A multi-device energy consumption monitoring and management method based on the Internet of Things

Through the combination of edge computing and artificial intelligence, combined with blockchain technology and network redundancy, the problem of insufficient data processing delay and security in smart home systems in energy consumption monitoring and management is solved, real-time, secure and personalized Energy management improves the overall performance and user satisfaction of the system.

CN118210240BActive Publication Date: 2024-11-05CIXI ZHOUXIANG JIASEN ELECTRICAL ACCESSORIES FACTORY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410216778.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-02-28
Publication Date
2024-11-05
Estimated Expiration
2044-02-28

AI Technical Summary

Technical Problem

The existing smart home systems have problems such as delay in energy consumption monitoring and management of data processing, insufficient security, high network dependence and insufficient automatic learning capabilities, which affect real-time and personalized energy management.

Method used

Adopt edge computing and artificial intelligence to enhance data security through blockchain technology, use network redundancy and offline functions to ensure system stability, and use adaptive algorithms to adjust energy consumption management according to user behavior and environmental conditions, and integrate renewable energy and smart battery system.

Benefits of technology

Realize real-time processing and in-depth analysis of energy consumption data of smart home equipment, improve the real-time and efficiency of the system, ensure data security and network stability, provide personalized and intelligent energy management, and improve the overall system. Availability and user trust.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118210240B_ABST
    Figure CN118210240B_ABST
Patent Text Reader

Abstract

The present invention discloses a multi-device energy consumption monitoring and management method based on the Internet of Things, including S1, using Internet of Things sensors to collect energy consumption data and user behavior data of smart home devices; S2, using edge computing devices to perform preliminary analysis on the collected data; S3, transmitting the processed data to a central processing server, and performing in-depth analysis on the data through an algorithm; S4, automatically adjusting the operating parameters of smart home devices based on the analysis results of the algorithm; S5, using network redundancy technology to ensure the stability of data transmission; S6, applying blockchain technology to record and verify all data transactions, including verifying the integrity, transparency and non-tamperability of data; S7, automatically adjusting settings through self-learning and adaptive algorithms; S8, integrating renewable energy and smart battery systems. The present invention has the advantages of high data processing efficiency, strong system operation stability, high data security and transparency, and improved energy utilization efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of multi-device energy consumption monitoring and management, and in particular to a multi-device energy consumption monitoring and management method based on the Internet of Things. Background Art

[0002] With the rapid development of smart home technology, home automation and energy management have become important means to improve living comfort and energy efficiency. Smart home systems integrate various sensors and devices to achieve automatic control of the home environment and optimal management of energy consumption. However, existing smart home systems face many challenges in energy consumption monitoring and management.

[0003] First, most existing systems rely on a centralized data processing architecture, which not only increases the reliance on central servers, but also causes delays in data processing, affecting real-time performance and efficiency. Second, data security issues have become a major problem for smart home systems. With the generation of a large amount of sensitive data, how to ensure data security and privacy has become an important consideration. In addition, smart home devices are highly dependent on network connections, so the reliability and effectiveness of the system are challenged in the event of network instability or interruption. Finally, existing smart home systems are not mature enough in terms of automatic learning and adaptation to user behavior, resulting in a lack of personalization and optimization of energy management.

[0004] In this context, the present invention proposes a method for applying Internet of Things technology to smart home device energy consumption monitoring and management, aiming to solve the deficiencies of the above-mentioned prior art. The characteristics and advantages of the present invention are reflected in the following aspects:

[0005] 1. Integration of edge computing and artificial intelligence: This invention reduces the reliance on central servers and improves the real-time and efficiency of data processing by using edge computing on local devices for data processing. At the same time, the integrated AI algorithm can achieve more accurate energy consumption prediction and management.

[0006] 2. Data security and privacy protection: By applying blockchain technology, the present invention enhances the integrity, traceability and transparency of data. The distributed ledger ensures the immutability of data, effectively improving the data security of the system and the trust of users.

[0007] 3. Adaptive energy management system: This invention adopts an AI-based adaptive algorithm to automatically adjust energy consumption according to user behavior and environmental conditions, improving the intelligence and personalization of energy use.

[0008] 4. Network redundancy and offline function: By constructing a system with network redundancy and developing an offline working mode, the present invention ensures the normal operation of the system and the continuity of energy consumption monitoring when the network is unstable or interrupted.

[0009] Therefore, how to provide a multi-device energy consumption monitoring and management method based on the Internet of Things is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0010] One object of the present invention is to propose a method for monitoring and managing energy consumption of multiple devices based on the Internet of Things. The present invention provides a comprehensive solution for monitoring and managing energy consumption of smart home devices by combining edge computing, artificial intelligence algorithms, network redundancy technology, blockchain, and self-learning and adaptive algorithms. This enables the system to effectively collect and process a large amount of energy consumption data and user behavior data while ensuring the security and privacy of the data.

[0011] A method for monitoring and managing energy consumption of multiple devices based on the Internet of Things according to an embodiment of the present invention is characterized by comprising the following steps:

[0012] S1. Use IoT sensors to collect energy consumption data and user behavior data of smart home devices;

[0013] S2. Clean, classify and perform preliminary analysis on the collected data through edge computing devices;

[0014] S3, transmit the processed data to the central processing server, and conduct in-depth analysis of the data through artificial intelligence algorithms, including energy consumption pattern recognition, user behavior habit analysis and fault prediction;

[0015] S4, automatically adjust the operating parameters of smart home devices based on the analysis results of artificial intelligence algorithms;

[0016] S5. Use network redundancy technology to ensure the stability of data transmission, including the use of multiple network channels and offline working mode;

[0017] S6. Apply blockchain technology to record and verify all data transactions, including verifying the integrity, transparency and immutability of data;

[0018] S7, automatically adjusts settings based on user habits, seasonal changes and weather conditions through self-learning and adaptive algorithms;

[0019] S8. Integrate renewable energy and smart battery systems to improve the system's self-sufficiency and overall energy efficiency.

[0020] Optionally, the S1 specifically includes:

[0021] S11, deploying multiple IoT sensors in the smart home environment, wherein the IoT sensors respectively collect temperature T, humidity H, light L, motion M, and power consumption P;

[0022] S12, assign a unique identifier (ID) to each sensor to identify and track the source of data during data collection and transmission;

[0023] S13, setting the sensor to collect data regularly, with a collection frequency of f, where f is a time interval determined according to the specific needs of the device and the usage environment;

[0024] S14. The collected data includes energy consumption data E, the frequency of use of the equipment, the use time period and the user's operation mode of the equipment;

[0025] S15. Perform preliminary formatting on the collected data to ensure that the data conforms to the format and standards required for subsequent analysis.

[0026] Optionally, the S2 specifically includes:

[0027] S21, the edge computing device receives data from IoT sensors, including temperature T, humidity H, light L, motion M, and power consumption P;

[0028] S22, performing a data cleaning process on the received data to remove invalid or erroneous data records;

[0029] S23, classifying the cleaned data into energy consumption data E and user behavior data B based on data characteristics, wherein the energy consumption data E mainly depends on the power consumption P, and the user behavior data B reflects the interaction mode between the user and the smart home device;

[0030] S24. Perform preliminary analysis on the classified data:

[0031] Calculate the average energy consumption of a device over a certain period of time

[0032]

[0033] Among them, E i represents the energy consumption value measured at different time points, and n is the total number of measurement points;

[0034] Calculating the variance of environmental data Assessing the volatility of environmental conditions:

[0035]

[0036] Among them, Env i is a single environmental data point, is the mean of these data points;

[0037] Analyze the changing trend of user behavior data B over time:

[0038] B t=a·t+b;

[0039] Among them, B t is the user behavior data at time t, a and b are regression coefficients;

[0040] Use the Z-score method to detect outliers in energy consumption data:

[0041]

[0042] Where E is a specific energy consumption data point, and σ E are the mean and standard deviation of the energy consumption dataset, respectively;

[0043] S25, formatting the cleaned, classified and preliminarily analyzed data into a format suitable for transmission to a central processing server.

[0044] Optionally, the S3 specifically includes:

[0045] S31, the central processing server receives the cleaned, classified and preliminarily analyzed data from the edge computing device;

[0046] S32. Use the Autoregressive Moving Average Model (ARMA) to conduct in-depth analysis of the received data:

[0047] E t =α+β1e t-1 +β2e t-2 +...+β n E t-n +ε t ;

[0048] Among them, E t represents the energy consumption data at time point t, β i represents the autoregressive coefficient of the model, α is a constant term, and ε t is the error term, n represents the number of time points considered;

[0049] S33. Analyze user behavior data B to identify usage patterns and preferences, and use K-means clustering algorithm to classify user behaviors into different groups to improve energy efficiency:

[0050] Initialize K cluster centers, which represent different types of user behavior patterns

[0051] C={c1,c2,...,c K};

[0052] For each user behavior data point B i , assigning it to the nearest cluster center:

[0053] m1≤j≤K |B i -c j |;

[0054] Among them, |B i -c j | represents user behavior data point B i With cluster center c j The square of the Euclidean distance between them.

[0055] Update the center point of each cluster to be the average of all user behavior data points belonging to that cluster:

[0056]

[0057] Among them, S j is the set of all data points in the jth cluster, |s j | is the number of data points in this cluster.

[0058] S34, using support vector machine (SVM) for fault prediction, predicting and classifying potential equipment faults based on historical data and current data features:

[0059]

[0060] Where x represents the new input feature, n is the number of support vectors, and α i is the coefficient of the learned support vector, y i are the labels of the corresponding support vectors in the training set, <x i ,x> is the support vector x i The inner product between and the input feature x, and b is the bias term of the model.

[0061] S35. Organize the results of the in-depth analysis into a report and provide suggestions for energy consumption optimization and fault prevention of smart home devices.

[0062] Optionally, the S4 specifically includes:

[0063] S41. Automatically identify energy consumption optimization opportunities and potential equipment failure risks based on the in-depth analysis results of the central processing server;

[0064] S42, calculate the optimized equipment operating parameters, including setting a new energy consumption target E target , and based on historical energy consumption data E historical and predicted data E predict Adjust device settings:

[0065] E target =λ·E historical +(1-λ)·E predict ;

[0066] Among them, λ is used to balance the impact of historical data and forecast data;

[0067] S43, automatically updating the operating mode of smart home devices, including temperature settings, lighting intensity, and on / off times of devices;

[0068] S44. Use a logistic regression model to predict user behavior patterns and automatically adjust device settings based on user behavior patterns and environmental changes:

[0069]

[0070] Among them, P(Y=1|X) is the probability that the user takes a certain action given feature X, β0,β1,...,β n are the model coefficients, X1,...,X n is a characteristic variable;

[0071] S45. If the system detects a potential equipment failure or performance degradation, it automatically triggers a maintenance process, including sending an alarm message to the user or maintenance personnel.

[0072] Optionally, the S5 specifically includes:

[0073] S51. Assign a unique identifier ID to each network channel channel , monitor and manage different network paths;

[0074] S53. Establish a network performance monitoring system to monitor the transmission quality of each network channel in real time, including delay δ and packet loss rate ρ:

[0075] NSI = a·δ+b·(1-ρ);

[0076] Among them, NSI is the network stability index, δ represents network delay, ρ represents packet loss rate, and a and b are the weight coefficients of the two respectively;

[0077] S54, adopt offline working mode to ensure that smart home devices can maintain basic monitoring and management functions when the network is unstable or interrupted. The device will record and store key operation and event data, including energy consumption data E, user behavior data B and device status S status .

[0078] Optionally, the S6 specifically includes:

[0079] S61. Use blockchain technology to establish a distributed ledger system to record and verify energy consumption data E, user behavior data B and device status information S in a smart home environment. status ;

[0080] S62. Generate a unique hash value H for each data transaction and store it in the blockchain together with the transaction data:

[0081] H=f(E,B,S status );

[0082] Among them, H is the unique hash value of the data transaction, E, B and S status Represent energy consumption data, user behavior data, and device status information respectively;

[0083] S63. Use smart contracts to automatically verify and execute data processing tasks. Each data transaction is time-stamped on the blockchain. The timestamp T is recorded in the blockchain together with the hash value H of each transaction, forming an irreversible time series record.

[0084] Optionally, the S7 specifically includes:

[0085] S71. Implement self-learning and adaptive algorithms to enable the system to automatically adjust the operating parameters of smart home devices according to user behavior habits, seasonal changes and weather conditions;

[0086] S72. Use time series analysis method to predict user behavior B and energy consumption demand E:

[0087]

[0088]

[0089] Among them, B predict (t) and E predict (t) represent the predicted user behavior and energy consumption demand at the future time point t, α, β i ,γ,δ i are model parameters, B(ti) and E(ti) represent user behavior and energy consumption data at past time points;

[0090] S73. Use a decision tree algorithm to classify and regress the historical data of user behavior B and energy consumption E, and generate decision rules to predict future user behavior and energy consumption requirements:

[0091] Decision(B,E,t,W)=TreeRules(B,E,t,W);

[0092] Among them, Decision represents the prediction result based on the decision tree, and TreeRules represents a series of decision rules learned from the data;

[0093] S74. Based on the above prediction and analysis results, the system will automatically adjust the operating parameters of the smart home devices and regularly evaluate and adjust the performance of the self-learning and adaptive algorithms.

[0094] Optionally, the S8 specifically includes:

[0095] S81. Real-time monitoring of renewable energy generation through energy management system E gen and the energy E stored in the smart battery store :

[0096] E opt =η·E gen +(1-η)·E store ;

[0097] Among them, E opt represents the optimized energy usage, η is the weight factor of renewable energy utilization;

[0098] S82, based on real-time and predicted energy consumption data E predict and renewable energy supply data E gen , automatically adjust the energy consumption of smart home devices.

[0099] The beneficial effects of the present invention are:

[0100] (1) The present invention combines edge computing and artificial intelligence algorithms to achieve real-time processing and in-depth analysis of smart home device energy consumption data, thereby greatly improving data processing speed and efficiency. This enables the system to quickly respond to environmental changes and user needs, optimize energy consumption in real time, and ensure high-precision energy consumption prediction and management.

[0101] (2) The present invention utilizes network redundancy technology and offline working mode to significantly improve the stability and reliability of the system in the case of network instability or interruption. This ensures that smart home devices can maintain basic monitoring and management functions even in poor network environments, thereby improving the overall availability of the system.

[0102] (3) The present invention enhances the security and transparency of data by applying blockchain technology, and improves users' trust in the smart home system. The distributed ledger of blockchain provides immutability and traceability for data transactions, ensures data integrity and tamper-proofness, and reduces the risk of data leakage and unauthorized access.

[0103] (4) The present invention uses self-learning and adaptive algorithms to enable the system to automatically adjust the settings of smart home devices according to user behavior habits, seasonal changes and weather conditions. This not only improves energy efficiency, but also provides users with a more personalized and comfortable living environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0104] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0105] Figure 1 This is a general architecture diagram of a multi-device energy consumption monitoring and management method based on the Internet of Things proposed by the present invention;

[0106] Figure 2 The invention proposes a flowchart of smart home device energy consumption data collection based on a multi-device energy consumption monitoring and management method of the Internet of Things;

[0107] Figure 3 A detailed step flow chart of the edge computing device of a multi-device energy consumption monitoring and management method based on the Internet of Things proposed in the invention. DETAILED DESCRIPTION

[0108] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0109] refer to Figure 1-Figure 3 , a multi-device energy consumption monitoring and management method based on the Internet of Things, characterized in that it includes the following steps:

[0110] S1, use IoT sensors to collect energy consumption data and user behavior data of smart home devices;

[0111] In this implementation, S1 specifically includes:

[0112] S11, deploying multiple IoT sensors in the smart home environment, wherein the IoT sensors respectively collect temperature T, humidity H, light L, motion M, and power consumption P;

[0113] S12, assign a unique identifier (ID) to each sensor to identify and track the source of data during data collection and transmission;

[0114] S13, setting the sensor to collect data regularly, with a collection frequency of f, where f is a time interval determined according to the specific needs of the device and the usage environment;

[0115] S14. The collected data includes energy consumption data E, the frequency of use of the equipment, the use time period and the user's operation mode of the equipment;

[0116] S15. Perform preliminary formatting on the collected data to ensure that the data conforms to the format and standards required for subsequent analysis.

[0117] S2. Clean, classify and perform preliminary analysis on the collected data through edge computing devices;

[0118] In this implementation, S2 specifically includes:

[0119] S21, the edge computing device receives data from IoT sensors, including temperature T, humidity H, light L, motion M, and power consumption P;

[0120] S22, performing a data cleaning process on the received data to remove invalid or erroneous data records;

[0121] S23, classifying the cleaned data into energy consumption data E and user behavior data B based on data characteristics, wherein the energy consumption data E mainly depends on the power consumption P, and the user behavior data B reflects the interaction mode between the user and the smart home device;

[0122] S24. Perform preliminary analysis on the classified data:

[0123] Calculate the average energy consumption of a device over a certain period of time

[0124]

[0125] Among them, E i represents the energy consumption value measured at different time points, and n is the total number of measurement points;

[0126] Calculating the variance of environmental data Assessing the volatility of environmental conditions:

[0127]

[0128] Among them, Env i is a single environmental data point, is the mean of these data points;

[0129] Analyze the changing trend of user behavior data B over time:

[0130] B t =a·t+b;

[0131] Among them, B t is the user behavior data at time t, a and b are regression coefficients;

[0132] Use the Z-score method to detect outliers in energy consumption data:

[0133]

[0134] Where E is a specific energy consumption data point, and σE are the mean and standard deviation of the energy consumption dataset, respectively;

[0135] S25, formatting the cleaned, classified and preliminarily analyzed data into a format suitable for transmission to a central processing server.

[0136] S3, transmit the processed data to the central processing server, and conduct in-depth analysis of the data through artificial intelligence algorithms, including energy consumption pattern recognition, user behavior habit analysis and fault prediction;

[0137] In this implementation, S3 specifically includes:

[0138] S31, the central processing server receives the cleaned, classified and preliminarily analyzed data from the edge computing device;

[0139] S32. Use the Autoregressive Moving Average Model (ARMA) to conduct in-depth analysis of the received data:

[0140] E t =α+β1E t-1 +β2E t-2 +...+β n E t-n +ε t ;

[0141] Among them, E t represents the energy consumption data at time point t, β i represents the autoregressive coefficient of the model, α is a constant term, and ε t is the error term, n represents the number of time points considered;

[0142] S33. Analyze user behavior data B to identify usage patterns and preferences, and use K-means clustering algorithm to classify user behaviors into different groups to improve energy efficiency:

[0143] Initialize K cluster centers, which represent different types of user behavior patterns

[0144] C={c1,c2,...,c K};

[0145] For each user behavior data point B i , assigning it to the nearest cluster center:

[0146] m 1≤j≤K |B i -c j |;

[0147] Among them, |B i -c j | represents user behavior data point B iWith cluster center c j The square of the Euclidean distance between them.

[0148] Update the center point of each cluster to be the average of all user behavior data points belonging to that cluster:

[0149]

[0150] Among them, S j is the set of all data points in the jth cluster, |S j | is the number of data points in this cluster.

[0151] S34, using support vector machine (SVM) for fault prediction, predicting and classifying potential equipment faults based on historical data and current data features:

[0152]

[0153] Where x represents the new input feature, n is the number of support vectors, and α i is the coefficient of the learned support vector, y i are the labels of the corresponding support vectors in the training set, <x i ,x> is the support vector x i The inner product between and the input feature x, and b is the bias term of the model.

[0154] S35. Organize the results of the in-depth analysis into a report and provide suggestions for energy consumption optimization and fault prevention of smart home devices.

[0155] S4, automatically adjust the operating parameters of smart home devices based on the analysis results of artificial intelligence algorithms;

[0156] In this implementation, S4 specifically includes:

[0157] S41. Automatically identify energy consumption optimization opportunities and potential equipment failure risks based on the in-depth analysis results of the central processing server;

[0158] S42, calculate the optimized equipment operating parameters, including setting a new energy consumption target E target , and based on historical energy consumption data E historical and predicted data E predict Adjust device settings:

[0159] E target =λ·E historical +(1-λ)·E predict ;

[0160] Among them, λ is used to balance the impact of historical data and forecast data;

[0161] S43, automatically updating the operating mode of smart home devices, including temperature settings, lighting intensity, and on / off times of devices;

[0162] S44. Use a logistic regression model to predict user behavior patterns and automatically adjust device settings based on user behavior patterns and environmental changes:

[0163]

[0164] Among them, P(Y=1|X) is the probability that the user takes a certain action given feature X, β0,β1,...,β n are the model coefficients, X1,...,X n is a characteristic variable;

[0165] S45. If the system detects a potential equipment failure or performance degradation, it automatically triggers a maintenance process, including sending an alarm message to the user or maintenance personnel.

[0166] S5. Use network redundancy technology to ensure the stability of data transmission, including the use of multiple network channels and offline working mode;

[0167] In this implementation, S5 specifically includes:

[0168] S51. Assign a unique identifier ID to each network channel channel , monitor and manage different network paths;

[0169] S53. Establish a network performance monitoring system to monitor the transmission quality of each network channel in real time, including delay δ and packet loss rate ρ:

[0170] NSI = a·δ+b·(1-ρ);

[0171] Among them, NSI is the network stability index, δ represents network delay, ρ represents packet loss rate, and a and b are the weight coefficients of the two respectively;

[0172] S54, adopt offline working mode to ensure that smart home devices can maintain basic monitoring and management functions when the network is unstable or interrupted. The device will record and store key operation and event data, including energy consumption data E, user behavior data B and device status S status .

[0173] S6. Apply blockchain technology to record and verify all data transactions, including verifying the integrity, transparency and immutability of data;

[0174] In this implementation, S6 specifically includes:

[0175] S61. Use blockchain technology to establish a distributed ledger system to record and verify energy consumption data E, user behavior data B and device status information S in a smart home environment. status ;

[0176] S62. Generate a unique hash value H for each data transaction and store it in the blockchain together with the transaction data:

[0177] H=f(E,B,S statue );

[0178] Among them, H is the unique hash value of the data transaction, E, B and S status Represent energy consumption data, user behavior data, and device status information respectively;

[0179] S63. Use smart contracts to automatically verify and execute data processing tasks. Each data transaction is time-stamped on the blockchain. The timestamp T is recorded in the blockchain together with the hash value H of each transaction, forming an irreversible time series record.

[0180] S7, automatically adjusts settings based on user habits, seasonal changes and weather conditions through self-learning and adaptive algorithms;

[0181] In this implementation, S7 specifically includes:

[0182] S71. Implement self-learning and adaptive algorithms to enable the system to automatically adjust the operating parameters of smart home devices according to user behavior habits, seasonal changes and weather conditions;

[0183] S72. Use time series analysis method to predict user behavior B and energy consumption demand E:

[0184]

[0185]

[0186] Among them, B predict (t) and E predict (t) represent the predicted user behavior and energy consumption demand at the future time point t, α, β i ,γ,δ i are model parameters, B(ti) and E(ti) represent user behavior and energy consumption data at past time points;

[0187] S73. Use a decision tree algorithm to classify and regress the historical data of user behavior B and energy consumption E, and generate decision rules to predict future user behavior and energy consumption requirements:

[0188] Decision(B,E,t,W)=TreeRules(B,E,t,W);

[0189] Among them, Decision represents the prediction result based on the decision tree, and TreeRules represents a series of decision rules learned from the data;

[0190] S74. Based on the above prediction and analysis results, the system will automatically adjust the operating parameters of the smart home devices and regularly evaluate and adjust the performance of the self-learning and adaptive algorithms.

[0191] S8. Integrate renewable energy and smart battery systems to improve the system's self-sufficiency and overall energy efficiency.

[0192] In this implementation, S8 specifically includes:

[0193] S81. Real-time monitoring of renewable energy generation through energy management system E gen and the energy E stored in the smart battery store :

[0194] E opt =η·E gen +(1-η)·E store ;

[0195] Among them, E opt represents the optimized energy usage, η is the weight factor of renewable energy utilization;

[0196] S82, based on real-time and predicted energy consumption data E predict and renewable energy supply data E gen , automatically adjust the energy consumption of smart home devices.

[0197] Embodiment 1:

[0198] In a large residential community in Beijing, the community faces the problem of increasing energy consumption and inefficient management. In order to meet these challenges, the community management committee decided to deploy the smart home device energy consumption monitoring and management system based on the Internet of Things technology proposed in this invention. The system aims to optimize the energy consumption management of smart home devices in the community by integrating edge computing, artificial intelligence, network redundancy technology, blockchain, and self-learning and adaptive algorithms.

[0199] The first step in deploying the system is to install IoT sensors in each household in the community. These sensors are deployed on smart home appliances such as air conditioners, lighting systems, televisions, refrigerators, etc., to collect real-time information about the device usage status, energy consumption data, and environmental conditions (such as temperature and humidity). In addition, each resident's smartphone and tablet are also included in the system to collect user behavior data.

[0200] Subsequently, the edge computing device performs preliminary processing on the collected data, including data cleaning, classification and preliminary analysis, which reduces the data transmission burden on the central server and improves the data processing speed. The processed data is then transmitted to the central processing server located in the community management center.

[0201] On the central processing server, artificial intelligence algorithms conduct in-depth analysis of the data. By analyzing users' living habits and device usage patterns, the system is able to predict future energy consumption needs and optimize the operating parameters of the equipment, such as adjusting the temperature settings of air conditioners and the brightness of lighting systems. In addition, the system can automatically adjust device settings based on weather forecasts and seasonal changes to further save energy. During the implementation, the system collected and analyzed the following data:

[0202] Table 1: Community smart home system implementation effect report

[0203] Data Category Pre-implementation data Post-implementation data Changes Total energy consumption 100,000 kWh 90,000 kWh -10% Customer satisfaction - +15% promote System response time 5 seconds 2 seconds 60% reduction Data Security and Privacy Several times 0 times Significantly reduce Network stability An average of 2 failures per month An average of 1 failure per month 50% reduction

[0204] As can be seen from Table 1 above, in the embodiment, through the implementation of the present invention, the energy efficiency of the community smart home has been significantly improved, and the quality of life of the residents has also been improved. The significant reduction in energy consumption not only reduces the overall operating cost of the community, but also contributes to environmental protection. In addition, the efficient response and user-friendly interaction of the system enhance the living experience of the residents. The improvement of data security and network stability also enhances the trust and satisfaction of the residents in the smart home system.

[0205] In summary, the implementation of the present invention not only solves the problems of low energy efficiency and complex equipment management faced by the community, but also improves the living comfort and satisfaction of residents, demonstrating the great potential and broad application prospects of Internet of Things technology in the field of smart homes.

[0206] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A multi-device energy consumption monitoring and management method based on the Internet of Things, characterized in that: The steps include: S1. Use IoT sensors to collect energy consumption data and user behavior data of smart home devices; The S1 specifically includes: S11, deploying multiple IoT sensors in the smart home environment, wherein the IoT sensors respectively collect temperature T, humidity H, light L, motion M, and power consumption P; S12, assign a unique identifier (ID) to each sensor to identify and track the source of data during data collection and transmission; S13, setting the sensor to collect data regularly, with a collection frequency of f, where f is a time interval determined according to the specific needs of the device and the usage environment; S14. The collected data includes energy consumption data E, the frequency of use of the equipment, the use time period and the user's operation mode of the equipment; S15. Perform preliminary formatting of the collected data to make it conform to the format and standards required for subsequent analysis; S2. Cleaning, classifying and preliminarily analyzing the collected data through edge computing devices; S2 specifically includes: S21, the edge computing device receives data from IoT sensors, including temperature T, humidity H, light L, motion M, and power consumption P; S22, performing a data cleaning process on the received data to remove invalid or erroneous data records; S23, classifying the cleaned data into energy consumption data E and user behavior data B based on data characteristics, wherein the energy consumption data E mainly depends on the power consumption P, and the user behavior data B reflects the interaction mode between the user and the smart home device; S24. Perform preliminary analysis on the classified data: Calculate the average energy consumption of a device over a certain period of time Among them, E i represents the energy consumption value measured at different time points, and n is the total number of measurement points; Calculating the variance of environmental data Assessing the volatility of environmental conditions: Among them, Env i is a single environmental data point, is the mean of these data points; Analyze the changing trend of user behavior data B over time: B t =a·t+b; Among them, B t is the user behavior data at time t, a and b are regression coefficients; Use the Z-score method to detect outliers in energy consumption data: Where E is a specific energy consumption data point, and σ E are the mean and standard deviation of the energy consumption dataset, respectively; S25, formatting the cleaned, classified and preliminarily analyzed data into a format suitable for transmission to a central processing server; S3, transmit the processed data to the central processing server, and conduct in-depth analysis of the data through artificial intelligence algorithms, including energy consumption pattern recognition, user behavior habit analysis and fault prediction; S4, automatically adjust the operating parameters of smart home devices based on the analysis results of artificial intelligence algorithms; The S4 specifically includes: S41. Automatically identify energy consumption optimization opportunities and potential equipment failure risks based on the in-depth analysis results of the central processing server; S42, calculate the optimized equipment operating parameters, including setting a new energy consumption target E target , and based on historical energy consumption data E historical and predicted data E predict Adjust device settings: AND target =λ·E historical +(1-λ)·E predict ; Among them, λ is used to balance the impact of historical data and forecast data; S43, automatically updating the operating mode of smart home devices, including temperature settings, lighting intensity, and on / off times of devices; S44. Use a logistic regression model to predict user behavior patterns and automatically adjust device settings based on user behavior patterns and environmental changes: Among them, P(Y=1|X) is the probability that the user takes a certain action given feature X, β0,β1,...,β n are the model coefficients, X1,...,X n is a characteristic variable; S45. If the system detects a potential equipment failure or performance degradation, it will automatically trigger the maintenance process, including Including sending alarm information to users or maintenance personnel; S5. Use network redundancy technology to ensure the stability of data transmission, including the use of multiple network channels and offline working mode; S6. Apply blockchain technology to record and verify all data transactions, including verifying the integrity, transparency and immutability of data; S7, automatically adjusts settings based on user habits, seasonal changes and weather conditions through self-learning and adaptive algorithms; S8. Integrate renewable energy and smart battery systems to improve the system's self-sufficiency and overall energy efficiency.

2. According to the method for monitoring and managing multi-device energy consumption based on the Internet of Things in claim 1, it is characterized in that: The S3 specifically includes: S31, the central processing server receives the cleaned, classified and preliminarily analyzed data from the edge computing device; S32. Use the Autoregressive Moving Average Model (ARMA) to conduct in-depth analysis of the received data: E t =α+β1E t-1 +β2E t-2 +...+b n E t-n +e t ; Among them, E t represents the energy consumption data at time point t, βi represents the autoregressive coefficient of the model, α is the constant term, and ε t is the error term, n represents the number of time points considered; S33. Analyze user behavior data B to identify usage patterns and preferences, and use K-means clustering algorithm to classify user behaviors into different groups to improve energy efficiency: Initialize K cluster centers, which represent different types of user behavior patterns C={c1,c2,..,c K }; For each user behavior data point B i , assigning it to the nearest cluster center: m 1≤j≤K |B i -c j |; Among them, |B i -c j | represents user behavior data point B i With cluster center c j The square of the Euclidean distance between them; Update the center point of each cluster to be the average of all user behavior data points belonging to that cluster: Among them, S j is the set of all data points in the jth cluster, |S j | is the number of data points in the cluster; S34, using support vector machine (SVM) for fault prediction, predicting and classifying potential equipment faults based on historical data and current data features: Where x represents the new input feature, n is the number of support vectors, and α i is the coefficient of the learned support vector, y i are the labels of the corresponding support vectors in the training set, <x i ,x> is the support vector x i The inner product between and the input feature x, b is the bias term of the model; S35. Organize the results of the in-depth analysis into a report and provide suggestions for energy consumption optimization and fault prevention of smart home devices.

3. According to the method for monitoring and managing multi-device energy consumption based on the Internet of Things in claim 1, it is characterized in that: The S5 specifically includes: S51. Assign a unique identifier ID to each network channel channel , monitor and manage different network paths; S53. Establish a network performance monitoring system to monitor the transmission quality of each network channel in real time, including delay δ and packet loss rate ρ: NSI = a·δ+b·(1-ρ); Among them, NSI is the network stability index, δ represents network delay, ρ represents packet loss rate, and a and b are the weight coefficients of the two respectively; S54, adopt offline working mode to ensure that smart home devices can maintain basic monitoring and management functions when the network is unstable or interrupted. The device will record and store key operation and event data, including energy consumption data E, user behavior data B and device status S status .

4. The method for monitoring and managing multi-device energy consumption based on the Internet of Things according to claim 1 is characterized in that: The S6 specifically includes: S61. Use blockchain technology to establish a distributed ledger system to record and verify energy consumption data E, user behavior data B and device status information S in a smart home environment. status ; S62. Generate a unique hash value H for each data transaction and store it in the blockchain together with the transaction data: H=f(E,B,S status ); Among them, H is the unique hash value of the data transaction, E, B and S status Represent energy consumption data, user behavior data, and device status information respectively; S63. Use smart contracts to automatically verify and execute data processing tasks. Each data transaction is time-stamped on the blockchain. The timestamp T is recorded in the blockchain together with the hash value H of each transaction, forming an irreversible time series record.

5. The method for monitoring and managing multi-device energy consumption based on the Internet of Things according to claim 1 is characterized in that: The S7 specifically includes: S71, implement self-learning and adaptive algorithms to enable the system to automatically adjust the operating parameters of smart home devices according to user behavior habits, seasonal changes and weather conditions; S72. Use time series analysis method to predict user behavior B and energy consumption demand E: Among them, B predict (t) and E predict (t) represent the predicted user behavior and energy consumption demand at the future time point t, α, β i ,γ,δ i are model parameters, B(ti) and E(ti) represent user behavior and energy consumption data at past time points; S73. Use a decision tree algorithm to classify and regress the historical data of user behavior B and energy consumption E, and generate decision rules to predict future user behavior and energy consumption requirements: Decision(B,E,t,W)=TreeRules(B,E,t,W); Among them, Decision represents the prediction result based on the decision tree, and TreeRules represents a series of decision rules learned from the data; S74. Based on the above prediction and analysis results, the system will automatically adjust the operating parameters of the smart home devices and regularly evaluate and adjust the performance of the self-learning and adaptive algorithms.

6. The method for monitoring and managing energy consumption of multiple devices based on the Internet of Things according to claim 1 is characterized in that: The S8 specifically includes: S81. Real-time monitoring of renewable energy generation through energy management system E gen and the energy E stored in the smart battery store : AND opt =η·E gen +(1-η)·E store ; Among them, E opt represents the optimized energy usage, η is the weight factor of renewable energy utilization; S82, based on real-time and predicted energy consumption data E predict and renewable energy supply data E gen , automatically adjust the energy consumption of smart home devices.