An Internet of Things energy management method, system, device and medium

Abstract

The present application discloses an Internet of Things energy management method, system, device and medium. The method obtains the initial energy management data of all nodes in the target Internet of Things; performs exception processing on the initial energy management data of each node to obtain the first energy management data of the corresponding node; performs denoising on the first energy management data of each node to obtain the second energy management data of the corresponding node; calculates the energy management characteristics of the target Internet of Things based on the second energy management data of each node; constructs the global objective function of the target Internet of Things based on the energy management characteristics of the target Internet of Things; and based on the global objective function, updates the initial node strategy of each node to obtain the optimal energy management strategy of each node, which can achieve real-time dynamic coordination between the node local energy strategy and the global network energy efficiency, thereby improving the energy management optimization efficiency.

Description

Technical Field

[0001] The present application relates to the field of Internet of Things energy management technology, and in particular to an Internet of Things energy management method, system, device and medium. Background Art

[0002] As IoT technology penetrates deeper into areas like industrial monitoring, smart cities, and smart homes, a vast number of IoT devices are distributed over vast areas and operate unattended. Because these devices are often deployed in areas with grid coverage gaps (such as production line sensors and monitoring nodes in remote areas), their energy supply relies heavily on renewable energy sources like batteries and solar and wind power. These energy sources are significantly affected by weather and environmental factors, resulting in unstable and volatile supply.

[0003] Current IoT energy management technology adopts fixed optimization strategies and lacks the ability to dynamically adapt to environmental changes. This results in poor algorithm adaptability in dynamic energy environments and poor adaptability to sudden environmental changes. It is difficult to adjust energy scheduling strategies in a timely manner, and there is a lack of coordination between nodes, which leads to one-sided optimization results and difficulty in achieving true global optimization. It is easy to cause the coexistence of local energy surpluses and shortages, and it fails to integrate multi-objective constraints such as energy consumption costs, energy storage risks, and energy volatility, resulting in low optimization efficiency. Summary of the Invention

[0004] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0005] The main purpose of the embodiments of the present disclosure is to propose an Internet of Things energy management method, system, device and storage medium, which can achieve real-time dynamic coordination of node local energy strategies and global network energy efficiency, thereby improving energy management optimization efficiency.

[0006] A first aspect of an embodiment of the present application provides an Internet of Things energy management method for a central controller, the method comprising:

[0007] Obtain the initial energy management data of all nodes in the target IoT;

[0008] Performing exception processing on the initial energy management data of each node to obtain first energy management data of the corresponding node;

[0009] performing denoising processing on the first energy management data of each node to obtain second energy management data of the corresponding node;

[0010] Calculating the energy management characteristics of the target Internet of Things according to the second energy management data of each node;

[0011] Constructing a global objective function of the target Internet of Things according to the energy management characteristics of the target Internet of Things;

[0012] Based on the global objective function, the initial node strategy of each node is updated to obtain the optimal energy management strategy of each node.

[0013] In some embodiments of the present application, performing exception processing on the initial energy management data of each node to obtain the first energy management data of the corresponding node includes:

[0014] Calculate the median based on the initial energy management data of all nodes;

[0015] Calculate the median absolute deviation from the median;

[0016] Based on the median and the median absolute deviation, an abnormality judgment is performed on the initial energy management data of each node, and the abnormal value is corrected according to the judgment result to obtain the first energy management data of the corresponding node.

[0017] In some embodiments of the present application, performing denoising on the first energy management data of each node to obtain the second energy management data of the corresponding node includes:

[0018] Performing multi-scale decomposition on the first energy management data of each node to obtain corresponding multi-scale coefficients;

[0019] Performing noise reduction processing on each of the multi-scale coefficients using a soft threshold function to obtain a noise-reduced multi-scale coefficient;

[0020] An inverse transformation is performed on the noise-reduced multi-scale coefficients to obtain second energy management data of the corresponding node.

[0021] In some embodiments of the present application, calculating the energy management characteristics of the target Internet of Things based on the second energy management data of each node includes:

[0022] extracting a key feature of each of the nodes from the second energy management data of each of the nodes;

[0023] The key features of all the nodes are integrated to obtain the energy management features of the target Internet of Things.

[0024] In some embodiments of the present application, updating the initial node policy of each node based on the global objective function to obtain the optimal energy management policy of each node includes:

[0025] Calculating the initial node strategy and the local objective function of the corresponding node according to the initial energy management data of each node and the global objective function;

[0026] Calculating the dual variable of each of the nodes according to the local objective function of each of the nodes;

[0027] The initial node strategy of the corresponding node is updated according to the dual variable of each node to obtain the optimal energy management strategy of each node.

[0028] In some embodiments of the present application, updating the initial node strategy of the corresponding node according to the dual variable of each node to obtain the optimal energy management strategy of each node includes:

[0029] Calculating a sub-gradient of each node according to the local objective function of each node;

[0030] Update the dual variable of the corresponding node according to the sub-gradient of each node;

[0031] The consensus mechanism is used to iteratively update the initial node strategy of each node to obtain the optimal energy management strategy for each node.

[0032] In some embodiments of the present application, the calculation formula for calculating the median based on the initial energy management data of all nodes includes:

[0033]

[0034] in, For the moment The median of the initial energy management data of all nodes, For nodes At the moment Initial energy management data;

[0035] The calculation formula for calculating the absolute deviation of the median based on the median includes:

[0036]

[0037] in, For the moment The median absolute deviation of all nodes, For nodes At the moment Initial energy management data.

[0038] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present invention provides an Internet of Things energy management system, the system comprising:

[0039] An acquisition module, used to obtain the initial energy management data of all nodes in the target IoT;

[0040] a correction module, configured to perform exception processing on the initial energy management data of each node to obtain first energy management data of the corresponding node;

[0041] a noise reduction module, configured to perform noise reduction processing on the first energy management data of each node to obtain second energy management data of the corresponding node;

[0042] a calculation module, configured to calculate the energy management characteristics of the target Internet of Things based on the second energy management data of each of the nodes;

[0043] A construction module, configured to construct a global objective function of the target Internet of Things according to the energy management characteristics of the target Internet of Things;

[0044] An updating module is used to update the initial node strategy of each node based on the global objective function to obtain the optimal energy management strategy of each node.

[0045] To achieve the above-mentioned purpose, the third aspect of an embodiment of the present invention provides an electronic device, comprising: at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the above-mentioned Internet of Things energy management method.

[0046] To achieve the above-mentioned purpose, a fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned IoT energy management method.

[0047] An embodiment of the present application provides an Internet of Things energy management method, which obtains the initial energy management data of all nodes in the target Internet of Things; performs exception processing on the initial energy management data of each node to obtain the first energy management data of the corresponding node; performs denoising on the first energy management data of each node to obtain the second energy management data of the corresponding node; calculates the energy management characteristics of the target Internet of Things based on the second energy management data of each node; constructs the global objective function of the target Internet of Things based on the energy management characteristics of the target Internet of Things; and based on the global objective function, updates the initial node strategy of each node to obtain the optimal energy management strategy of each node, which can achieve real-time dynamic coordination between the node local energy strategy and the global network energy efficiency, thereby improving the energy management optimization efficiency.

[0048] It can be understood that the beneficial effects of the second to fourth aspects compared with the relevant technologies are the same as the beneficial effects of the first aspect compared with the relevant technologies. Please refer to the relevant description in the first aspect and no further details will be given here. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0050] Figure 1 This is a flow chart of an IoT energy management method provided by an embodiment of the present application;

[0051] Figure 2 This is a structural diagram of an IoT energy management training system provided by an embodiment of the present application;

[0052] Figure 3 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application.

[0054] In the description of this application, if there is a description of first, second, etc., it is only for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0055] In the description of this application, it should be understood that descriptions involving orientation, such as the orientation or positional relationship indicated by up, down, etc., are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on this application.

[0056] In the description of this application, it should be noted that, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technical personnel in the relevant technical field can reasonably determine the specific meaning of the above terms in this application based on the specific content of the technical solution.

[0057] With the rapid development of IoT technology, an increasing number of devices are being widely used in various fields, including industrial production, smart homes, smart cities, and transportation. These IoT devices are numerous, geographically distributed, and often unattended. Since most IoT nodes are deployed in areas far from reliable power supplies, energy supply issues are becoming a significant bottleneck hindering the stable operation of IoT systems. For example, in industrial monitoring, numerous sensors and actuators are installed throughout production lines to monitor equipment status and optimize production scheduling. These nodes often lack direct access to stable power from the grid and must rely on batteries or renewable energy sources such as solar and wind power. However, these energy sources are highly uncertain and volatile. For example, solar power is affected by weather, while wind power suffers from variable wind speeds, making it difficult to maintain a stable supply.

[0058] Currently, existing energy management technologies are poorly equipped to cope with the volatility and uncertainty of renewable energy sources, such as solar and wind power. When environmental conditions change rapidly, such as solar power generation fluctuating dramatically due to weather changes or wind power supply becoming unstable due to drastic changes in wind speed, existing energy management technologies often struggle to respond quickly, resulting in delayed decisions and an inability to adapt to changes in energy supply in real time. This lag not only reduces energy efficiency but can also lead to energy waste or equipment interruptions, seriously impacting system stability.

[0059] Furthermore, existing distributed energy optimization methods often treat key factors—node energy costs, energy storage risks, and energy supply uncertainty—in isolation, lacking effective coordination mechanisms. This isolated approach ignores the inherent connections and interactions between these factors, potentially leading to one-sided optimization results and making it difficult to achieve true global optimization. For example, when a device focuses solely on reducing short-term energy costs, it may overlook energy storage capacity risks, increasing the risk of energy depletion and, in turn, raising overall operating costs.

[0060] Furthermore, current distributed optimization methods are computationally complex, especially in IoT networks with a large number of nodes and widespread distribution. The system computational overhead is enormous, making it difficult to meet real-time requirements. In practice, limited computing and communication resources make real-time optimization difficult to achieve, significantly reducing the timeliness and accuracy of decision-making, and thus restricting the effective application of distributed optimization methods in real-world scenarios.

[0061] At the same time, traditional distributed optimization technologies typically employ fixed optimization strategies and lack the ability to dynamically adapt to environmental changes. This results in poor adaptability in dynamic energy environments and an inability to flexibly respond to real-time changes in operating conditions. Furthermore, existing methods often lack effective robust optimization mechanisms during design and implementation, failing to fully consider abnormal data and interference factors in actual operating environments. Once data anomalies or external interference occur, algorithm performance can significantly degrade or even fail to operate properly, further exacerbating the uncertainty and instability of energy management systems.

[0062] Based on this, the embodiments of the present application provide an IoT energy management method, system, electronic device and medium, aiming to achieve real-time dynamic coordination of node local energy strategies and global network energy efficiency, thereby improving energy management optimization efficiency.

[0063] The IoT energy management method, system, electronic device, and medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the IoT energy management method in the embodiments of the present application is described.

[0064] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, techniques, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0065] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0066] The Internet of Things energy management method provided in the embodiment of the present application relates to the field of Internet of Things energy management technology. The Internet of Things energy management method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server side, and can also be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the Internet of Things energy management method, etc., but is not limited to the above forms.

[0067] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments in which tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0068] It should be noted that in each specific embodiment of the present application, when it comes to the need to perform relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of such data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0069] For this purpose, refer to Figure 1The embodiment of the present application provides an IoT energy management method. The method is applied to a central controller. The controller can be a server, an electronic device, or a mobile terminal, etc., and is not specifically limited here. The method includes the following steps S110 to S160:

[0070] Step S110: Acquire initial energy management data of all nodes in the target Internet of Things;

[0071] Step S120: performing exception processing on the initial energy management data of each node to obtain first energy management data of the corresponding node;

[0072] Step S130: De-noising the first energy management data of each node to obtain second energy management data of the corresponding node;

[0073] Step S140: Calculate the energy management characteristics of the target Internet of Things based on the second energy management data of each node;

[0074] Step S150: constructing a global objective function of the target Internet of Things based on the energy management characteristics of the target Internet of Things;

[0075] Step S160: Based on the global objective function, the initial node strategy of each node is updated to obtain the optimal energy management strategy of each node.

[0076] In this step, the initial energy management data refers to the raw energy information collected by the node. Specifically, it can be achieved by real-time monitoring of parameters such as the remaining battery power, renewable energy input power, and equipment energy consumption rate through voltage sensors, current sensors, or power metering modules. This provides basic input for subsequent processing and solves the optimization deviation problem caused by low data quality in traditional methods.

[0077] Specifically, anomaly handling refers to identifying and correcting energy data that deviates from the normal range through the median and absolute deviation methods. It is preferred to use a sliding time window to count the median of all node data, combine the preset deviation threshold to judge the abnormal points, and replace them with the mean or interpolated data of adjacent moments, thereby eliminating noise interference caused by sensor failure or sudden environmental changes and improving data reliability.

[0078] Specifically, denoising refers to eliminating high-frequency noise in the data through signal decomposition technology. It is preferred to use wavelet transform and empirical mode decomposition methods to perform multi-scale decomposition on energy data, and use soft threshold function to filter out noise coefficients and then reconstruct the signal, thereby retaining the effective components in energy fluctuations and enhancing data availability.

[0079] Specifically, energy management characteristics refer to key indicators that reflect the overall energy status of the Internet of Things. Preferably, the principal component analysis method is used to extract parameters such as the mean residual energy, charging and discharging efficiency, and energy fluctuation variance of each node, and then a comprehensive feature vector is generated through weighted fusion, thereby providing a quantitative basis for constructing a global optimization model.

[0080] Specifically, the global objective function refers to a mathematical model that integrates energy utilization, energy storage equipment loss, and energy supply and demand balance. Preferably, a linear weighted method can be used to transform multi-objective constraints into a single-objective optimization problem, and a mathematical expression including an energy consumption cost function, an energy storage risk function, and an energy fluctuation penalty term is defined, thereby achieving a unified quantitative evaluation of multi-dimensional optimization objectives.

[0081] Specifically, the optimal energy management strategy refers to a dynamic decision-making plan generated by a distributed optimization algorithm. It preferably adopts the dual decomposition method combined with the consensus mechanism. During the iteration process, the charging and discharging strategy, equipment start and stop plan, and energy allocation ratio are adjusted according to the node energy status, so as to achieve collaborative optimization among nodes and avoid local resource imbalance.

[0082] In this step, the initial energy management data of all nodes in the target Internet of Things are first obtained. These data contain the energy status information of each node. Then, the initial data of each node are processed for exceptions to correct possible outliers and obtain the first energy management data. The first energy management data are then denoised to filter out interference signals and obtain more accurate second energy management data. Based on the processed second energy management data, the energy management characteristics of the target Internet of Things are calculated to reflect the energy distribution status of the entire network through these characteristics. Then, based on the energy management characteristics, the global objective function of the target Internet of Things is constructed, and the overall energy optimization goal of the network is comprehensively considered. Finally, the initial strategy of each node is updated based on the global objective function to obtain the optimal energy management strategy, which solves the problem of uneven energy distribution between nodes, thereby improving data quality through multi-step data processing, integrating multi-node characteristics to establish a global objective function, and using a distributed optimization mechanism to dynamically generate energy management strategies, thereby realizing adaptive collaborative management of the Internet of Things system in a dynamic energy environment.

[0083] In some embodiments, performing exception processing on the initial energy management data of each node in step S120 to obtain first energy management data of the corresponding node includes the following steps S210 to S230:

[0084] Step S210: Calculate the median based on the initial energy management data of all nodes;

[0085] Step S220: Calculate the median absolute deviation based on the median;

[0086] Step S230 : Based on the median and the median absolute deviation, perform abnormality judgment on the initial energy management data of each node, and correct the abnormal value according to the judgment result to obtain the first energy management data of the corresponding node.

[0087] In this embodiment, the median calculation adopts the method of sorting each time point and taking the middle value, which is suitable for scenarios with dynamic fluctuations in energy data; the median absolute deviation avoids the interference of outliers on the deviation estimation by calculating the median of the absolute distance between each node data and the median.

[0088] Specifically, in a dynamic energy environment, energy data can experience intermittent and extreme fluctuations. Taking the initial energy data of each node at a given moment as an example, sorting and taking the middle value as the global median can eliminate interference from high-energy or low-power nodes in the data center. By calculating the absolute deviation of each node's data from the median and then taking the median again, the degree of data dispersion can be quantified, and this metric is insensitive to outliers.

[0089] In some embodiments, when a node generates abnormally high energy consumption data due to a sudden failure, its deviation from the median will be significantly higher than that of other nodes, but the calculation process of the median absolute deviation automatically excludes the influence of such extreme deviations. After setting dynamic thresholds based on the median and the median absolute deviation, the data of each node is detected point by point in the time dimension, and data that exceeds the threshold range is marked as abnormal. During the correction process, the outliers are replaced with threshold boundary values ​​or reasonable values ​​are generated through linear interpolation to ensure that the corrected data retains the true fluctuation trend and eliminates abnormal interference, thereby achieving the goal of effectively improving the robustness of anomaly detection in the case of unstable energy supply, providing a high-quality data foundation for subsequent denoising processing and strategy optimization, and avoiding the interference of abnormal data on overall energy management decisions.

[0090] In some embodiments, a formula for calculating the median based on the initial energy management data of all nodes includes:

[0091]

[0092] in, For the moment The median of the initial energy management data of all nodes, For nodes At the moment Initial energy management data;

[0093] The formula for calculating the absolute deviation of the median based on the median includes:

[0094]

[0095] in, For the moment The median absolute deviation of all nodes, For nodes At the moment Initial energy management data.

[0096] In this embodiment, the median calculation step is to take all nodes at time The median value of energy data is used to eliminate the influence of extreme values ​​on statistics. The median absolute deviation calculation step is to construct a robustness measurement index of dynamic data distribution range through the median of the absolute deviation of each node data and the median. The time dimension parameter The introduction of enables the calculation process to track data fluctuations moment by moment and adapt to dynamic scenarios with unstable energy supply.

[0097] Specifically, during the execution process, Nodes at time The initial energy management data is sorted by value and the median value is extracted to generate a global median benchmark. . Further traverse all node data, calculate the absolute deviation of each data point from the benchmark value, generate a new data set and extract the median again as , in order to achieve the stability of statistics when there are intermittent mutations or regional anomalies in energy data, and avoid the problem of distortion of overall judgment threshold caused by single point anomaly in traditional mean-standard deviation method, and through dynamic adjustment and , it can perceive the group distribution characteristics of node data in real time, provide an accurate benchmark reference for subsequent outlier correction, ensure that the data quality before denoising meets the multi-objective optimization requirements, and help improve the accuracy and robustness of anomaly detection.

[0098] In some embodiments, performing denoising on the first energy management data of each node in step S130 to obtain the second energy management data of the corresponding node includes the following steps S310 to S330:

[0099] Step S310: performing multi-scale decomposition on the first energy management data of each node to obtain corresponding multi-scale coefficients;

[0100] Step S320: Using a soft threshold function, perform noise reduction processing on each multi-scale coefficient to obtain a noise-reduced multi-scale coefficient;

[0101] Step S330: Perform inverse transformation on the denoised multi-scaling coefficients to obtain second energy management data of the corresponding node.

[0102] In this embodiment, multi-scale decomposition is preferably performed to decompose the data into coefficients of different frequency ranges through wavelet transform; a soft threshold function sets a dynamic threshold, which is set to zero when the absolute value of the coefficient is lower than the threshold, and is reduced by the difference when it is higher than the threshold, and the threshold is set to 1.5 times the standard deviation of the noise of each layer; the inverse transform uses the wavelet basis function corresponding to the decomposition process to reconstruct the signal, retaining the coefficients of the energy concentration area.

[0103] Specifically, the data is decomposed into three scales: high frequency, medium frequency, and low frequency. The high frequency coefficient corresponds to short-term energy mutation noise, and the low frequency coefficient reflects long-term energy trend fluctuations. The high frequency coefficients are processed by soft thresholding, and the coefficients with an absolute value greater than 0.5 are retained to eliminate impulse noise. At the same time, the low frequency coefficients are compressed by 10% to suppress the baseline drift caused by environmental factors. During the reconstruction process, the denoised coefficients are superimposed according to the scale weight. For example, the high frequency layer weight is set to 0.3 and the low frequency layer weight is set to 0.7. The requirements of noise suppression and feature retention are balanced to achieve adaptive noise reduction of energy data in the time-frequency domain, eliminate abnormal fluctuations caused by sudden weather changes, and retain the effective energy consumption characteristics generated by device state switching. This can effectively remove noise interference in the first energy management data, improve the reliability and accuracy of the data, and thus improve the performance and efficiency of the entire IoT energy management system.

[0104] In some embodiments, calculating the energy management characteristics of the target Internet of Things based on the second energy management data of each node in step S140 includes the following steps S410 to S420:

[0105] Step S410: extracting key features of each node from the second energy management data of each node;

[0106] Step S420: Fusion the key features of all nodes to obtain the energy management features of the target Internet of Things.

[0107] In this embodiment, key feature extraction is preferably achieved using time-domain statistics, frequency-domain energy distribution, or principal component analysis, and feature fusion is preferably achieved using weighted averaging, linear superposition, or neural network embedding. The key feature extraction step includes a sliding window mechanism, and the feature fusion process introduces a dynamic weight allocation mechanism. The weight coefficient is dynamically adjusted based on the ratio of node energy fluctuation rate to energy storage capacity to match node status changes in real time.

[0108] Specifically, after completing the multi-scale decomposition and noise reduction processing, key features are extracted from the second energy management data. Preferably, the second energy management data is input into the feature extraction module, the continuous time series is intercepted through the sliding window, and the mean, variance and kurtosis indicators in each window are calculated to form a time domain feature vector.

[0109] The windowed data is further subjected to a fast Fourier transform (FFT) to extract the amplitudes of the first three main frequency components as frequency domain features. Principal component analysis (PCA) is then used to reduce the dimensionality of the time-frequency hybrid features, retaining the top three principal components with a cumulative contribution of 90%. The PCA vectors for all nodes are then fed into a fusion layer, where fusion weights are calculated based on the remaining battery capacity of each node. Nodes with a capacity above 60% have their weights increased by 20%, while those with a capacity below 30% have their weights reduced by 15%. Finally, a weighted summation is performed to generate a global feature vector that captures the energy distribution differences and dynamic correlation features between nodes. This vector is compressed to 12%-18% of the original data, significantly reducing the computational complexity of the subsequent objective function construction. This vector also preserves the spatial correlation of energy states across nodes, providing high-information feature input for global optimization. This effectively extracts and fuses energy management features for the IoT system, comprehensively reflecting the energy status of the entire IoT system and generating more global and comprehensive energy management features, avoiding the biased nature of relying solely on individual node data.

[0110] In some embodiments, in step S160, based on the global objective function, the initial node policy of each node is updated to obtain the optimal energy management policy for each node, including the following steps S510 to S530:

[0111] Step S510: Calculate the initial node strategy and local objective function of the corresponding node based on the initial energy management data of each node and the global objective function;

[0112] Step S520: Calculate the dual variable of each node according to the local objective function of each node;

[0113] Step S530: Update the initial node strategy of the corresponding node according to the dual variable of each node to obtain the optimal energy management strategy of each node.

[0114] In this embodiment, the calculation of the initial node strategy needs to simultaneously integrate the real-time parameters of the global objective function and the node's initial energy management data, where the global objective function includes weight factors for energy cost, energy storage risk, and volatility constraints, and the initial energy management data includes historical energy consumption, current energy storage capacity, and energy supply forecast values; the dual variable is generated through the Lagrange multiplier method or the alternating direction multiplier method to characterize the constraint relationship between the node strategy and the global objective; the sub-gradient is calculated based on the first-order derivative or sub-gradient of the local objective function with respect to the node strategy, and its update step size is negatively correlated with the energy fluctuation amplitude; the consensus mechanism adopts a distributed optimization algorithm to synchronously exchange the dual variables of adjacent nodes in each iteration.

[0115] Specifically, when calculating the initial node strategy, the node's historical energy consumption data and current energy storage capacity are input into the local objective function, where the historical energy consumption data is processed by a sliding window mechanism, and the multi-objective constraints in the global objective function are converted into penalty terms and added to the calculation, thereby generating an initial strategy that matches the node's dynamic characteristics.

[0116] Furthermore, during the dual variable update phase, the sub-gradient direction is dynamically adjusted by comparing the energy utilization differences between adjacent node strategies. During the consensus mechanism iteration process, each node broadcasts its latest policy parameters according to a preset time period, receives and integrates the policy parameters of nodes within a preset range, and calculates the integration weight based on the energy supply similarity between nodes. For example, the weight of nodes with a similarity greater than 80% is set to 0.7, and the weight of the remaining nodes is set to 0.3. Then, after 10-15 rounds of consensus update iterations, the strategies of each node converge to a stable state that meets the global optimization goal, achieving adaptive adjustment of the energy scheduling strategy in a dynamic environment, ensuring overall performance while taking into account the individual needs of each node. Moreover, by introducing dual variables and iterative update mechanisms, it is possible to effectively handle complex constraints, improve the convergence speed and stability of the optimization algorithm, and enhance the energy utilization efficiency and operational reliability of the system.

[0117] In some embodiments, in step S530, the initial node policy of the corresponding node is updated according to the dual variable of each node to obtain the optimal energy management policy of each node, including the following steps S610 to S630:

[0118] Step S610: Calculate the sub-gradient of each node according to the local objective function of each node;

[0119] Step S620: Update the dual variable of the corresponding node according to the sub-gradient of each node;

[0120] Step S630: Use the consensus mechanism to iteratively update the initial node strategy of each node to obtain the optimal energy management strategy for each node.

[0121] In this embodiment, sub-gradient calculation is achieved by solving the sub-differential set of the local objective function in the policy space. Each sub-gradient vector corresponds to a feasible descent direction in the policy space. The dual variable update adopts an iterative formula with a momentum term, and the momentum coefficient is set to a dynamic interval value to balance the convergence speed and stability. The consensus mechanism adopts a distributed average consistency algorithm. In each round of iteration, the node exchanges policy information with the neighboring nodes and performs a weighted average operation. The weight matrix satisfies the double randomness condition to ensure convergence.

[0122] Specifically, in the sub-gradient calculation stage, each node determines the sub-gradient vector based on the left derivative and right derivative of the objective function at the current strategy point to point to the direction where the objective function value decreases fastest. Then, when updating the dual variable, the dual variable value of the previous iteration is linearly combined with the current sub-gradient according to the preset step coefficient. The step coefficient decays as the number of iterations increases to ensure convergence.

[0123] Furthermore, during the consensus mechanism's execution, each node maintains a local copy of the policy. Under a pre-set communication topology, after a pre-set number of iterations, the discrepancy between each node's policy copies converges to within an ideal pre-set range. This maintains the independence of each node's local computation while gradually aligning the policy updates toward the global optimal solution, ultimately achieving a Pareto optimal state for the energy management strategy. This achieves the convergence and stability of the distributed optimization algorithm, avoids the communication overhead of a centralized algorithm, and improves its scalability and robustness. Furthermore, through multiple rounds of iterative optimization, the algorithm can adapt to dynamically changing energy environments and adjust energy management strategies in a timely manner.

[0124] In some embodiments, an IoT energy system is first constructed. Consider an energy network consisting of multiple distributed IoT devices, which are deployed in different geographical locations. The overall system is modeled as a node set. Each node is equipped with local energy storage and renewable energy acquisition capabilities. Time is expressed in discrete periods, recorded as ,The system needs to carry out multi-stage and robust energy optimization management under ,the constraints of energy supply uncertainty and real-time coordination.

[0125] Step 1: First, computing nodes deployed on the device side or at the edge of the network are used to collect device energy consumption and environmental data (such as temperature, wind speed, and sunlight intensity) in real time. Robust preprocessing operations are then performed to identify and eliminate abnormal data during sensor acquisition. Multi-scale signal processing methods are combined to effectively remove background noise and extract representative and reliable data information. These data are then integrated into unified, high-quality input features, providing accurate and stable support for subsequent optimization models and a solid guarantee for achieving precise energy consumption management.

[0126] Specifically, the energy consumption and environmental data of the equipment are collected in real time through edge nodes, and the original data are subjected to anomaly elimination, denoising and feature extraction by combining robust statistics and wavelet transform. Finally, a high-quality and stable input feature vector is formed, providing reliable data support for the subsequent robust optimization model.

[0127] In this embodiment, by inputting node energy consumption data sequence , environmental perception data vector , threshold parameter (robustness control), wavelet threshold parameter (Denoising degree control), get the output fused feature vector: , which is used as the input feature vector for the subsequent optimization model.

[0128] Specifically, in the IoT environment, distributed edge nodes are used to collect device energy consumption and environmental data in real time. nodes, each node in The energy consumption data at the moment is recorded as: ; At the same time, the environmental data is expressed in vector form, which is recorded as:

[0129] ;

[0130] in, Indicates the The measurement values ​​of environmental variables (such as solar radiation, wind speed, temperature, load status, etc.) specifically define the basic mathematical representation of energy consumption data and environmental data, laying the foundation for subsequent data preprocessing and feature extraction.

[0131] Furthermore, robust statistical methods are used to pre-process the acquired energy consumption data and environmental data. For example:

[0132] First, calculate the time The median of all node energy consumption data:

[0133]

[0134] Where, For the moment The median of all node energy consumption data, For nodes At the moment The node energy consumption data can be used to effectively reflect the trend of the data through the median.

[0135] Furthermore, the median of absolute deviations is calculated:

[0136]

[0137] Where, For the moment The median absolute deviation, For nodes At the moment The node energy consumption data is obtained by using the median of absolute deviation as a robust statistic to measure the degree of data dispersion.

[0138] Furthermore, the threshold factor is set (usually 3), if:

[0139] ;

[0140] It is believed that For abnormal values, the median or interpolation method is used to correct the detected abnormal values, and the corrected data is recorded as , in order to effectively eliminate or correct abnormal data caused by noise or sensor failure, and ensure the quality of data for subsequent processing.

[0141] Furthermore, the discrete wavelet transform (DWT) is used to perform multi-scale decomposition of the signal to achieve fine denoising.

[0142] Specifically, the corrected energy consumption signal of each node Perform wavelet decomposition, and the wavelet coefficients are:

[0143] ;

[0144] in, is the scale index, is the translation index, is the corresponding wavelet basis function, so that the original signal is decomposed into components at different scales through wavelet transform, so that the noise in the signal and the real signal can be distinguished at different scales.

[0145] Furthermore, for each wavelet coefficient Use soft threshold function for noise reduction:

[0146] ;

[0147] in, is the threshold parameter, usually determined according to the signal-to-noise level, Represents the sign function, thereby effectively weakening the noise component while retaining the important information of the signal.

[0148] Furthermore, after denoising, the denoised signal is restored by inverse wavelet transform:

[0149] ;

[0150] Thus, the denoised wavelet coefficients are recombined into time domain signals through inverse transformation to obtain smoother and lower-noise energy consumption data.

[0151] At the same time, the environmental data is preprocessed. It may also be affected by anomalies and noise, so for each environment variable Perform similar processing.

[0152] Specifically, for Environmental variables, calculate their median and median absolute deviation:

[0153]

[0154] ;

[0155] Similar to energy consumption data, the impact of noise and outliers is reduced through robust statistical methods.

[0156] Furthermore, the outliers are judged if:

[0157] ;

[0158] The current judgment value is regarded as an abnormal value and is corrected to ensure that the environmental data is free of abnormal noise before subsequent processing.

[0159] Furthermore, after processing Similarly, wavelet transform and soft threshold denoising are applied to obtain the denoised environmental data, which is recorded as .

[0160] Furthermore, key features are extracted from each node data and environmental data and fused to form high-quality input for subsequent optimization solutions.

[0161] Specifically, the denoised energy consumption signal of each node Extract key features (such as mean, variance, peak, etc.), denoted as , and use the weighted average method to fuse the features of each node:

[0162] ;

[0163] Among them, the weight The weight is determined based on the signal-to-noise ratio or variance of the node data. The weight calculation formula is:

[0164] ;

[0165] in, Representation node The noise variance of the data can be effectively integrated into the data of each node to reduce the impact of the error of a single node on the overall decision.

[0166] Specifically, for each denoised environmental variable Extract features , and adopt a similar weighted strategy to merge into:

[0167] ;

[0168] in, is the environment variable weight, satisfying:

[0169] ;

[0170] Environmental feature fusion also uses the weighted average method to integrate multiple environmental data into a comprehensive indicator, providing environmental background information for subsequent robust optimization.

[0171] Furthermore, the features after fusion of node energy consumption and environmental data are integrated into the final input feature vector:

[0172] ;

[0173] pass The vector comprehensively reflects the current energy consumption status of the system and external environmental factors, so as to obtain fused feature data with high signal-to-noise ratio and stability, providing high-quality and stable input data for the subsequent multi-objective robust optimization model, and providing a solid data foundation for the subsequent construction of accurate and robust optimization models.

[0174] Step 2: Based on the high-quality input features obtained in step 1, a multi-objective robust optimization model is constructed that takes into account energy consumption costs, energy storage risks, and renewable energy supply uncertainty.

[0175] First determine the input as: feature vector (output by robust feature fusion method), node set , total energy supply constraint , risk weight coefficient , node uncertainty set , output the preliminary local optimal strategy for each node: , iterative intermediate variables: dual variables (Incoming consensus coordination algorithm) Among them, For all nodes at time The total electricity budget or total power supply, and These are preset parameters used to limit the range of changes in renewable energy supply.

[0176] Specifically, let the energy consumption cost of each node be and energy storage risks ,in and Node The energy consumption decision and storage strategy of the whole objective function is constructed as follows:

[0177] ;

[0178] in is the risk weight coefficient. At the same time, in order to consider the uncertainty of renewable energy supply, it is assumed that each node renewable energy input Falling into the uncertain set The robust constraint of supply and demand balance can be written as:

[0179] ;

[0180] in Representation node to ensure that each node can still meet the demand in the most unfavorable situation.

[0181] Furthermore, Lagrangian dual decomposition is performed. In particular, there are usually global coupling constraints in IoT systems, such as the supply and demand balance of the entire system, which can be expressed as:

[0182] ;

[0183] in is the total system demand.

[0184] In order to reduce the complexity of solving the global problem, the Lagrange multiplier is introduced Relax the coupling constraints and construct the Lagrangian function:

[0185] ;

[0186] The global problem can be decomposed into local sub-problems independent of each node through Lagrangian dual decomposition. transfer.

[0187] Furthermore, we construct a distributed subproblem and use the Lagrangian function to calculate the probability of each node The following local subproblems can be solved independently:

[0188] ;

[0189] At the same time, satisfy their respective local robust constraints:

[0190] ;

[0191] Therefore, through distributed solution, each node can be optimized independently based on local information, reducing the computational complexity of the overall problem.

[0192] Furthermore, distributed sub-gradient updates are performed. After each node independently solves the local sub-problem, it is necessary to update the global dual variable To coordinate the global supply and demand balance. The distributed sub-gradient algorithm is used, and its update rule is:

[0193] ;

[0194] in, For the The step size of the iteration, For nodes In the The decision results of the iterations are gradually adjusted according to the global supply and demand deviation , ensuring that the system tends to the global optimal solution.

[0195] Furthermore, we perform dual linearization of robust constraints, first for the constraints containing uncertainty:

[0196] ;

[0197] Assume that the uncertainty set In the form of a polyhedron, that is:

[0198] ;

[0199] Using duality theory, introduce dual variables And meet:

[0200] ;

[0201] By dual strong ideality, the above uncertainty constraint is equivalent to:

[0202] ;

[0203] This allows the original nonlinear robust constraints to be transformed into a set of linear constraints, which is beneficial for improving computational efficiency in a distributed solution framework.

[0204] In step two, the global optimization problem is broken down into individual nodes, allowing each node to independently solve the problem based on local data while simultaneously transmitting global information through dual variables. This process not only reduces computational complexity but also lays the foundation for eventual global coordination.

[0205] Step 3: Based on the solution of local sub-problems, the distributed sub-gradient calculation and neighborhood consensus update mechanism are used to achieve dynamic coordination of local decisions of each node, thereby achieving the global optimal energy management strategy.

[0206] First determine the input as the initial strategy (initialized by the dual decomposition method), neighbor set (network topology), initial dual variables , initial step length and the maximum number of iterations , output the collaborative optimization strategy after convergence and the final dual variables of each node .

[0207] Specifically, in a distributed scenario, each node uses its own local information to calculate the sub-gradient of the objective function with respect to the decision variable. The local objective function is:

[0208] ;

[0209] in is the dual variable introduced in step 2. In the At iterations, the local sub-gradient is calculated:

[0210] ;

[0211] The local sub-gradient reflects the descent direction of the local objective function at the current decision point, providing an optimization basis for subsequent variable updates.

[0212] Furthermore, a consensus coordination mechanism between neighbors is adopted. The neighborhood set of , consensus update is achieved by weighted average method, and its update formula is:

[0213] ;

[0214] in, is the weight between nodes, satisfying:

[0215] ;

[0216] and For the The step size parameter of the iteration is used to combine the optimization information of neighboring nodes, so that each node can achieve global coordination through the exchange of local information, and gradually make the overall decision tend to be consistent.

[0217] Furthermore, in order to achieve stable convergence in the later stages of iteration, a dynamic step size adjustment strategy is introduced, using a decreasing step size, such as:

[0218] ;

[0219] in is the initial step size. The step size reduction strategy makes it decrease faster in the early stage and the convergence speed gradually slows down in the later stage, thereby improving the global convergence and stability.

[0220] Furthermore, the entire process of the distributed sub-gradient and consensus collaboration algorithm (DSC algorithm) can be described as follows:

[0221] Through local sub-gradient calculation, neighborhood consensus update and dynamic step size adjustment, the real-time coordination and global optimization of the energy management strategy of each node in the distributed environment are achieved, which ultimately promotes the improvement of the overall energy efficiency and robustness of the system. The process of the entire distributed sub-gradient and consensus collaboration algorithm (DSC algorithm) is as follows: Each node initializes the local decision variable , Storage Policy and the dual variable ; Each node calculates the local objective function And find the sub-gradient Nodes exchange their own and Information, and update the local decision variables according to the consensus update formula At the same time, each node adjusts according to the global supply and demand situation and the dual update rule of step 2 . Furthermore, the step size is adjusted dynamically , repeating the above process until the preset convergence conditions are met. Thus, through real-time local gradient transfer and consensus mechanisms, the local optimal solutions of each node are unified and coordinated into a global optimal solution, giving full play to the advantages of the decomposition solution in step 2, and ultimately achieving real-time and efficient collaborative control of the system in a dynamic environment.

[0222] like Figure 2 As shown, some embodiments of the present application provide an IoT energy management system, which includes an acquisition module 210, a correction module 220, a noise reduction module 230, a calculation module 240, a construction module 250, and an update module 260. Specifically:

[0223] An acquisition module 210 is configured to acquire initial energy management data of all nodes in a target IoT;

[0224] A correction module 220 is configured to perform exception processing on the initial energy management data of each node to obtain first energy management data of the corresponding node;

[0225] a noise reduction module 230 for performing noise reduction processing on the first energy management data of each node to obtain second energy management data of the corresponding node;

[0226] a calculation module 240, configured to calculate an energy management characteristic of a target Internet of Things based on the second energy management data of each node;

[0227] A construction module 250 is configured to construct a global objective function of the target Internet of Things based on the energy management characteristics of the target Internet of Things;

[0228] The updating module 260 is used to update the initial node strategy of each node based on the global objective function to obtain the optimal energy management strategy of each node.

[0229] In some embodiments, the correction module 220 may include calculating a median based on the initial energy management data of all nodes.

[0230] In some implementations, the correction module 220 may include calculating a median absolute deviation based on the median.

[0231] In some embodiments, the correction module 220 may include: performing anomaly judgment on the initial energy management data of each node based on the median and the median absolute deviation, and correcting the abnormal value according to the judgment result to obtain the first energy management data of the corresponding node.

[0232] In some implementations, the noise reduction module 230 may include: performing multi-scale decomposition on the first energy management data of each node to obtain corresponding multi-scale coefficients.

[0233] In some embodiments, the noise reduction module 230 may include: performing noise reduction processing on each multi-scale coefficient using a soft threshold function to obtain the noise-reduced multi-scale coefficient.

[0234] In some embodiments, the noise reduction module 230 may include: performing an inverse transformation on the noise-reduced multi-scaling coefficients to obtain the second energy management data of the corresponding node.

[0235] In some embodiments, the calculation module 240 may include: extracting a key feature of each node from the second energy management data of each node.

[0236] In some embodiments, the calculation module 240 may include: fusing key features of all nodes to obtain energy management features of the target Internet of Things.

[0237] In some embodiments, the updating module 260 may include: calculating an initial node policy and a local objective function of the corresponding node according to the initial energy management data of each node and the global objective function.

[0238] In some implementations, the updating module 260 may include calculating a dual variable of each node according to a local objective function of each node.

[0239] In some embodiments, the updating module 260 may include: updating the initial node policy of the corresponding node according to the dual variable of each node to obtain the optimal energy management policy of each node.

[0240] In some implementations, the updating module 260 may include calculating a sub-gradient of each node according to the local objective function of each node.

[0241] In some implementations, the updating module 260 may include: updating the dual variable of each node according to the sub-gradient of each node.

[0242] In some embodiments, the updating module 260 may include: iteratively updating the initial node strategy of each node using a consensus mechanism to obtain the optimal energy management strategy of each node.

[0243] In some implementations, the correction module 220 may include:

[0244]

[0245] in, For the moment The median of the initial energy management data of all nodes, For nodes At the moment Initial energy management data.

[0246] In some implementations, the correction module 220 may include:

[0247]

[0248] in, For the moment The median absolute deviation of all nodes, For nodes At the moment Initial energy management data.

[0249] It should be noted that the Internet of Things energy management system provided in this embodiment and the above-mentioned Internet of Things energy management method are based on the same inventive concept, so the relevant content of the above-mentioned Internet of Things energy management method is also applicable to the content of the Internet of Things energy management system, so it will not be repeated here.

[0250] To achieve this, the system obtains the initial energy management data of all nodes in the target IoT; performs exception processing on each node's initial energy management data to obtain the corresponding node's first energy management data; performs denoising on each node's first energy management data to obtain the corresponding node's second energy management data; calculates the target IoT's energy management characteristics based on each node's second energy management data; constructs a global objective function for the target IoT based on the target IoT's energy management characteristics; and based on the global objective function, updates each node's initial node policy to obtain the optimal energy management policy for each node. This allows for real-time dynamic coordination between node-local energy policies and global network energy efficiency, thereby improving energy management optimization efficiency.

[0251] An embodiment of the present application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the above-mentioned Internet of Things energy management method when executing the computer program.

[0252] like Figure 3 , Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. The electronic device includes:

[0253] At least one battery;

[0254] at least one memory;

[0255] at least one processor;

[0256] at least one program;

[0257] The program is stored in the memory, and the processor executes at least one program to implement the above-mentioned IoT energy management method implemented in the present disclosure.

[0258] The electronic device may be any intelligent terminal including a mobile phone, a tablet computer, a personal digital assistant (PDA), a car computer, etc.

[0259] The electronic device according to the embodiment of the present application is described in detail below.

[0260] The processor 1600 may be implemented as a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided by the embodiments of the present disclosure.

[0261] Memory 1700 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). Memory 1700 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program code is stored in memory 1700 and is called by processor 1600 to execute the IoT energy management method of the embodiments of this disclosure.

[0262] Input / output interface 1800, used for information input and output;

[0263] Communication interface 1900, used to implement communication interaction between this device and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WiFi, Bluetooth, etc.);

[0264] Bus 2000 , which transmits information between various components of the device (e.g., processor 1600 , memory 1700 , input / output interface 1800 , and communication interface 1900 );

[0265] The processor 1600 , the memory 1700 , the input / output interface 1800 , and the communication interface 1900 are connected to each other in communication within the device via the bus 2000 .

[0266] An embodiment of the present disclosure further provides a storage medium, which is a computer-readable storage medium. The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned IoT energy management method.

[0267] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0268] The embodiments described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems.

[0269] Those skilled in the art will understand that the technical solutions shown in the drawings do not constitute a limitation on the embodiments of the present disclosure, and may include more or fewer steps than shown in the drawings, or a combination of certain steps, or different steps.

[0270] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, i.e., they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of this embodiment.

[0271] Those skilled in the art will appreciate that all or some of the steps in the methods, systems, and functional modules / units in the devices disclosed above may be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0272] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0273] It should be understood that in this application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0274] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0275] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0276] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0277] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes multiple instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store programs, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0278] The above is a specific description of the preferred implementation of the embodiments of the present application, but the embodiments of the present application are not limited to the above-mentioned implementation methods. Technical personnel familiar with the art can also make various equivalent modifications or substitutions without violating the spirit of the embodiments of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the embodiments of the present application.

[0279] The embodiments of the present application are described in detail above in conjunction with the accompanying drawings, but the present application is not limited to the above embodiments. Various changes can be made within the scope of knowledge possessed by ordinary technicians in the relevant technical field without departing from the purpose of the present application.

Claims

1. An Internet of Things energy management method, characterized in that: The method comprises: Obtain the initial energy management data of all nodes in the target IoT; Performing exception processing on the initial energy management data of each node to obtain first energy management data of the corresponding node; performing denoising processing on the first energy management data of each node to obtain second energy management data of the corresponding node; Calculating the energy management characteristics of the target Internet of Things according to the second energy management data of each node; Constructing a global objective function of the target Internet of Things according to the energy management characteristics of the target Internet of Things; Based on the global objective function, updating the initial node strategy of each node to obtain the optimal energy management strategy of each node; The updating of the initial node strategy of each node based on the global objective function to obtain the optimal energy management strategy of each node includes: Calculating the initial node strategy and the local objective function of the corresponding node according to the initial energy management data of each node and the global objective function; Calculating the dual variable of each of the nodes according to the local objective function of each of the nodes; updating the initial node strategy of the corresponding node according to the dual variable of each node to obtain the optimal energy management strategy of each node; The updating of the initial node strategy of the corresponding node according to the dual variable of each node to obtain the optimal energy management strategy of each node includes: Calculating a sub-gradient of each node according to the local objective function of each node; Update the dual variable of the corresponding node according to the sub-gradient of each node; Iteratively updating the initial node strategy of each node using a consensus mechanism to obtain the optimal energy management strategy for each node; The performing denoising on the first energy management data of each node to obtain the second energy management data of the corresponding node includes: Performing multi-scale decomposition on the first energy management data of each node to obtain corresponding multi-scale coefficients; Performing noise reduction processing on each of the multi-scale coefficients using a soft threshold function to obtain a noise-reduced multi-scale coefficient; Performing an inverse transformation on the noise-reduced multi-scale coefficients to obtain second energy management data of the corresponding node; Calculating the energy management characteristics of the target Internet of Things according to the second energy management data of each node includes: extracting a key feature of each of the nodes from the second energy management data of each of the nodes; fusing the key features of all the nodes to obtain the energy management features of the target Internet of Things; The process of integrating the key features of all the nodes includes introducing a dynamic weight allocation mechanism, wherein the weight coefficient in the dynamic weight allocation mechanism is dynamically adjusted by the ratio of the node energy fluctuation rate of the node to the energy storage capacity of the node.

2. The IoT energy management method according to claim 1, wherein: The performing exception processing on the initial energy management data of each node to obtain first energy management data of the corresponding node includes: Calculate the median based on the initial energy management data of all nodes; Calculate the median absolute deviation from the median; Based on the median and the median absolute deviation, an abnormality judgment is performed on the initial energy management data of each node, and the abnormal value is corrected according to the judgment result to obtain the first energy management data of the corresponding node.

3. The IoT energy management method according to claim 2, characterized in that: The calculation formula for calculating the median based on the initial energy management data of all nodes includes: in, For the moment The median of the initial energy management data of all nodes, For nodes At the moment Initial energy management data; The calculation formula for calculating the absolute deviation of the median based on the median includes: in, For the moment The median absolute deviation of all nodes, For nodes At the moment Initial energy management data.

4. An Internet of Things energy management system, characterized in that: The system comprises: An acquisition module, used to obtain the initial energy management data of all nodes in the target IoT; a correction module, configured to perform exception processing on the initial energy management data of each node to obtain first energy management data of the corresponding node; a noise reduction module, configured to perform noise reduction processing on the first energy management data of each node to obtain second energy management data of the corresponding node; a calculation module, configured to calculate the energy management characteristics of the target Internet of Things based on the second energy management data of each of the nodes; A construction module, configured to construct a global objective function of the target Internet of Things according to the energy management characteristics of the target Internet of Things; An updating module, configured to update the initial node strategy of each node based on the global objective function to obtain the optimal energy management strategy for each node; The updating of the initial node strategy of each node based on the global objective function to obtain the optimal energy management strategy of each node includes: Calculating the initial node strategy and the local objective function of the corresponding node according to the initial energy management data of each node and the global objective function; Calculating the dual variable of each of the nodes according to the local objective function of each of the nodes; updating the initial node strategy of the corresponding node according to the dual variable of each node to obtain the optimal energy management strategy of each node; The updating of the initial node strategy of the corresponding node according to the dual variable of each node to obtain the optimal energy management strategy of each node includes: Calculating a sub-gradient of each node according to the local objective function of each node; Update the dual variable of the corresponding node according to the sub-gradient of each node; Iteratively updating the initial node strategy of each node using a consensus mechanism to obtain the optimal energy management strategy for each node; The performing denoising on the first energy management data of each node to obtain the second energy management data of the corresponding node includes: Performing multi-scale decomposition on the first energy management data of each node to obtain corresponding multi-scale coefficients; Performing noise reduction processing on each of the multi-scale coefficients using a soft threshold function to obtain a noise-reduced multi-scale coefficient; Performing an inverse transformation on the noise-reduced multi-scale coefficients to obtain second energy management data of the corresponding node; Calculating the energy management characteristics of the target Internet of Things according to the second energy management data of each node includes: extracting a key feature of each of the nodes from the second energy management data of each of the nodes; fusing the key features of all the nodes to obtain the energy management features of the target Internet of Things; The process of integrating the key features of all the nodes includes introducing a dynamic weight allocation mechanism, wherein the weight coefficient in the dynamic weight allocation mechanism is dynamically adjusted by the ratio of the node energy fluctuation rate of the node to the energy storage capacity of the node.

5. An electronic device, characterized in that: It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute an Internet of Things energy management method as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the Internet of Things energy management method according to any one of claims 1 to 3.

Images