An Energy Consumption Optimization Method for Internet of Things Devices Based on Artificial Intelligence

Abstract

An energy consumption optimization method for Internet of Things devices based on artificial intelligence, comprising: S1, integrating data of Internet of Things devices and forming a multi-dimensional data fusion set by using multi-source data fusion technology; S2, dynamically establishing an energy consumption baseline model by using an adaptive regression algorithm; S3, monitoring the fluctuation deviation of energy consumption devices through fluctuation identification technology, quickly locating the abnormal energy consumption position by using an energy consumption detection mechanism, and diagnosing the cause of abnormal energy consumption; S4, inputting the energy consumption data and user behavior data into an intelligent energy consumption scheduling system to optimize the task scheduling of Internet of Things devices and reduce the energy consumption peak; S5, constructing an energy consumption peak optimization mechanism, optimizing the weights and thresholds of the Internet of Things, and achieving continuous reduction of energy consumption. Through multi-source data fusion, dynamic energy consumption baseline modeling, energy consumption anomaly detection and diagnosis, intelligent task scheduling, and continuous optimization mechanism, the present invention realizes the effective management and reduction of the energy consumption of Internet of Things devices, and improves the overall energy efficiency and user experience of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption management of Internet of Things devices, and specifically to an energy consumption optimization method for Internet of Things devices based on artificial intelligence. Background Art

[0002] In the context of the explosive growth in the number of Internet of Things devices and the complex and diverse application scenarios, traditional static or semi-static energy consumption management strategies are no longer sufficient to meet the requirements of efficient and flexible energy management. With the popularization of Internet of Things devices, the collaborative operation of a large number of devices generates a huge amount of data traffic and energy consumption. Especially for resource-constrained edge devices, how to balance performance and energy consumption has become an urgent problem to be solved.

[0003] Traditional energy consumption optimization methods often ignore the dynamic changes in the device operating state and the influence of external environmental factors, resulting in poor energy consumption optimization effects and limited device performance and battery life. In addition, Internet of Things devices are often deployed in a wide and variable environment, from indoor to outdoor, from stationary to mobile, from low temperature to high temperature. These unpredictable conditions require the device to have intelligent self-adjustment capabilities to adapt to different usage scenarios. Moreover, in traditional technologies for Internet of Things device energy consumption management, devices usually adopt preset energy consumption management strategies, fixed operating frequencies, power levels, and sleep cycles. These strategies are often determined at the device design stage and remain unchanged throughout the device life cycle. In addition, devices usually operate independently, lacking collaboration and information sharing with other devices. Energy consumption optimization is limited to the single-device level and fails to fully utilize environmental data and the status information of other devices for optimization to reduce energy consumption.

[0004] Chinese Patent CN118210240A (Publication Date: June 18, 2024) discloses a multi-device energy consumption monitoring and management method based on the Internet of Things. It uses Internet of Things sensors to collect energy consumption data, preliminarily analyzes the collected data through edge computing devices, transmits the processed data to a central processing server, deeply analyzes the data through algorithms, automatically adjusts operating parameters based on the analysis results of the algorithms, uses network redundancy technology to ensure the stability of data transmission, applies blockchain technology to record and verify all data transactions, including verifying the integrity, transparency, and immutability of data, automatically adjusts settings through self-learning and adaptive algorithms, and integrates renewable energy and intelligent battery systems. The above invention uses edge computing for data processing, reducing the dependence on the central server and improving the real-time performance and efficiency of data processing. At the same time, the integrated AI algorithm can achieve more accurate energy consumption prediction and management.

[0005] However, in terms of the dynamicity and accuracy of energy consumption optimization in the above patents, although artificial intelligence algorithms are used for energy consumption pattern recognition and user behavior analysis, the adjustment of device operating frequency, power, and sleep cycle may rely on the analysis results of the central processing server, which may lead to limited response speed and adjustment accuracy. At the same time, the rapid information exchange and two-way collaborative work between devices, mainly based on local data processing and swarm intelligence network optimization mechanisms, may not fully exploit the potential of deep collaboration between devices, especially in making advanced decisions using swarm intelligence. Although self-learning and adaptive algorithms are introduced, their adaptive capabilities may mainly focus on predicting user behavior and seasonal changes, and may be insufficient in the immediate response to changes in the device's own state and sudden environmental events.

[0006] To solve the above problems, the present invention provides an energy consumption optimization method for Internet of Things devices based on artificial intelligence, achieving high dynamicity and accuracy in energy consumption optimization. Through an optimization mechanism, the device can make advanced decisions based on new data and environmental changes, optimize the energy consumption model and strategy, and combine with a multi-dimensional energy consumption analysis model to ensure the comprehensiveness and intelligence of energy consumption management. An adaptive energy consumption optimization adjustment mechanism is designed to enable the system to automatically adjust the optimization strategy according to real-time feedback, realizing true adaptive energy consumption management. Summary of the Invention

[0007] An energy consumption optimization method for Internet of Things devices based on artificial intelligence includes the following steps:

[0008] S1. Integrate energy consumption data, user behavior data, and environmental interaction data from Internet of Things devices, and use multi-source data fusion technology to form a multi-dimensional data fusion set;

[0009] S2. Dynamically establish an energy consumption baseline model using an adaptive regression algorithm based on the multi-dimensional data fusion set to reflect the normal fluctuation range of device energy consumption;

[0010] S3. Monitor the fluctuation deviation of energy consumption devices through fluctuation recognition technology, and use an energy consumption detection mechanism to quickly locate the position of abnormal energy consumption and diagnose the cause of abnormal energy consumption;

[0011] S4. Input the energy consumption data and user behavior data into an intelligent energy consumption scheduling system to optimize the task scheduling of Internet of Things devices, solve the cause of abnormal energy consumption, and reduce the energy consumption peak;

[0012] S5. Construct an energy consumption peak optimization mechanism, combine user feedback and system performance data, optimize the weights and thresholds of the Internet of Things, and achieve continuous reduction of energy consumption and improvement of system performance.

[0013] Preferably, S1 specifically includes: unifying the energy consumption data E, user behavior data U, and environmental interaction data A in the Internet of Things device to the same scale to eliminate the influence of dimensions;

[0014] Given the original data point X of the energy consumption data E, user behavior data U, and environmental interaction data A for a feature j j , and converting it into a standard data point X' through the formula j :

[0015]

[0016] where min(X j ) is the minimum value of the j-th feature, and max(X j ) is the maximum value of the j-th feature;

[0017] Select the feature j in the Internet of Things device according to the standard data point X' j , calculate the absolute correlation coefficient |ρ j |, and judge the correlation between the feature j and the energy consumption according to |ρ j |>r threshold . When |ρ j |>r threshold , the feature j is directly related to the energy consumption; otherwise, it is not related;

[0018]

[0019] where X' j.i is the i-th sample of the standardized feature j, Y i is the energy consumption value of the i-th sample, and are the means of the feature j and the energy consumption respectively, n is the number of samples, and r threshold is the set correlation coefficient threshold;

[0020] Let w E , w U and w A be the weights of the energy consumption data, user behavior data, and environmental interaction data respectively. Then the multi-dimensional fusion dataset Z is:

[0021] Z = (w E E + w U U + w A A)

[0022] where w E is the weight of the energy consumption data, w U is the weight of the user behavior data, and w A is the weight of the environmental interaction data.

[0023] Preferably, the S2 specifically includes: extracting a feature set F directly related to energy consumption from the multi-dimensional fusion data set Z, and adding the feature j that meets the conditions to the feature set F;

[0024] Assume that the feature set F contains k features, and establish an energy consumption baseline model to predict the energy consumption value k i :

[0025]

[0026] where, k0 is the intercept term, k j is the weight coefficient of the j-th feature, F j is the j-th feature in the feature set F, and k is the number of features in the feature set F;

[0027] For the construction of the optimal energy consumption model, through a set of parameters, the energy consumption value predicted by the optimal energy consumption model is close to the actually observed energy consumption value:

[0028]

[0029] Assume that the predicted value of the model is k i , calculate the mean value i of the predicted value k and the standard deviation σ p , and the normal fluctuation range of the energy consumption of the Internet of Things device is where, c is the range constant.

[0030] Preferably, the energy consumption anomaly detection in the S3 specifically includes:

[0031] Detect energy consumption anomalies through the fluctuation deviation D between the energy consumption value and the predicted value;

[0032] The formula for the fluctuation deviation D is:

[0033] D = Y i - k i

[0034] When |D| > δ, there is an abnormal situation, where δ is the set deviation threshold.

[0035] Preferably, the energy consumption anomaly location in the S3 specifically includes:

[0036] Confirm the energy consumption anomaly location through the standard deviation σ D of the fluctuation deviation D;

[0037] The standard deviation σ D is:

[0038]

[0039] where c is the detection constant, D i is the fluctuation deviation value of the i-th one, is the fluctuation deviation D;

[0040] If the mean value of D and |D| > c·σ D , there is an abnormality in the energy consumption data. If |D| < c·σ D , there is an abnormality in the user behavior data.

[0041] Preferably, the intelligent energy consumption scheduling system in S4 includes: an optimization module and an energy consumption peak smoothing module;

[0042] The optimization module will optimize the execution plan of the Internet of Things device tasks and reduce the peak value of the Internet of Things energy consumption;

[0043] The energy consumption peak smoothing module dynamically adjusts the task execution time and order of the Internet of Things devices to reduce the energy consumption peak of the intelligent energy consumption scheduling system.

[0044] Preferably, the optimization module of the intelligent energy consumption scheduling system in S4 specifically includes:

[0045] The energy consumption data E and the user behavior data U optimize the execution time and order of the device tasks through the optimization module, and use the optimization algorithm to schedule the device task list T:

[0046] The device task list T = {t1, t2,..., t i};

[0047] where, t i represents the i-th device task;

[0048] For each device task t i , use the energy consumption data E to evaluate its expected energy consumption E i :

[0049]

[0050] where, w j is the weight at the j-th time point, and E(t i , j) represents the expected energy consumption of the i-th device task at the j-th time point;

[0051] Use the optimization algorithm to sort and allocate time for the device task list T:

[0052]

[0053] where, T' represents all possible task scheduling schemes, and T opt is the optimal scheduling scheme, and E i$E_{i}(T')$ is the energy consumption of the $i$-th task under the scheduling $T'$.

[0054] Preferably, the energy consumption peak smoothing module of the intelligent energy consumption scheduling system in S4 specifically includes:

[0055] The energy consumption peak smoothing module adopts dynamic adjustment of the task execution time and order of devices to reduce the energy consumption peak;

[0056] For each Internet of Things device $d$, according to the optimized device scheduling scheme $T$ opt , calculate the energy consumption $E$ of the Internet of Things device d ;

[0057]

[0058] where $I(t$ i , $t)$ represents the indicator function, which takes 1 when device $d$ executes task $t$ i at time $t$, and 0 otherwise;

[0059] Adjust the execution time and order of devices through an optimization algorithm to calculate the minimum energy consumption peak $E$ p ;

[0060]

[0061] The optimized minimum energy consumption peak $E$ p .

[0062] Preferably, the weight optimization of the energy consumption peak optimization mechanism in S5 specifically includes:

[0063] The weight optimization collects user feedback to evaluate the actual performance of the system, combines it with the system performance indicators, and the user feedback is quantitative information regarding energy consumption awareness, device availability, and satisfaction;

[0064] The set defines the user feedback factor $f$ u

[0065]

[0066] where $s$ i is the satisfaction score of the $i$-th user, $\overline{s}$ avg is the average satisfaction score, $N$ is the number of users participating in the feedback, and the weight parameter is adjusted using the user feedback factor $f$ u ;

[0067] The weights of the energy consumption data $E$, user behavior data $U$, and environmental interaction data $A$ are adjusted according to the user feedback factor $f$ u to update the optimization parameters;

[0068] $w$E ' = α + f u ·λ1

[0069] w U ' = β + f u ·λ2

[0070] w A ' = γ + f u ·λ3

[0071] Among them, λ1, λ2, and λ3 are learning rates for updating the weights of energy consumption data E, user behavior data U, and environmental interaction data A, respectively.

[0072] Preferably, the threshold optimization of the energy consumption peak optimization mechanism in S5 specifically includes:

[0073] Determining the difference between the actual energy consumption and the predicted energy consumption through system performance data, and adjusting the optimization parameters accordingly

[0074] Defining the performance difference factor f p :

[0075]

[0076] Among them, E pi is the predicted energy consumption at the i-th time point, and E ai is the actual energy consumption at the i-th time point;

[0077] The update formula for the anomaly detection threshold is:

[0078] δ′ = δ + f p ·η

[0079] Among them, η is the learning rate for updating the anomaly detection threshold;

[0080] The update formula for the fluctuation range constant is:

[0081] c′ = c + f p ·ξ

[0082] Among them, ξ is the learning rate for updating the fluctuation range constant.

[0083] The present invention uses multi-source data fusion technology for data with different dimensions and scales from different sources, unifies these data to the same scale, can eliminate the influence of dimensions, and enables effective integration and analysis of different types of energy consumption-related data.

[0084] The present invention dynamically establishes an energy consumption baseline model using an adaptive regression algorithm, solves the problem of the device's energy consumption changing over time and being difficult to reflect the normal energy consumption fluctuation range, provides an energy consumption level that can accurately reflect the normal working state of the device, and provides a benchmark for subsequent energy consumption anomaly detection.

[0085] The present invention detects and diagnoses energy consumption anomalies through fluctuation identification technology and fluctuation deviation analysis, can timely discover energy consumption anomalies, and distinguish whether the energy consumption data itself or the anomalies caused by user behavior.

[0086] The present invention dynamically adjusts the task execution time and sequence of the device through an optimization algorithm, effectively reduces the energy consumption peak, and realizes more efficient energy consumption management.

[0087] The present invention combines user feedback and system performance data, continuously adjusts and optimizes the strategy, can continuously improve the energy consumption management strategy, improve the system performance and enhance the user experience.

[0088] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, so as to be implemented in accordance with the content of the description, and in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following takes the preferred embodiments of this application and combines the drawings to describe in detail as follows.

[0089] According to the following detailed description of the specific embodiments of this application in combination with the drawings, those skilled in the art will be more clear about the above and other purposes, advantages and features of this application. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to actual scale.

[0091] Figure 1 Steps diagram of the energy consumption management method for Internet of Things devices with dynamic feedback;

[0092] Figure 2 Steps diagram of the multi-dimensional data fusion set;

[0093] Figure 3 Steps diagram of the energy consumption baseline model;

[0094] Figure 4 Steps diagram of the anomaly detection of fluctuation deviation;

[0095] Figure 5 It is a flowchart for energy consumption optimization steps. Specific embodiments

[0096] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. In the following description, specific details such as specific configurations and components are provided only to assist in a comprehensive understanding of the embodiments of the present application. Therefore, those skilled in the art should clearly understand that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Additionally, descriptions of known functions and structures are omitted for clarity and conciseness.

[0097] It should be understood that the phrase "an embodiment" or "the embodiment" mentioned throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the present application. Therefore, the phrase "an embodiment" or "the embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.

[0098] In addition, the present application may repeat reference numerals and / or letters in different instances. This repetition is for the purpose of simplicity and clarity and does not in itself indicate the relationship between the various embodiments and / or arrangements discussed.

[0099] The term "and / or" in this document is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, B exists alone, and both A and B exist simultaneously. The term " / and" in this document is a description of another association relationship of associated objects, indicating that two relationships may exist. For example, A / and B may represent: A exists alone, and both A and B exist. Additionally, the character " / " in this document generally indicates that the associated objects before and after are in an "or" relationship.

[0100] The term "at least one" in this document is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, at least one of A and B may represent: A exists alone, both A and B exist simultaneously, and B exists alone.

[0101] It should also be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion.

[0102] Embodiment 1

[0103] This embodiment mainly and specifically describes a specific implementation scheme of an energy consumption optimization method for Internet of Things devices based on artificial intelligence;

[0104] As Figure 1 shown, an energy consumption optimization method for Internet of Things devices based on artificial intelligence includes the following steps:

[0105] S1. Integrate the energy consumption data, user behavior data, and environmental interaction data from the Internet of Things devices, and use multi-source data fusion technology to form a multi-dimensional data fusion set;

[0106] S2. Dynamically establish an energy consumption baseline model according to the multi-dimensional data fusion set by using an adaptive regression algorithm to reflect the normal fluctuation range of device energy consumption;

[0107] S3. Monitor the fluctuation deviation of the energy consumption device through fluctuation identification technology, and use the energy consumption detection mechanism to quickly locate the abnormal energy consumption position and diagnose the cause of abnormal energy consumption;

[0108] S4. Input the energy consumption data and user behavior data into the intelligent energy consumption scheduling system to optimize the task scheduling of the Internet of Things devices, solve the cause of abnormal energy consumption, and reduce the energy consumption peak;

[0109] S5. Build an energy consumption peak optimization mechanism, combine user feedback and system performance data, optimize the weights and thresholds of the Internet of Things, and achieve continuous energy consumption reduction and system performance improvement.

[0110] Furthermore, as Figure 2 shown, unify the energy consumption data E, user behavior data U, and environmental interaction data A in the Internet of Things devices to the same scale to eliminate the influence of dimensions; give the energy consumption data E, user behavior data U, and environmental interaction data A the original data point X of a feature j j , and convert it into a standard data point X' through the formula j :

[0111]

[0112] where, min(X j ) is the minimum value of the j-th feature, and max(X j ) is the maximum value of the j-th feature;

[0113] According to the standard data point X' j Select the feature j in the Internet of Things device, and calculate the absolute correlation coefficient |ρ j |. According to |ρ j |>r threshold Judge the correlation between the feature j and the energy consumption. The setting of r threshold usually takes values between [-1, 1]. Being close to 1 indicates a positive correlation, being close to -1 indicates a negative correlation, and being close to 0 indicates almost no linear correlation. Set r threshold to take 0.5 - 0.7; when |ρ j |>r threshold , then the feature j is directly related to the energy consumption; otherwise, it is not related;

[0114]

[0115] where, X' j.i is the i-th sample of the standardized feature j, Y i is the energy consumption value of the i-th sample, and are the means of the feature j and the energy consumption respectively, n is the number of samples, and r threshold is the set correlation coefficient threshold;

[0116] Let w E , w U and w A be the weights of the energy consumption data, user behavior data, and environmental interaction data respectively. Initially, set the weight of w E to be greater than the weights of w U and w A . The multi-dimensional fusion data set Z is:

[0117] Z = (w E E + w U U + w A A)

[0118] where, w E is the weight of the energy consumption data, w U is the weight of the user behavior data, and w A is the weight of the environmental interaction data;

[0119] After determining that the feature is directly related to the energy consumption in S1, set the weights w E , w U and w A to ensure that in the subsequent energy consumption management process, the processing of features is more reasonable and effective, so as to achieve better energy consumption management and optimization effects.

[0120] Furthermore, as Figure 3As shown, S2 specifically includes: extracting the feature set F directly related to energy consumption from the multi-dimensional fusion data set Z, and adding the feature j that meets the conditions to the feature set F;

[0121] Assume that the feature set F contains k features, and establish an energy consumption baseline model to predict the energy consumption value k i :

[0122]

[0123] where k0 is the intercept term, k j is the weight coefficient of the jth feature, F j is the jth feature in the feature set F, and k is the number of features in the feature set F;

[0124] Construct an optimal energy consumption model, and through the intercept term k0 and the feature weight coefficient k j parameters, make the energy consumption value predicted by the optimal energy consumption model close to the actually observed energy consumption value:

[0125]

[0126] Set the predicted value of the model to k i and calculate the mean value i of the predicted value k and the standard deviation σ p . The normal fluctuation range of the energy consumption of the Internet of Things device is where c is the range constant. For first-level energy consumption requirements, c usually takes 3, for second-level energy consumption, c usually takes 2, and for third-level energy consumption, c usually takes 1.

[0127] Furthermore, as Figure 4 shown, the energy consumption anomaly detection in S3 specifically includes:

[0128] Detect energy consumption anomalies through the fluctuation deviation D between the energy consumption value and the predicted value;

[0129] The formula for the fluctuation deviation D is:

[0130] D = Y i - k i

[0131] When |D| > δ, there is an abnormal situation, where δ is the set deviation threshold.

[0132] Furthermore, the specific location of the energy consumption anomaly in S3 includes:

[0133] Confirm the location of the energy consumption anomaly through the standard deviation σ D of the fluctuation deviation D;

[0134] The standard deviation σ D is:

[0135]

[0136] where c is the detection constant, D i is the fluctuation deviation value of the i-th one, is the fluctuation deviation D;

[0137] If the mean value of the fluctuation deviation D is such that |D| > c·σ D , there is an abnormality in the energy consumption data. If |D| < c·σ D , there is an abnormality in the user behavior data.

[0138] Furthermore, the intelligent energy consumption scheduling system in S4 includes: an optimization module and an energy consumption peak smoothing module;

[0139] The optimization module will optimize the execution plan of the Internet of Things device tasks and reduce the peak value of the Internet of Things energy consumption;

[0140] The energy consumption peak smoothing module dynamically adjusts the task execution time and order of the Internet of Things devices to reduce the energy consumption peak of the intelligent energy consumption scheduling system.

[0141] Furthermore, as Figure 5 shown, the steps of the optimization module of the intelligent energy consumption scheduling system in S4 include:

[0142] The energy consumption data E and the user behavior data U are used by the optimization module to optimize the execution time and order of the device tasks, and an optimization algorithm is used to schedule the device task list T:

[0143] The device task list T = {t1, t2,..., t i};

[0144] where, t i represents the i-th device task;

[0145] For each device task t i , the energy consumption data E is used to evaluate its expected energy consumption E i :

[0146]

[0147] where, w j is the weight at the j-th time point, and E(t i , j) represents the expected energy consumption of the i-th device task at the j-th time point;

[0148] An optimization algorithm is used to sort and allocate time to the device task list T:

[0149]

[0150] Among them, T' represents all possible task scheduling schemes, and T opt is the optimal scheduling scheme, and E i (T') is the energy consumption of the i-th task under the scheduling T'.

[0151] Furthermore, the energy consumption peak smoothing module of the intelligent energy consumption scheduling system in S4 specifically includes:

[0152] The energy consumption peak smoothing module adopts dynamic adjustment of the task execution time and order of devices to reduce the energy consumption peak;

[0153] For each Internet of Things device d, according to the optimized device scheduling scheme T opt , calculate the energy consumption E of the Internet of Things device d ;

[0154]

[0155] Among them, I(t i , t) represents the indicator function, which takes 1 when the device d executes the task t i at time t, and takes 0 otherwise;

[0156] Adjust the execution time and order of devices through an optimization algorithm to calculate the minimum energy consumption peak E p ;

[0157]

[0158] After optimization, the minimized energy consumption peak E p is obtained.

[0159] Furthermore, the weight optimization of the energy consumption peak optimization mechanism in S5 specifically includes:

[0160] The weight optimization collects user feedback to evaluate the actual performance of the system, combines it with the system performance indicators, and the user feedback is quantitative information regarding energy consumption awareness, device availability, and satisfaction;

[0161] Set and define the user feedback factor f u

[0162]

[0163] Among them, s i is the satisfaction score of the i-th user, s avg is the average satisfaction score, N is the number of users participating in the feedback, and use the user feedback factor f u to adjust and optimize the weight parameters;

[0164] According to the user feedback factor f uAdjust the weights of the energy consumption data E, user behavior data U, and environmental interaction data A, and update the optimization parameters;

[0165] w E ' = α + f u ·λ1

[0166] w U ' = β + f u ·λ2

[0167] w A ' = γ + f u ·λ3

[0168] Among them, λ1, λ2, and λ3 are the learning rates for updating the weights of the energy consumption data E, user behavior data U, and environmental interaction data A respectively.

[0169] Furthermore, the threshold optimization of the energy consumption peak optimization mechanism in S5 specifically includes:

[0170] Determine the difference between the actual energy consumption and the predicted energy consumption through the system performance data, and adjust the optimization parameters accordingly;

[0171] Define the performance difference factor f p :

[0172]

[0173] Among them, E pi is the predicted energy consumption at the i-th time point, and E ai is the actual energy consumption at the i-th time point;

[0174] The update formula for the anomaly detection threshold is:

[0175] δ' = δ + f p ·η

[0176] Among them, η is the learning rate for updating the anomaly detection threshold;

[0177] The update formula for the fluctuation range constant is:

[0178] c' = c + f p ·ξ

[0179] Among them, ξ is the learning rate for updating the fluctuation range constant.

[0180] Through the specific description of an energy consumption optimization method for Internet of Things devices based on artificial intelligence in this embodiment, through multi-source data fusion, dynamic energy consumption baseline modeling, energy consumption anomaly detection and diagnosis, intelligent task scheduling, and continuous optimization mechanism, the effective management and reduction of the energy consumption of Internet of Things devices are achieved, and the overall energy efficiency of the system and the user experience are improved.

[0181] Example 2

[0182] Based on Example 1, this example will be specifically described with examples;

[0183] There are two Internet of Things devices d1 and d2 in a certain area, and each device will generate energy consumption data E, user behavior data U, and environmental interaction data A;

[0184] The energy consumption data of devices d1 and d2 are 100 and 120 units of energy consumption respectively;

[0185] The user behavior data U are active times of 3 minutes and 4 minutes respectively;

[0186] The environmental interaction data A are temperatures of 25°C and 28°C respectively.

[0187] The data is standardized to eliminate the influence of dimensions. The minimum value of the energy consumption data is 100, and the maximum value is 120; the minimum value of the user behavior data is 3, and the maximum value is 4; the minimum value of the environmental interaction data is 25, and the maximum value is 28;

[0188] Converted to standardized data:

[0189] Device d1: X' E1 = 0, X' U1 = 0, X' A1 = 0;

[0190] Device d2: X' E2 = 1, X' U2 = 1, X' A2 = 1;

[0191] Calculate the correlation between features and energy consumption. Assume that the correlation coefficient between energy consumption data and energy consumption is 0.9, the correlation coefficient between user behavior data and energy consumption is 0.6, and the correlation coefficient between environmental interaction data and energy consumption is 0.75.

[0192] Correlation coefficient threshold r threshold Is set to 0.5, so all features are considered to be directly related to energy consumption.

[0193] Assume that the weight w of the energy consumption data E = 0.5, the weight w of the user behavior data U = 0.3, the weight w of the environmental interaction data A = 0.2;

[0194] The multi-dimensional fusion dataset Z is:

[0195] Device d1: Z1 = 0.5·0 + 0.3·0 + 0.2·0 = 0;

[0196] Device d2: Z2 = 0.5·1 + 0.3·1 + 0.2·1 = 1;

[0197] Suppose the feature set F contains three features, energy consumption data, user behavior data, and environmental interaction data;

[0198] An energy consumption baseline model is established to predict the energy consumption value. The intercept term k0 of the model is set to 50, and the feature weight coefficients k j are respectively k E = 50, k U = 30, k A = 20;

[0199] The energy consumption baseline model is:

[0200] k i = 50 + 50·Z E + 30·Z U + 20·Z A ;

[0201] where Z E , Z U and Z A are respectively the values of the energy consumption data, user behavior data, and environmental interaction data in the multi-dimensional fusion dataset Z;

[0202] Calculate the mean standard deviation σ p = 10;

[0203] The range constant c is set to 2, so the normal fluctuation range is [90, 130];

[0204] The actual observed energy consumption values of devices d1 and d2 are 115 and 140 unit energy consumptions respectively.

[0205] According to the energy consumption baseline model, the predicted energy consumption values are 100 and 120 unit energy consumptions respectively.

[0206] The fluctuation deviations D are respectively:

[0207] Device d1: D1 = 115 - 100 = 15;

[0208] Device d2: D2 = 140 - 120 = 20;

[0209] The deviation threshold δ is set to 10 unit energy consumption;

[0210] The fluctuation deviation |D1| of device d1 = 15 > δ, there is an anomaly;

[0211] The fluctuation deviation |D2| of device d2 = 20 > δ, there is also an anomaly.

[0212] The standard deviation σD of the fluctuation deviation D is assumed to be 5;

[0213] The detection constant c is set to 2;

[0214] Therefore, the standard deviation σ D = 5;

[0215] The fluctuation deviations of devices d1 and d2 are both greater than c·σ D = 2·5 = 10, indicating that there are anomalies in the energy consumption data.

[0216] The task lists T of devices d1 and d2 include four tasks:

[0217] T = {t1, t2, t3, t4}

[0218] Each task t i represents an operation that a device needs to perform;

[0219] For each device task t i , we need to use the energy consumption data to evaluate its expected energy consumption E i ;

[0220] Each task can be executed at multiple time points during a day. We consider each time point as a time period. A day is divided into two time periods: morning and afternoon, and each time period has a weight w j , representing the degree of influence of this time period on energy consumption;

[0221] The weight w1 of the first time period (morning) = 0.6;

[0222] The weight w2 of the second time period (afternoon) = 0.4;

[0223] Suppose the expected energy consumption of each task in the two time periods is as follows:

[0224] t1: E(t1,1) = 20 units of energy consumption in the morning, E(t1,2) = 30 units of energy consumption in the afternoon;

[0225] t2: E(t2,1) = 25 units of energy consumption in the morning, E(t2,2) = 20 units of energy consumption in the afternoon;

[0226] t3: E(t3,1) = 35 units of energy consumption in the morning, E(t3,2) = 15 units of energy consumption in the afternoon;

[0227] t4: E(t4,1) = 15 units of energy consumption in the morning, E(t4,2) = 40 units of energy consumption in the afternoon;

[0228] Calculate the expected energy consumption E i ;

[0229]

[0230] E1 = 0.6×20 + 0.4×30 = 12 + 12 = 24;

[0231] E2 = 0.6×25 + 0.4×20 = 15 + 8 = 23;

[0232] E3 = 0.6×35 + 0.4×15 = 21 + 6 = 27;

[0233] E4 = 0.6×15 + 0.4×40 = 9 + 16 = 25;

[0234] Use an optimization algorithm to find the optimal scheduling scheme T opt :

[0235] Calculate the total energy consumption of the current scheduling scheme:

[0236] E(T) = E1 + E2 + E3 + E4 = 24 + 23 + 27 + 25 = 99;

[0237] T' = {t1, t2, t3, t4}

[0238] Exchange the execution order of the tasks. Assume the first attempt: swap the positions of t1 and t4 to get a new scheduling scheme, and evaluate the total energy consumption of the new scheduling scheme;

[0239] Calculate the total energy consumption of E(T'). If the total energy consumption of the new scheme is lower, then adopt the new scheme; otherwise, keep the original scheme unchanged until the lowest energy consumption scheme is obtained;

[0240] Assume the optimal scheduling scheme is

[0241] T' = {t4, t2, t3, t1}

[0242] Device d1 is responsible for executing tasks t1 and t3;

[0243] Device d2 is responsible for executing tasks t2 and t4;

[0244] Calculate the energy consumption E according to the optimized device scheduling scheme Topt d ;

[0245] The energy consumption E of device d1 d1 :

[0246] The expected energy consumption E1 of task t1 = 24;

[0247] The expected energy consumption E3 of task t3 = 27.

[0248] Device d1 executes tasks t1 and t3 in the morning and afternoon respectively;

[0249] Therefore, the energy consumption E of device d1 in the morningd1 is:

[0250] E d1 = E1·I(t1, morning) + E3·I(t3, afternoon);

[0251] Since t1 is executed in the morning and t3 is executed in the afternoon, so: E d1 = 24·1 + 27·1 = 51;

[0252] The energy consumption E of device d2 d2 :

[0253] The expected energy consumption E2 of task t2 = 23;

[0254] The expected energy consumption E4 of task t4 = 25.

[0255] The execution times of task t2 and t4 by device d2 are in the morning and afternoon respectively;

[0256] Therefore, the energy consumption E of device d2 in the morning d2 is: E d2 = E2·I(t2, morning) + E4·I(t4, afternoon);

[0257] Since t2 is executed in the morning and t4 is executed in the afternoon, so: E d2 = 23·1 + 25·1 = 48;

[0258] Calculate the minimized peak energy consumption E p ;

[0259] The maximum energy consumption of device d1 is 51;

[0260] The maximum energy consumption of device d2 is 48.

[0261] Minimize the peak energy consumption E p :

[0262]

[0263] Achieve the minimization of peak energy consumption by dynamically adjusting the task execution time and order of devices.

[0264] Collect user feedback and optimize the peak energy consumption mechanism:

[0265] Obtain the user feedback factor through the feedback formula:

[0266]

[0267] The user feedback factor f u = 0.2;

[0268] Learning rates: λ1 = 0.1, λ2 = 0.1, λ3 = 0.1;

[0269] The updated weight is:

[0270] w E = w E + λ1·f u = 0.5 + 0.1·0.2 = 0.52

[0271] w U = w U + λ2·f u = 0.3 + 0.1·0.2 = 0.32

[0272] w A = w A + λ3·f u = 0.2 + 0.1·0.2 = 0.22

[0273] Determine the difference between the actual energy consumption and the predicted energy consumption through the system performance data, and adjust the optimization parameters accordingly. Define the performance difference factor f p :

[0274]

[0275] Performance difference factor f p = 5;

[0276] Learning rate η = 0.05, ξ = 0.05;

[0277] The update formula for the anomaly detection threshold is:

[0278] δ' = δ + f p ·η = δ + 0.05·5;

[0279] The update formula for the fluctuation range constant is:

[0280] c' = c + f p ·ξ = c + 0.05·5;

[0281] The optimized anomaly detection threshold and fluctuation range constant will further optimize the scheduling scheme of the Internet of Things and reduce the energy consumption peak.

[0282] In this embodiment, the intelligent energy consumption scheduling system is optimized through a specific Internet of Things device to reduce the energy consumption peak. The weights and thresholds are optimized through user feedback and system performance data, achieving continuous energy consumption reduction and system performance improvement, ensuring that the overall system can operate efficiently and stably, and can adapt to changing environments and user needs;

[0283] The above are only the preferred embodiments of the present invention, and thus do not limit the protection scope of the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any changes, modifications, substitutions, integrations, and parameter changes made to these embodiments without departing from the principle and spirit of the present invention by means of conventional substitutions or capable of achieving the same functions fall within the protection scope of the present invention.

Claims

1. A method for optimizing energy consumption of IoT devices based on artificial intelligence, characterized in that: The following steps are involved: S1, integrate energy consumption data, user behavior data and environmental interaction data from IoT devices, and use multi-source data fusion technology to form a multi-dimensional data fusion set; S2. Dynamically establish an energy consumption baseline model using an adaptive regression algorithm based on the multi-dimensional data fusion set to reflect the normal fluctuation range of equipment energy consumption; S3. Monitor the fluctuation deviation of energy-consuming equipment through fluctuation identification technology, use energy consumption detection mechanism to quickly locate abnormal energy consumption, and diagnose the cause of abnormal energy consumption; S4, transferring energy consumption data and user behavior data to the intelligent energy consumption scheduling system to optimize the task scheduling of IoT devices, solve the causes of abnormal energy consumption, and reduce energy consumption peaks; S5. Build an energy consumption peak optimization mechanism, combine user feedback and system performance data, optimize the weight and threshold of the Internet of Things, and achieve continuous energy consumption reduction and system performance improvement; In S2, a feature set F directly related to energy consumption is extracted from the multidimensional fusion data set Z, and the feature j that meets the conditions is added to the feature set F; Assume that the feature set F contains k features and establish an energy consumption baseline model to predict the energy consumption value k i : Among them, k0 is the intercept term, k j is the weight coefficient of the jth feature, F j is the jth feature in the feature set F, k is the number of features in the feature set F; Construct an optimal energy consumption model, and through a set of parameters, make the energy consumption value predicted by the optimal energy consumption model close to the actual observed energy consumption value: Set the model's prediction value to k i , calculate the predicted value k i The mean and standard deviation σ p , the normal fluctuation range of energy consumption of IoT devices is Where c is the range constant.

2. According to the method for optimizing energy consumption of IoT devices based on artificial intelligence in claim 1, it is characterized in that: S1 specifically includes: unifying the energy consumption data E, user behavior data U and environmental interaction data A in the IoT devices to the same scale to eliminate the impact of the dimension; The energy consumption data E, user behavior data U and environment interaction data A are given an original data point X with feature j j , which is converted into the standard data point X′ by the formula j : Among them, min(X j ) is the minimum value of the jth feature, max(X j ) is the maximum value of the jth feature; According to the standard data point X' j Select feature j in the IoT device and calculate the absolute correlation coefficient |ρ j ∣, according to ∣ρ j ∣>r threshold Determine the correlation between feature j and energy consumption, when |ρ j ∣>r threshold , then feature j is directly related to energy consumption, otherwise, it is not related; Among them, X′ j.i is the i-th sample of feature j after standardization, Y i is the energy consumption value of the i-th sample, and are the mean of feature j and energy consumption, n is the number of samples, r threshold is the set correlation coefficient threshold; Assume w E 、w U and w A are the weights of energy consumption data, user behavior data, and environmental interaction data, respectively. The multidimensional fusion data set Z is: Z=(w E E+w U U+w A A) Among them, w E is the weight of energy consumption data, w U is the weight of user behavior data, w A is the weight of the environmental interaction data.

3. According to the method for optimizing energy consumption of IoT devices based on artificial intelligence in claim 1, it is characterized in that: The energy consumption anomaly detection in S3 specifically includes: Detect energy consumption anomalies through the fluctuation deviation D between the energy consumption value and the predicted value; The formula of the fluctuation deviation D is: D=Y i -k i When |D|>δ, an abnormal situation exists, where δ is the set deviation threshold.

4. The method for optimizing energy consumption of IoT devices based on artificial intelligence according to claim 1 or 3, characterized in that: The energy consumption abnormality locations in S3 specifically include: By the standard deviation σ of the fluctuation deviation D D Confirm the location of abnormal energy consumption; The standard deviation σ D for: Where c is the detection constant, D i is the fluctuation deviation value of the ith one, is the fluctuation deviation D; The mean of D is if |D|>c·σ D , then there is an abnormality in the energy consumption data. If |D|<c·σ D , then there are anomalies in user behavior data.

5. The method for optimizing energy consumption of IoT devices based on artificial intelligence according to claim 1, characterized in that: The intelligent energy consumption scheduling system in S4 includes: an optimization module and an energy consumption peak smoothing module; The optimization module will optimize the execution plan of IoT device tasks and reduce the peak energy consumption of IoT; The energy consumption peak smoothing module dynamically adjusts the task execution time and sequence of the Internet of Things devices to reduce the energy consumption peak of the intelligent energy consumption scheduling system.

6. The method for optimizing energy consumption of IoT devices based on artificial intelligence according to claim 1 or 5, characterized in that: The optimization module of the intelligent energy consumption scheduling system in S4 specifically includes: The energy consumption data E and user behavior data U are used to optimize the execution time and sequence of device tasks through the optimization module, and the device task list T is scheduled using the optimization algorithm: The equipment task list T = {t1, t2, ..., t i }; Among them, t i represents the i-th device task; For each device task t i , using the energy consumption data E to evaluate its expected energy consumption E i Among them, w j is the weight at the jth time point, E(t i , j) represents the expected energy consumption of the i-th device task at the j-th time point; Use the optimization algorithm to sort and allocate the time of the equipment task list T: Among them, T′ represents all possible task scheduling schemes, T opt is the optimal scheduling solution, E i (T′) is the energy consumption of the ith task under schedule T′.

7. The method for optimizing energy consumption of IoT devices based on artificial intelligence according to claim 1, characterized in that: The energy consumption peak smoothing module of the intelligent energy consumption scheduling system in S4 specifically includes: The energy consumption peak smoothing module dynamically adjusts the task execution time and sequence of the equipment to reduce the energy consumption peak; For each IoT device d, according to the optimized device scheduling scheme T opt , calculate the energy consumption E of IoT devices d ; Among them, I(t i , t) represents the indicator function, when device d performs task t at time t i When it is 1, otherwise it is 0; The optimization algorithm is used to adjust the execution time and sequential calculation of the equipment to minimize the peak energy consumption E p ; The energy consumption peak E obtained after the optimization is minimized p .

8. The method for optimizing energy consumption of IoT devices based on artificial intelligence according to claim 1, characterized in that: The weight optimization of the energy consumption peak optimization mechanism in S5 specifically includes: The weight optimization collects user feedback to evaluate the actual performance of the system and combines it with the system performance indicators. The user feedback is quantitative information about energy consumption perception, equipment availability and satisfaction. Set the user feedback factor f u Among them, s i is the satisfaction score of the i-th user, s avg is the average satisfaction score, N is the number of users who participated in the feedback, and the user feedback factor f is used u Adjust optimization weight parameters; According to the user feedback factor f u Adjust the weights of energy consumption data E, user behavior data U, and environmental interaction data A, and update the optimization parameters; w E ′=α+f u ·λ1 w U ′=β+f u ·λ2 w A ′=γ+f u ·λ3 Among them, λ1, λ2, and λ3 are the learning rates used to update the weights of energy consumption data E, user behavior data U, and environmental interaction data A, respectively.

9. The method for optimizing energy consumption of IoT devices based on artificial intelligence according to claim 1, characterized in that: The threshold optimization of the energy consumption peak optimization mechanism in S5 specifically includes: Use system performance data to determine the difference between actual energy consumption and predicted energy consumption, and adjust optimization parameters accordingly Define the performance difference factor f p : Among them, E pi is the predicted energy consumption at the i-th time point, E ai is the actual energy consumption at the i-th time point; The update formula of the anomaly detection threshold is: δ'=δ+f p ·or Where η is the learning rate used to update the anomaly detection threshold; The updating formula of the fluctuation range constant is: c'=c+f p ·ξ Where ξ is the learning rate used to update the fluctuation range constant.

Images