A is the coefficient matrix, and b is the constant vector. At the same time, in the energy management optimization algorithm, a parameter optimization method based on genetic algorithm is introduced to find the optimal control parameters, specifically: Where f(x) is the fitness function, x i is a parameter, f i (x) is the fitness contribution of each parameter.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention can accurately identify energy-saving opportunities and optimize energy management strategies through the data fusion and analysis engine module. It can continuously improve the control strategy and adapt to the ever-changing environment and user needs through the self-learning control algorithm module. It can reduce maintenance costs and improve the reliability and service life of equipment through the predictive maintenance and fault diagnosis module. It can achieve highly secure communication and protect the security of data transmission through the quantum encryption communication module. Finally, through the cloud platform and edge computing module, the speed and efficiency of data processing can be improved to reduce the burden on the cloud platform.

[0042] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a block diagram of the intelligent energy-saving control system of the Internet of Things device of the present invention.

[0044] Figure 2 It is a structural schematic diagram of the basic equipment module in the present invention.

[0045] Figure 3 It is a structural schematic diagram of the data integration module in the present invention.

[0046] Figure 4 It is a structural schematic diagram of the communication network module in the present invention.

[0047] Figure 5 It is a structural diagram of the edge computing module of the cloud platform in the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Embodiment 1

[0050] See also Figure 1-Figure 5 , an intelligent energy-saving control system for IoT devices, including a basic equipment module, a data integration module, a communication network module, a cloud platform and edge computing module, a user interface module, and a system integration and testing module;

[0051] The data integration module processes and integrates data from different sensors and actuators; the communication network module realizes communication between devices and between devices and the cloud platform; the cloud platform and the edge computing module store data and process complex calculations; the interface module provides an interactive interface and supports touch screen operation and voice control; the system integration and testing module is used to ensure that all parts of the system work together and conduct tests, including automated test scripts and simulation tools, to ensure the stability and reliability of the system;

[0052] It also includes an energy management optimization module, which uses linear programming and dynamic programming and implements parameter optimization based on machine learning to automatically adjust control parameters;

[0053] It also includes a security mechanism module to implement multi-level security protection, including physical security, network security and data security, regularly and automatically update system firmware to fix known security vulnerabilities, and implement intrusion detection system (IDS) and intrusion prevention system (IPS).

[0054] The basic equipment modules include multifunctional intelligent sensor node module, dynamic execution unit module, autonomous drone monitoring system module, and nanosensor network module;

[0055] Among them, the multifunctional intelligent sensor node module collects environmental data and performs edge computing; the dynamic execution unit module adjusts the equipment status according to the control instructions; the autonomous drone monitoring system module remotely monitors and collects data, covering large and difficult-to-reach areas. In the autonomous drone monitoring system module, an image recognition algorithm based on deep learning is added to improve the accuracy and response speed of monitoring. The algorithm formula is f(x)=σ(W·x+b), where f(x) is the output of the neural network, x is the input feature, W is the weight matrix, b is the bias vector, and σ is the activation function. At the same time, a path planning algorithm based on deep learning is added. The algorithm uses the following formula: Where Path is the optimal path, f is the flight cost function, x i is a point on the path;

[0056] Nanosensor network modules monitor the internal status of devices and provide health and performance indicators.

[0057] The multifunctional intelligent sensor node module includes sensors, microcontrollers, communication interfaces, and power management; the dynamic execution unit module includes intelligent switches, regulating valves, servo motors, and actuator controllers; the autonomous UAV monitoring system module includes UAVs, cameras, sensors, flight control systems, and data transmission devices; the nanosensor network module includes nanosensors, data transmission units, and power management.

[0058] Specifically, each sensor is connected to a microcontroller, and code is written to read sensor data to implement edge computing functions including data preprocessing and preliminary analysis. The optimal value of sensor data is estimated through a Kalman filter to reduce noise interference, and the amount of data transmission is reduced through edge computing algorithms.

[0059] The formula used to predict the status is:

[0060]

[0061] in, is the predicted state, F k-1 is the state transition matrix, is the state estimate of the previous moment, B k-1 is the control matrix, is the control input.

[0062] Prediction covariance equation:

[0063]

[0064] Among them, P k∣k-1 is the predicted covariance, P k-1∣k-1 is the covariance of the previous moment, Q K-1 is the covariance of the process noise.

[0065] Update equation:

[0066]

[0067] Among them, K k is the Kalman gain, P k∣k-1 is the forecast covariance, H k is the observation matrix, R k is the covariance of the observation noise.

[0068] Furthermore, the actuator is connected to the microcontroller, the code is written to receive the control instructions, the output of the actuator is controlled by the PID control algorithm, the logic flow is designed, the control instructions and the actuator status are processed, and the control parameters are adjusted by the feedback mechanism.

[0069] In the PID control algorithm, the formula used for the proportional term is:

[0070] P=K P ·e(t)

[0071] Among them, K P is the proportional gain, and e(t) is the error at the current moment.

[0072] The formula used for the integral term is:

[0073]

[0074] Among them, K i It is the integral gain, which is the accumulation of the error signal from the beginning to the current moment.

[0075] The formula used for the differential term is:

[0076]

[0077] Among them, K d is the differential gain, which calculates the rate of change of the error signal.

[0078] The formula used to control the output is:

[0079] C=P+I+D

[0080] Where C is the output of the controller, which is used to adjust the action of the actuator.

[0081] Furthermore, we select the UAV platform, write the flight control code, implement the autonomous navigation algorithm, design the data transmission protocol, achieve stable communication between the UAV and the ground station, and reduce the amount of data transmitted by the UAV through the data compression algorithm.

[0082] The data integration module includes data fusion and analysis engine module, self-learning control algorithm module, and predictive maintenance and fault diagnosis module;

[0083] The data fusion and analysis engine module processes and fuses multi-source data to optimize energy management; the self-learning control algorithm module automatically adjusts the control strategy according to user behavior and environmental patterns. In the data fusion and analysis engine module, a prediction model based on time series analysis is introduced, using the following formula y t =φ1y t-1 +φ2y t-2 +···+φ p y t-p +ε t , where y t is the energy consumption at time t, φ i is the autoregressive coefficient, p is the model order, ε t It is white noise;

[0084] The predictive maintenance and fault diagnosis module predicts equipment failures and performs maintenance in advance.

[0085] The data fusion and analysis engine module includes data processing algorithms, machine learning models, and analysis tools; the self-learning control algorithm module includes learning algorithms, decision logic, and pattern recognition; the predictive maintenance and fault diagnosis module includes fault prediction models, diagnostic tools, and maintenance suggestion generation systems.

[0086] In the energy management optimization algorithm, the objective function of linear programming is to minimize / maximize T x, the constraint is Ax≤b;

[0087] Among them, c is the objective function coefficient vector, x is the decision variable vector, A is the coefficient matrix, and b is the constant vector.

[0088] The communication network module includes a hybrid communication network module and a quantum encryption communication module. In the quantum encryption communication module, the quantum key distribution (QKD) protocol is used, and the following formula K=H(E k (P)), where K is the key, E k is the encryption function, P is the plaintext, H is the hash function, and in the quantum encryption communication module, a quantum random number generator is used to generate the encryption key. The key generation formula is K is the generated key, X iIt is the output bit of the quantum random number generator. The key is constructed through a series of bits generated by the quantum random number generator. Due to the unpredictability of quantum random numbers, this provides extremely high security for communication;

[0089] Among them, the hybrid communication network module provides a data transmission network; the quantum encryption communication module protects the security of data transmission.

[0090] The hybrid communication network module includes wired communication equipment, wireless communication equipment, and network management software; the quantum encryption communication module includes quantum key distribution equipment, encryption and decryption algorithms, and security protocols.

[0091] The cloud platform and edge computing modules include distributed cloud platform modules and edge computing cluster modules;

[0092] Among them, the distributed cloud platform module performs distributed storage and calculation of data, and the edge computing cluster module processes real-time data to share the burden of the cloud platform. Among them, the distributed cloud platform module performs distributed storage and calculation of data. In the cloud platform and edge computing modules, an anomaly detection algorithm based on machine learning is implemented for real-time monitoring and identification of system anomalies. The anomaly score calculation adopts the following formula: score is the anomaly score, is the weight, x i is the eigenvalue, μ i is the average value of the feature. At the same time, a load balancing algorithm based on machine learning is implemented in the cloud platform and edge computing module to optimize the allocation of computing resources. The specific formula is as follows: Load is the optimal load distribution, L i is the load of the ith node, C i is the processing capacity of the i-th node. The optimal load distribution is found by minimizing the sum of the squares of the load and processing capacity ratios. This method can ensure balanced distribution of computing resources and improve overall processing efficiency.

[0093] The edge computing cluster module processes real-time data and shares the burden of the cloud platform.

[0094] The distributed cloud platform module includes server clusters, storage systems, and cloud service management tools; the edge computing cluster module includes edge servers, edge storage, and edge computing software. In the distributed cloud platform module, the hash algorithm is used to implement the data storage algorithm based on blockchain, specifically H new =H old + hash(T), where H new is the new hash value, H oldis the old hash value, T is the transaction data, hash is the hash function, and in the distributed cloud platform module, a distributed machine learning algorithm based on federated learning is implemented to train the global model while protecting data privacy. The specific model formula is: Where θ is the model parameter, l is the loss function, and x i j and i j are the features and labels of the jth sample of the ith client, respectively.

[0095] Preferably, the multifunctional intelligent sensor node module includes a sensor, a microcontroller, a communication interface, and a power management system. In the multifunctional intelligent sensor node module, a signal denoising algorithm based on wavelet transform is added. The algorithm formula is: where d k is the signal after wavelet transformation, x(n) is the original signal, ψ is the wavelet function, j is the scale parameter, k is the translation parameter, t k is the translation vector;

[0096] The dynamic execution unit module includes intelligent switches, regulating valves, servo motors, and actuator controllers; the autonomous drone monitoring system module includes drones, cameras, sensors, flight control systems, and data transmission devices; the nanosensor network module includes nanosensors, data transmission units, and power management.

[0097] Furthermore, the data fusion and analysis engine module includes data processing algorithms, machine learning models, and analysis tools. In the data fusion and analysis engine module, a clustering-based data analysis algorithm is introduced to identify and classify device data. The algorithm formula is: Where distance is the distance from the data point to the cluster center, x i is the data point, μ is the cluster center, and a classification algorithm based on support vector machine (SVM) is introduced to classify device data. The specific formula is: f(x) is the decision function, α i is the Lagrange multiplier, K(x,x i ) is the kernel function, b is the bias term, the self-learning control algorithm module includes learning algorithm, decision logic, and pattern recognition; the predictive maintenance and fault diagnosis module includes fault prediction model, diagnostic tools, and maintenance suggestion generation system.

[0098] Specifically, the hybrid communication network module includes wired communication equipment, wireless communication equipment, and network management software. In the hybrid communication network module, a traffic management algorithm based on software defined network (SDN) is added to dynamically adjust network traffic. Specifically, the following formula is used: Among them, flow is the flow rate, ri is the residual bandwidth of the path, c i is the total bandwidth of the path. At the same time, in the hybrid communication network module, a routing optimization algorithm based on Markov decision process (MDP) is added, specifically,

[0099] V(s)=max a (r(s,a)+γ∑ s' P(s'|s,a)V(s')), where V(s) is the value function of state s, r(s,a) is the immediate reward of action a in state s, γ is the discount factor, P(s'|s,a) is the transition probability from state s to state s', and the quantum encryption communication module includes quantum key distribution equipment, encryption and decryption algorithms, and security protocols.

[0100] Furthermore, the objective function and constraints of linear programming can be expressed as:

[0101] Minimizec c T x Subject to Ax≤b, where c is the objective function coefficient vector, x is the decision variable vector, A is the coefficient matrix, and b is the constant vector;

[0102] Implement machine learning based parameter optimization to automatically adjust control parameters by using a genetic algorithm, where the fitness function and parameter update can be expressed as, f(x)x new =x old +α·Δf(x old ), where f(x) is the fitness function, x is the parameter vector, α is the learning rate, and Δf(x old ) is the gradient of the fitness function;

[0103] Implement multi-layered security, including physical security, network security, and data security, to protect the system from external attacks and internal threats. This can be achieved by using intrusion detection systems (IDS) and intrusion prevention systems (IPS), and implementing encrypted communications to ensure the security of data transmission. This can be achieved by using the Advanced Encryption Standard (AES) algorithm, where the encryption process can be expressed as,

[0104] Ciphertext = AES Key (Plaintext), where Plaintext is the original data, Key is the encryption key, and Ciphertext is the encrypted data. Digital signature is implemented to ensure the integrity and source authentication of data. This can be achieved by using the RSA signature algorithm. The signature generation and verification process can be expressed as

[0105] Signature = RSA PrivateKey(Hash(Message))Valid=RSA Public Key (Signature), where Message

[0106] is the original message, Hash is the hash function, Private Key and Public Key are the private key and public key respectively, Signature is the generated signature, and Valid is the verification result

[0107] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0108] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0109] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0110] A person skilled in the art may understand that all or part of the steps in the above-mentioned embodiment method may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0111] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0112] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. An intelligent energy-saving control system for Internet of Things devices, characterized in that: It includes basic equipment module, data integration module, communication network module, cloud platform and edge computing module, user interface module, system integration and testing module; The data integration module processes and integrates data from different sensors and actuators; the communication network module realizes communication between devices and between devices and the cloud platform; the cloud platform and the edge computing module store data and process complex calculations; the interface module provides an interactive interface and supports touch screen operation and voice control; the system integration and testing module is used to ensure that all parts of the system work together and conduct tests, including automated test scripts and simulation tools, to ensure the stability and reliability of the system; It also includes an energy management optimization module, which uses linear programming and dynamic programming and implements parameter optimization based on machine learning to automatically adjust control parameters; It also includes a security mechanism module to implement multi-level security protection, including physical security, network security and data security, regularly and automatically update system firmware to fix known security vulnerabilities, and implement intrusion detection system (IDS) and intrusion prevention system (IPS).

2. The intelligent energy-saving control system of an Internet of Things device according to claim 1, characterized in that: The basic equipment modules include a multifunctional intelligent sensor node module, a dynamic execution unit module, an autonomous drone monitoring system module, and a nanosensor network module; Among them, the multifunctional intelligent sensor node module collects environmental data and performs edge computing; the dynamic execution unit module adjusts the equipment status according to the control instructions; the autonomous drone monitoring system module remotely monitors and collects data, covering large and difficult-to-reach areas. In the autonomous drone monitoring system module, an image recognition algorithm based on deep learning is added. The algorithm formula is f(x)=σ(W·x+b), where f(x) is the output of the neural network, x is the input feature, W is the weight matrix, b is the bias vector, and σ is the activation function. At the same time, a path planning algorithm based on deep learning is also added. The algorithm adopts the following formula: Where Path is the optimal path, f is the flight cost function, x i is a point on the path; Nanosensor network modules monitor the internal status of devices and provide health and performance indicators; The data integration module includes a data fusion and analysis engine module, a self-learning control algorithm module, and a predictive maintenance and fault diagnosis module; The data fusion and analysis engine module processes and fuses multi-source data to optimize energy management; the self-learning control algorithm module automatically adjusts the control strategy according to user behavior and environmental patterns. In the data fusion and analysis engine module, a prediction model based on time series analysis is introduced, using the following formula y t =φ1y t-1 +φ2y t-2 +···+φ p y t-p +ε t , where y t is the energy consumption at time t, φ i is the autoregressive coefficient, p is the model order, ε t It is white noise; The predictive maintenance and fault diagnosis module predicts equipment failures and performs maintenance in advance.

3. The intelligent energy-saving control system of an Internet of Things device according to claim 1, characterized in that: The communication network module includes a hybrid communication network module and a quantum encryption communication module; The hybrid communication network module provides a data transmission network; the quantum encryption communication module protects the security of data transmission. In the quantum encryption communication module, the quantum key distribution (QKD) protocol is used, using the following formula K = H (E k (P)), where K is the key, E k is the encryption function, P is the plaintext, H is the hash function, and in the quantum encryption communication module, a quantum random number generator is used to generate the encryption key. The key generation formula is: K is the generated key, X i is the output bit of the quantum random number generator.

4. The intelligent energy-saving control system of an Internet of Things device according to claim 1, characterized in that: The cloud platform and edge computing module include a distributed cloud platform module and an edge computing cluster module; Among them, the distributed cloud platform module performs distributed storage and calculation of data. In the cloud platform and edge computing modules, an anomaly detection algorithm based on machine learning is implemented for real-time monitoring and identification of system anomalies. The anomaly score is calculated using the following formula: score is the anomaly score, is the weight, x i is the eigenvalue, μ i is the average value of the feature. At the same time, a load balancing algorithm based on machine learning is implemented in the cloud platform and edge computing module to optimize the allocation of computing resources. The specific formula is as follows: Load is the optimal load distribution, L i is the load of the ith node, C i is the processing capacity of the ith node; The edge computing cluster module processes real-time data and shares the burden of the cloud platform.

5. The intelligent energy-saving control system of an Internet of Things device according to claim 2, characterized in that: The multifunctional intelligent sensor node module includes a sensor, a microcontroller, a communication interface, and a power management system. A signal denoising algorithm based on wavelet transform is added to the multifunctional intelligent sensor node module. The algorithm formula is: where d k is the signal after wavelet transformation, x(n) is the original signal, ψ is the wavelet function, j is the scale parameter, k is the translation parameter, t k is the translation vector; The dynamic execution unit module includes intelligent switches, regulating valves, servo motors, and actuator controllers; the autonomous drone monitoring system module includes drones, cameras, sensors, flight control systems, and data transmission devices; the nanosensor network module includes nanosensors, data transmission units, and power management.

6. The intelligent energy-saving control system of an Internet of Things device according to claim 2, characterized in that: The data fusion and analysis engine module includes data processing algorithms, machine learning models, and analysis tools. In the data fusion and analysis engine module, a clustering-based data analysis algorithm is introduced to identify and classify device data. The algorithm formula is: Where distance is the distance from the data point to the cluster center, x i is the data point, μ is the cluster center, and a classification algorithm based on support vector machine (SVM) is introduced to classify device data. The specific formula is: f(x) is the decision function, α i is the Lagrange multiplier, K(x,x i ) is the kernel function, b is the bias term; The self-learning control algorithm module includes learning algorithm, decision logic, and pattern recognition; the predictive maintenance and fault diagnosis module includes fault prediction model, diagnostic tools, and maintenance suggestion generation system.

7. The intelligent energy-saving control system of an Internet of Things device according to claim 3 is characterized in that: The hybrid communication network module includes wired communication equipment, wireless communication equipment, and network management software. In the hybrid communication network module, a traffic management algorithm based on software defined network (SDN) is added to dynamically adjust network traffic. Specifically, the following formula is used: Among them, flow is the flow rate, r i is the residual bandwidth of the path, c i is the total bandwidth of the path. At the same time, in the hybrid communication network module, a routing optimization algorithm based on Markov decision process (MDP) is added, specifically, V(s)=max a (r(s,a)+γ∑ s' P(s'|s,a)V(s')), where V(s) is the value function of state s, r(s,a) is the immediate reward of action a in state s, γ is the discount factor, and P(s'|s,a) is the transition probability from state s to state s'; The quantum encryption communication module includes quantum key distribution equipment, encryption and decryption algorithms, and security protocols.

8. The intelligent energy-saving control system of an Internet of Things device according to claim 4, characterized in that: The distributed cloud platform module includes a server cluster, a storage system, and a cloud service management tool. In the distributed cloud platform module, a hash algorithm is used to implement a data storage algorithm based on blockchain, specifically H new =H old + hash(T), where H new is the new hash value, H old is the old hash value, T is the transaction data, and hash is the hash function. At the same time, the distributed cloud platform module implements a distributed machine learning algorithm based on federated learning, which is used to train the global model while protecting data privacy. The specific model formula is: Where θ is the model parameter, l is the loss function, and are the features and labels of the jth sample of the i-th client, respectively; The edge computing cluster module includes edge servers, edge storage, and edge computing software.

9. The intelligent energy-saving control system of an Internet of Things device according to claim 1, characterized in that: The objective function and constraints of the linear programming can be expressed as: Minimizec c T x Subject to Ax≤b, where c is the objective function coefficient vector, x is the decision variable vector, A is the coefficient matrix, and b is the constant vector; Implement machine learning based parameter optimization to automatically adjust control parameters by using a genetic algorithm, where the fitness function and parameter update can be expressed as, f(x)x new =x old +α·Δf(x old ), where f(x) is the fitness function, x is the parameter vector, α is the learning rate, and Δf(x old ) is the gradient of the fitness function; Implement multi-layered security, including physical security, network security, and data security, to protect the system from external attacks and internal threats. This can be achieved by using intrusion detection systems (IDS) and intrusion prevention systems (IPS), and implementing encrypted communications to ensure the security of data transmission. This can be achieved by using the Advanced Encryption Standard (AES) algorithm, where the encryption process can be expressed as, Ciphertext = AES Key (Plaintext), where Plaintext is the original data, Key is the encryption key, and Ciphertext is the encrypted data. Digital signature is implemented to ensure the integrity and source authentication of data. This can be achieved by using the RSA signature algorithm. The signature generation and verification process can be expressed as Signature = RSA PrivateKey (Hash(Message))Valid = RSA PublicKey (Signature), where Message is the original message, Hash is the hash function, Private Key and Public Key are the private key and public key respectively, Signature is the generated signature, and Valid is the verification result.

10. The intelligent energy-saving control system of an Internet of Things device according to claim 3, characterized in that: In the energy management optimization algorithm, the objective function of linear programming is minimize / maximizec T x, the constraint is Ax≤b; Among them, c is the objective function coefficient vector, x is the decision variable vector, A is the coefficient matrix, and b is the constant vector. At the same time, in the energy management optimization algorithm, a parameter optimization method based on genetic algorithm is introduced to find the optimal control parameters, specifically: Where f(x) is the fitness function, x i is a parameter, f i (x) is the fitness contribution of each parameter.

Images