CN117896384B - Internet of things communication method, device, equipment and storage medium - Google Patents
Internet of things communication method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117896384B CN117896384B CN202410305756.0A CN202410305756A CN117896384B CN 117896384 B CN117896384 B CN 117896384B CN 202410305756 A CN202410305756 A CN 202410305756A CN 117896384 B CN117896384 B CN 117896384B
- Authority
- CN
- China
- Prior art keywords
- communication
- internet
- edge node
- things
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004891 communication Methods 0.000 title claims abstract description 326
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000001514 detection method Methods 0.000 claims abstract description 97
- 230000005856 abnormality Effects 0.000 claims abstract description 38
- 230000002159 abnormal effect Effects 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 29
- 238000013145 classification model Methods 0.000 claims abstract description 20
- 239000002245 particle Substances 0.000 claims description 45
- 230000008901 benefit Effects 0.000 claims description 38
- 230000006870 function Effects 0.000 claims description 31
- 239000013598 vector Substances 0.000 claims description 26
- 230000009466 transformation Effects 0.000 claims description 24
- 230000009471 action Effects 0.000 claims description 21
- 230000004927 fusion Effects 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 15
- 230000007246 mechanism Effects 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 230000006855 networking Effects 0.000 claims 4
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000005265 energy consumption Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a communication method, a device, equipment and a storage medium of the Internet of things, wherein the method comprises the following steps: performing edge node deployment based on the edge node pool range to form an edge node pool, and performing communication service on a plurality of pieces of Internet of things equipment through edge nodes in the edge node pool; collecting communication data among all the nodes of the Internet of things in the communication service process through an edge node pool by the gateway of the Internet of things, and detecting the data to obtain a communication quality value; inputting communication data corresponding to the edge nodes with the communication quality values smaller than the quality threshold value into an anomaly detection classification model to obtain corresponding anomaly detection types; and selecting a communication adjustment strategy corresponding to the abnormality detection type to adjust the corresponding edge node or the Internet of things equipment. The method carries out self-adaptive adjustment by accurately identifying the abnormal type and selecting a corresponding communication adjustment strategy according to the abnormal type. The robustness and the self-adaptive capacity of the Internet of things system in the face of abnormal conditions are improved.
Description
Technical Field
The present invention relates to the field of internet of things communications, and in particular, to an internet of things communication method, device, equipment and storage medium.
Background
With the rapid development of internet of things (IoT) technology, more and more devices are connected to each other through a network, so as to realize data exchange and communication, so as to support various intelligent applications. In the process, how to effectively manage and process data generated by a huge amount of internet of things equipment, and ensure the reliability and efficiency of communication. Currently, internet of things communication mainly relies on centralized data processing centers or cloud computing resources. However, with the increase in the number of devices and the complexity of application scenarios, such a centralized communication mode faces challenges such as high latency, high bandwidth pressure, data privacy and security issues. To address these problems, edge computing has been proposed as an emerging computing model that aims to reduce latency, improve communication efficiency, and reduce the stress on the central processing unit by processing data near the edges of the network. However, a flexible mechanism is lacking in the prior art to dynamically adjust the communication policy to cope with the change of the communication environment, which limits the self-adaptive capability and robustness of the internet of things system in the face of abnormal situations such as equipment failure, network congestion and the like.
Disclosure of Invention
The invention mainly aims to solve the technical problems of poor self-adaption capability and poor robustness of the existing communication of the Internet of things when abnormal conditions occur.
The first aspect of the present invention provides an internet of things communication method, which includes:
acquiring an Internet of things communication request among a plurality of Internet of things devices, and determining a corresponding edge node pool range according to the Internet of things communication request;
performing edge node deployment based on the edge node pool range to form an edge node pool, and performing communication service on the plurality of Internet of things devices through edge nodes in the edge node pool;
Collecting communication data among all the Internet of things nodes in the communication service process through the edge node pool by a preset Internet of things gateway, and carrying out data detection on the communication data to obtain a communication quality value of communication of all the Internet of things devices through the corresponding edge nodes;
Judging whether an edge node with a communication quality value smaller than a preset quality threshold exists in the edge node pool or not;
If yes, inputting the communication data corresponding to the edge node with the communication quality value smaller than the preset quality threshold value into a preset abnormal detection classification model to obtain a corresponding abnormal detection type;
And selecting a communication adjustment strategy corresponding to the anomaly detection type to adjust the corresponding edge node or the Internet of things equipment until the communication quality value of the edge node in the edge node pool is not smaller than the quality threshold.
Optionally, in a first implementation manner of the first aspect of the present invention, the performing edge node deployment based on the edge node pool range, forming an edge node pool, and performing communication service on the plurality of devices of the internet of things through edge nodes in the edge node pool includes:
Performing edge node deployment based on the edge node pool range to form an edge node pool, and acquiring communication connection relations among all the Internet of things devices;
Taking the Internet of things equipment with communication adjacency relations as target Internet of things equipment, and acquiring equipment data of the target Internet of things equipment and node data of each edge node in the edge node pool;
calculating loss data and benefit data of communication service of the target internet of things equipment provided by each edge node in the edge node pool based on the equipment data and the node data;
And selecting a first edge node corresponding to the target internet of things device from the edge node pool based on the loss data and the benefit data, and carrying out communication service on the plurality of internet of things devices through the first edge node.
Optionally, in a second implementation manner of the first aspect of the present invention, the selecting, based on the loss data and the benefit data, a first edge node corresponding to the target internet of things device from the edge node pool, and performing communication service on the plurality of internet of things devices through the first edge node includes:
Acquiring a benefit calculation function and constraint conditions of the benefit data, and taking the benefit calculation function as an objective function;
Performing particle swarm processing on edge nodes in the edge node pool to obtain particle positions and particle speeds of all particles;
Calculating the fitness value of each particle in the particle swarm based on the benefit calculation function, the constraint condition, the particle position, the particle speed and the loss data, and carrying out cyclic iteration on the particle position and the particle speed of each particle which are reproducibly allocated based on the fitness value until the preset termination condition is met;
and when a preset termination condition is met, determining a first edge node corresponding to the target Internet of things device from the edge node pool according to the optimal solution of the particle swarm processing.
Optionally, in a third implementation manner of the first aspect of the present invention, the acquiring, by the preset gateway of the internet of things, communication data between the nodes of the internet of things in the communication service process through the edge node pool, and performing data detection on the communication data, and obtaining a communication quality value of communication between the devices of the internet of things through the corresponding edge nodes includes:
collecting communication data among all the nodes of the Internet of things in the communication service process through the edge node pool by a preset gateway of the Internet of things, and taking the communication data as communication data points;
Acquiring a historical data point set corresponding to each Internet of things node, and calculating the statistical distance between the communication data point and each historical data point in the historical data point set;
and calculating the communication quality value of the corresponding internet of things equipment for communication through the corresponding edge node based on the statistical distance.
Optionally, in a fourth implementation manner of the first aspect of the present invention, inputting the communication data corresponding to the edge node with the communication quality value smaller than the preset quality threshold into a preset anomaly detection classification model, and obtaining the corresponding anomaly detection type includes:
Dividing communication data corresponding to edge nodes with communication quality values smaller than a preset quality threshold according to corresponding Internet of things equipment with communication connection relations to obtain first communication data and second communication data;
Inputting the first communication data and the second communication data into a preset abnormality detection classification model, wherein the abnormality detection classification model comprises an input layer, an attention mechanism layer, a feature fusion layer, a classification layer and an output layer;
performing data preprocessing and feature extraction on the first communication data and the second communication data through the input layer to obtain a first data feature and a second data feature;
calculating attention weight vectors corresponding to the first data features and the second data features through the attention mechanism layer;
performing feature fusion on the first data feature and the second data feature according to the attention weight vector through the feature fusion layer to obtain a corresponding fusion feature vector;
And carrying out abnormality detection classification according to the fusion feature vector through the classification layer to obtain a corresponding abnormality detection type, and outputting the abnormality detection type through the output layer.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the performing, by the classification layer, abnormality detection classification according to the fusion feature vector, to obtain a corresponding abnormality detection type, and outputting, by the output layer, the abnormality detection type includes:
Mapping the feature vector linear transformation to a high-dimensional feature space through the classification layer to obtain a linear transformation result;
Nonlinear transformation is carried out on the linear transformation result through a preset activation function, and a nonlinear transformation result is obtained;
mapping the nonlinear transformation result to a corresponding abnormality detection type through a full connection layer in the classification layer, and outputting the abnormality detection type through the output layer.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the anomaly detection type includes a communication interference type, and the selecting a communication adjustment policy corresponding to the anomaly detection type to adjust a corresponding edge node or an internet of things device includes:
Selecting a communication adjustment strategy corresponding to the communication interference type, and determining all edge nodes with the abnormal detection type of the communication interference type in the edge node pool as second edge nodes based on the communication adjustment strategy, and Internet of things equipment corresponding to the second edge nodes;
Acquiring node information of the second edge node and equipment information of the Internet of things equipment corresponding to the second edge node, and taking the node information and the equipment information as state representations;
Acquiring network parameters from a preset global network through each second edge node, and selecting a plurality of corresponding optimal actions from the action space of each second edge node according to the network parameters and a strategy network corresponding to each second edge node;
Updating state representations based on the plurality of optimal actions, and calculating a reward value of each optimal action by using a preset reward function;
Updating the corresponding strategy network based on the updated state representation and the rewarding value, updating the network parameters of the global network through the network parameters of the strategy networks, and returning to acquiring the network parameters from the preset global network through each second edge node until the preset iteration condition is reached;
and when a preset iteration condition is reached, adjusting node information of a second edge node and the Internet of things equipment corresponding to the second edge node based on a preset global network.
The second aspect of the present invention provides an internet of things communication device, which includes:
The request acquisition module is used for acquiring Internet of things communication requests among a plurality of Internet of things devices and determining a corresponding edge node pool range according to the Internet of things communication requests;
the deployment module is used for carrying out edge node deployment based on the edge node pool range to form an edge node pool, and carrying out communication service on the plurality of Internet of things devices through edge nodes in the edge node pool;
The detection module is used for collecting communication data among all the Internet of things nodes in the communication service process through the preset Internet of things gateway through the edge node pool, and carrying out data detection on the communication data to obtain a communication quality value of communication of all the Internet of things devices through the corresponding edge nodes;
the judging module is used for judging whether an edge node with a communication quality value smaller than a preset quality threshold exists in the edge node pool or not;
The classification module is used for inputting the communication data corresponding to the edge nodes with the communication quality values smaller than the preset quality threshold into a preset abnormal detection classification model if the communication quality values are smaller than the preset quality threshold, and obtaining the corresponding abnormal detection types;
And the adjusting module is used for selecting a communication adjusting strategy corresponding to the abnormal detection type to adjust the corresponding edge node or the Internet of things equipment until the communication quality value of the edge node in the edge node pool is not smaller than the quality threshold.
A third aspect of the present invention provides an internet of things communication device, comprising: a memory and at least one processor, the memory having instructions stored therein, the memory and the at least one processor being interconnected by a line; and the at least one processor invokes the instructions in the memory to enable the internet of things communication device to execute the steps of the internet of things communication method.
A fourth aspect of the present invention provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the steps of the internet of things communication method described above.
According to the Internet of things communication method, the device, the equipment and the storage medium, the edge node deployment is carried out based on the edge node pool range to form the edge node pool, and the communication service is carried out on a plurality of Internet of things equipment through the edge nodes in the edge node pool; collecting communication data among all the nodes of the Internet of things in the communication service process through an edge node pool by the gateway of the Internet of things, and detecting the data to obtain a communication quality value; inputting communication data corresponding to the edge nodes with the communication quality values smaller than the quality threshold value into an anomaly detection classification model to obtain corresponding anomaly detection types; and selecting a communication adjustment strategy corresponding to the abnormality detection type to adjust the corresponding edge node or the Internet of things equipment. The method carries out self-adaptive adjustment by accurately identifying the abnormal type and selecting a corresponding communication adjustment strategy according to the abnormal type. The robustness and the self-adaptive capacity of the Internet of things system in the face of abnormal conditions are improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 is a schematic diagram of a first embodiment of a communication method of the internet of things in an embodiment of the present invention;
FIG. 2 is a schematic diagram of an embodiment of an Internet of things communication device according to an embodiment of the present invention;
Fig. 3 is a schematic diagram of an embodiment of an internet of things communication device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The terms "comprising" and "having" and any variations thereof, as used in the embodiments of the present invention, are intended to cover non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed or inherent to such process, method, article, or apparatus but may optionally include other steps or elements not listed or inherent to such process, method, article, or apparatus.
For the sake of understanding the present embodiment, first, a detailed description is provided of an internet of things communication method disclosed in the present embodiment. As shown in fig. 1, the method comprises the following steps:
101. Acquiring an Internet of things communication request among a plurality of Internet of things devices, and determining a corresponding edge node pool range according to the Internet of things communication request;
In one embodiment of the present invention, in such a scenario, the plurality of internet of things devices may be various types of smart devices, including sensors, actuators, controllers, smart home devices, industrial devices, and the like. The devices are connected to a network through the technology of the Internet of things, have the functions of data acquisition, processing, communication and the like, and can exchange information with each other and initiate a communication request. There are multiple situations between the internet of things devices that need to initiate an internet of things communication request, for example, after the sensor device collects data, the sensor device needs to upload the data to the cloud for analysis and processing, the controller device needs to execute corresponding operations when receiving a remote instruction, and the intelligent home device needs to be linked or interacted with other devices.
Specifically, when an internet of things communication request is initiated among a plurality of internet of things devices, the system can determine the corresponding edge node pool range according to the requests, and particularly, by collecting and analyzing the communication requests initiated by the plurality of internet of things devices, including information such as communication types, data amounts, communication frequencies and the like, the system determines the edge node pool range suitable for processing the requests according to the characteristics and the requirements of the internet of things communication request. This includes taking into account factors such as location distribution of edge nodes, computing resources, network bandwidth, etc., to ensure optimal communication services are provided to the device.
Specifically, in the process of determining the range of the edge node pool, according to the data volume carried by the communication request of the internet of things and the communication frequency, the processing capacity and the network bandwidth of the edge node are evaluated, so that the selected edge node can bear the communication requests. Considering the distance between the Internet of things equipment and the edge nodes, selecting the edge node with a closer distance to reduce communication delay and reduce energy consumption in network transmission. Computing resources of the edge node, including processor performance, memory size, storage capacity, etc., are evaluated to ensure that the edge node has sufficient computing power to handle the internet of things communication request. Considering the data security requirement related to the communication request of the Internet of things, selecting an edge node with a corresponding security mechanism to process the communication request of the sensitive data. Network connectivity of the edge node is assessed, including network stability, bandwidth, etc., to ensure that the edge node is able to reliably communicate with the cloud platform and other devices. In combination with the above factors, the system can determine the range of the edge node pool suitable for processing the communication request of the internet of things through an intelligent algorithm or a rule engine. For example, a dynamic allocation policy based on location information may be employed to select the best edge node based on device location and network load conditions; dynamic adjustment policies based on workload may also be employed to dynamically adjust the allocation of edge nodes based on their computing resource utilization and communication load.
102. Performing edge node deployment based on the edge node pool range to form an edge node pool, and performing communication service on the plurality of Internet of things devices through edge nodes in the edge node pool;
In one embodiment of the present invention, the performing edge node deployment based on the edge node pool range, forming an edge node pool, and performing communication service on the plurality of devices of the internet of things through edge nodes in the edge node pool includes: performing edge node deployment based on the edge node pool range to form an edge node pool, and acquiring communication connection relations among all the Internet of things devices; taking the Internet of things equipment with communication adjacency relations as target Internet of things equipment, and acquiring equipment data of the target Internet of things equipment and node data of each edge node in the edge node pool; calculating loss data and benefit data of communication service of the target internet of things equipment provided by each edge node in the edge node pool based on the equipment data and the node data; and selecting a first edge node corresponding to the target internet of things device from the edge node pool based on the loss data and the benefit data, and carrying out communication service on the plurality of internet of things devices through the first edge node.
In particular, in the process of edge node pool placement, first, it is necessary to determine the geographic extent of the edge node pool, i.e., which regions or locations are to be included in the edge node pool. Based on the location of the data source, user distribution, or other specific needs. For each potential edge node location, its network connectivity needs to be assessed. The edge nodes need to communicate with a central data center or other edge nodes and thus need to ensure that the network connection is reliable and with low latency. And formulating a node deployment strategy according to the geographic range and the network connectivity. This involves determining the number of edge nodes per location, the node type (e.g., server, gateway or sensor) and the topology between them. The computing resources, storage capacity, and network bandwidth of each edge node are determined and considered how these resources are allocated and managed throughout the pool of edge nodes, and how load balancing is achieved. According to the design, deployment of edge nodes is started. This involves the operations of installing hardware devices, configuring network connections, deploying software and applications, etc.
Specifically, when calculating the loss data and the benefit data, first, device data, such as data transmission amount, communication requirement, etc., of the target internet of things device is collected, and node data, such as calculation resources, energy consumption, etc., of the edge node is collected. Based on the communication connection relationship between the devices and the network condition, the communication loss generated when the edge node provides the communication service is calculated. This can be estimated based on factors such as the amount of data transmitted, network delay, etc. The computing resources and energy consumed by the edge node in providing the communication service are analyzed. This includes CPU utilization, memory usage, power consumption of the node, etc. And evaluating the service benefit of the edge node according to the benefit brought by the provided communication service. This may be determined based on metrics such as communication delay, data security, etc. And comprehensively considering communication loss, calculation resource consumption and service benefit to obtain the total loss data and benefit data of the edge node for providing communication service. Based on the loss data and the benefit data, an optimal edge node is selected from the pool of edge nodes to provide the communication service. The selection criteria may be to minimize overall losses or maximize benefits.
Further, the selecting, based on the loss data and the benefit data, a first edge node corresponding to the target internet of things device from the edge node pool, and performing communication service on the plurality of internet of things devices through the first edge node includes: acquiring a benefit calculation function and constraint conditions of the benefit data, and taking the benefit calculation function as an objective function; performing particle swarm processing on edge nodes in the edge node pool to obtain particle positions and particle speeds of all particles; calculating the fitness value of each particle in the particle swarm based on the benefit calculation function, the constraint condition, the particle position, the particle speed and the loss data, and carrying out cyclic iteration on the particle position and the particle speed of each particle which are reproducibly allocated based on the fitness value until the preset termination condition is met; and when a preset termination condition is met, determining a first edge node corresponding to the target Internet of things device from the edge node pool according to the optimal solution of the particle swarm processing.
Specifically, the benefit calculation function is a mathematical function used to evaluate the benefit of the edge node providing communication services. It can quantify the quality and value of the service based on different metrics, such as communication delay, data security, energy consumption, etc. For example, one possible benefit calculation function is to minimize overall cost by balancing communication latency and energy consumption, or to optimize quality of service by maximizing communication rate and minimizing data loss rate. The constraint condition is a condition for limiting the problem solution space, and the feasibility and the rationality of the solution are ensured. In this case, constraints may include computational resource limitations of the edge nodes, energy consumption limitations, communication bandwidth limitations, and the like. For example, the computing resources of the edge node cannot exceed its maximum capacity, the energy consumption cannot exceed an acceptable range, the communication bandwidth cannot exceed the bandwidth limitations of the network, etc. Particle swarm processing is an optimization algorithm for finding optimal solutions in a multi-dimensional search space. In this algorithm, each particle represents a solution in the problem space whose position represents the position of the solution in the problem space and velocity represents the direction and velocity of movement of the particle during the search. Particle swarm processing gradually optimizes the solution by modeling the movement and interaction of particles in the solution space. The fitness value is an index for evaluating the degree of merit of each particle solution. In this case, the fitness value may be calculated from the benefit calculation function, the constraint, and the loss data. In general, a higher fitness value indicates a better solution. In particle swarm algorithms, fitness values are used to guide movement and updating of particles. By calculating fitness values for each particle solution, it may be determined which solutions are optimal solutions or more nearly optimal solutions.
103. Collecting communication data among all the Internet of things nodes in the communication service process through the edge node pool by a preset Internet of things gateway, and carrying out data detection on the communication data to obtain a communication quality value of communication of all the Internet of things devices through the corresponding edge nodes;
In an embodiment of the present invention, the acquiring, by the preset gateway of the internet of things, communication data between the nodes of the internet of things in the communication service process through the edge node pool, and performing data detection on the communication data, and obtaining a communication quality value of communication between the devices of the internet of things through the corresponding edge nodes includes: collecting communication data among all the nodes of the Internet of things in the communication service process through the edge node pool by a preset gateway of the Internet of things, and taking the communication data as communication data points; acquiring a historical data point set corresponding to each Internet of things node, and calculating the statistical distance between the communication data point and each historical data point in the historical data point set; and calculating the communication quality value of the corresponding internet of things equipment for communication through the corresponding edge node based on the statistical distance.
Specifically, the historical data point set refers to a set of data points of the internet of things node that were previously collected. These data points may include communication related indicators such as communication delay, data loss rate, signal strength, and the like, as well as other parameters related to communication quality. The purpose of the historical data point set is to provide a reference base for evaluating the performance of the current communication data point. Statistical distance calculations are used to measure the degree of similarity or difference between a communication data point and each of the historical data points in the set of historical data points. Common statistical distances include euclidean distance, manhattan distance, chebyshev distance, and the like. These distance measurement methods may be selected according to the specific circumstances. For example, euclidean distance may be used to measure the spatial distance between a communication data point and a historical data point, manhattan distance may be used to measure the absolute difference between them, chebyshev distance may be used to measure the maximum difference between them, and so on. Based on the statistical distance, a distance between the communication data point and each of the set of historical data points can be calculated. These distance values may reflect the degree of similarity or difference between the current communication data point and the historical data point. The communication quality value may be calculated from these distance values. For example, a function may be defined to convert the distance to a communication quality value, which may be a linear function, an exponential function, a logarithmic function, etc., to map the distance into a suitable communication quality range. A higher communication quality value indicates a better communication quality, and conversely, a worse communication quality.
104. Judging whether an edge node with a communication quality value smaller than a preset quality threshold exists in the edge node pool or not;
105. if yes, inputting the communication data corresponding to the edge node with the communication quality value smaller than the preset quality threshold value into a preset abnormal detection classification model to obtain a corresponding abnormal detection type;
In one embodiment of the present invention, inputting the communication data corresponding to the edge node with the communication quality value smaller than the preset quality threshold into the preset anomaly detection classification model, and obtaining the corresponding anomaly detection type includes: dividing communication data corresponding to edge nodes with communication quality values smaller than a preset quality threshold according to corresponding Internet of things equipment with communication connection relations to obtain first communication data and second communication data; inputting the first communication data and the second communication data into a preset abnormality detection classification model, wherein the abnormality detection classification model comprises an input layer, an attention mechanism layer, a feature fusion layer, a classification layer and an output layer; performing data preprocessing and feature extraction on the first communication data and the second communication data through the input layer to obtain a first data feature and a second data feature; calculating attention weight vectors corresponding to the first data features and the second data features through the attention mechanism layer; performing feature fusion on the first data feature and the second data feature according to the attention weight vector through the feature fusion layer to obtain a corresponding fusion feature vector; and carrying out abnormality detection classification according to the fusion feature vector through the classification layer to obtain a corresponding abnormality detection type, and outputting the abnormality detection type through the output layer.
Specifically, first, communication data corresponding to edge nodes whose communication quality values are smaller than a preset quality threshold are divided into two groups: first communication data and second communication data. This division is made based on the internet of things devices having a communication connection relationship, meaning that communication data of devices having a communication relationship with each other are divided into the same group of inputs. One communication data and a second communication data are input to an input layer of the abnormality detection classification model. At the input layer, the data is subjected to data preprocessing and feature extraction steps to ensure that the data input to the model has the proper format and important features. This includes normalization, or other preprocessing operations, as well as extracting relevant features from the raw data. At the attention mechanism layer, for the first data feature and the second data feature, their corresponding attention weight vectors are calculated. This step aims at determining which features are more important to the anomaly detection task, i.e. to strengthen or weaken the contribution of the different features, to increase the sensitivity of the model to anomaly patterns. Based on the calculated attention weight vector, the feature fusion layer fuses the first data feature and the second data feature. This process combines the features of the two sets of data together to form a fused feature vector. The manner of fusion may be a weighted summation, where the weights are determined by an attention weight vector to emphasize important features. The fused feature vectors are input to a classification layer that performs anomaly detection classification by a trained model. The model adopts various machine learning algorithms, such as a neural network, a support vector machine and the like. The goal of the classification layer is to identify patterns in the fused feature vectors and assign them to different anomaly detection types. Finally, the output of the classification layer is passed to the output layer, outputting the type of anomaly detection. This type may represent different anomaly patterns reflecting the model's understanding of the degree of anomalies in the input data. The output may be an anomaly score, category label, or other form, depending on the task setting for anomaly detection.
Further, the performing, by the classification layer, abnormality detection classification according to the fusion feature vector, to obtain a corresponding abnormality detection type, and outputting, by the output layer, the abnormality detection type includes: mapping the feature vector linear transformation to a high-dimensional feature space through the classification layer to obtain a linear transformation result; nonlinear transformation is carried out on the linear transformation result through a preset activation function, and a nonlinear transformation result is obtained; mapping the nonlinear transformation result to a corresponding abnormality detection type through a full connection layer in the classification layer, and outputting the abnormality detection type through the output layer.
Specifically, in the classification layer, the feature vector is first mapped to a high-dimensional feature space through linear transformation, and a linear transformation result is generated. This mapping process may increase the complexity and degree of differentiation between features. Then, a preset activation function is applied to the linear transformation result to perform nonlinear transformation, so as to obtain the nonlinear transformation result. The role of the activation function is to introduce non-linear factors that enable the model to learn more complex data patterns and features. These nonlinear transformation results are then mapped to the corresponding anomaly detection types by the fully connected layer in the classification layer. The function of the full connection layer is to establish the relation between the characteristics and the output category, and to realize the prediction of the abnormality detection type through the adjustment of the weight parameter. And finally, outputting the predicted abnormality detection type through an output layer to complete the whole abnormality detection classification process.
106. And selecting a communication adjustment strategy corresponding to the anomaly detection type to adjust the corresponding edge node or the Internet of things equipment until the communication quality value of the edge node in the edge node pool is not smaller than the quality threshold.
In one embodiment of the present invention, the anomaly detection type includes a communication interference type, and the selecting a communication adjustment policy corresponding to the anomaly detection type to adjust a corresponding edge node or an internet of things device includes: selecting a communication adjustment strategy corresponding to the communication interference type, and determining all edge nodes with the abnormal detection type of the communication interference type in the edge node pool as second edge nodes based on the communication adjustment strategy, and Internet of things equipment corresponding to the second edge nodes; acquiring node information of the second edge node and equipment information of the Internet of things equipment corresponding to the second edge node, and taking the node information and the equipment information as state representations; acquiring network parameters from a preset global network through each second edge node, and selecting a plurality of corresponding optimal actions from the action space of each second edge node according to the network parameters and a strategy network corresponding to each second edge node; updating state representations based on the plurality of optimal actions, and calculating a reward value of each optimal action by using a preset reward function; updating the corresponding strategy network based on the updated state representation and the rewarding value, updating the network parameters of the global network through the network parameters of the strategy networks, and returning to acquiring the network parameters from the preset global network through each second edge node until the preset iteration condition is reached; and when a preset iteration condition is reached, adjusting node information of a second edge node and the Internet of things equipment corresponding to the second edge node based on a preset global network.
Specifically, the node information includes:
Node identifier: information uniquely identifying the node, such as a node ID or name;
Node position: the information describing the position of the node can be geographic position coordinates or other position descriptions;
Node state: information indicating the current state of the node, such as online/offline state, running state, etc.;
Node resources: information describing available resources of the node, such as processor speed, memory size, storage capacity, etc.;
other network and application specific information: possibly including network connection information, bandwidth, delay, etc.
The device information includes:
device identifier: information uniquely identifying the device, such as a device ID or serial number.
Device type: information describing the type or class of device, such as sensors, actuators, smart devices, etc.
Device status: information indicating the current state of the device, such as on/off state, normal/abnormal state, etc.
Device attributes: information describing the device characteristics and functions, such as sensor type, data acquisition frequency, etc.
Device location: the information describing the location of the device may be associated with the location of the node or may be described separately.
By taking node information and device information as state representations when making the selection of the best action, it may be necessary to encode or embed it in a vector to facilitate algorithmic processing. And selecting a plurality of corresponding optimal actions from the action space of each second edge node by using a preset global network. This typically involves performing some sort of search or optimization algorithm in the action space to find the optimal set of actions in the current state. The action may be a combination of a series of parameters for adjusting the communication policy or other operation. Based on the selected plurality of best actions, the state representation is updated to reflect the new state after the actions were taken. And calculating the rewarding value of each optimal action by using a preset rewarding function. The bonus function is defined in terms of goals and performance metrics of the system, generally encouraging the system to evolve toward a good state. The policy network is updated based on the updated status representation and the prize value. This may involve updating network parameters using an optimization algorithm such as gradient descent. The network parameters of the global network are then updated by the network parameters of the plurality of policy networks to enable the global network to reflect the most current knowledge and policies. Repeating the above steps until reaching a preset iteration condition, for example, reaching a certain training round or reaching a certain performance index. When the preset iteration condition is reached, the node information of the second edge node and the corresponding internet of things equipment can be adjusted according to a preset global network.
In the embodiment, an edge node pool is formed by edge node deployment based on the range of the edge node pool, and communication service is carried out on a plurality of pieces of Internet of things equipment through edge nodes in the edge node pool; collecting communication data among all the nodes of the Internet of things in the communication service process through an edge node pool by the gateway of the Internet of things, and detecting the data to obtain a communication quality value; inputting communication data corresponding to the edge nodes with the communication quality values smaller than the quality threshold value into an anomaly detection classification model to obtain corresponding anomaly detection types; and selecting a communication adjustment strategy corresponding to the abnormality detection type to adjust the corresponding edge node or the Internet of things equipment. The method carries out self-adaptive adjustment by accurately identifying the abnormal type and selecting a corresponding communication adjustment strategy according to the abnormal type. The robustness and the self-adaptive capacity of the Internet of things system in the face of abnormal conditions are improved.
The method for communication of the internet of things in the embodiment of the present invention is described above, and the device for communication of the internet of things in the embodiment of the present invention is described below, referring to fig. 2, an embodiment of the device for communication of the internet of things in the embodiment of the present invention includes:
the request acquisition module 201 is configured to acquire an internet of things communication request between a plurality of internet of things devices, and determine a corresponding edge node pool range according to the internet of things communication request;
A deployment module 202, configured to perform edge node deployment based on the edge node pool range, form an edge node pool, and perform communication service on the plurality of internet of things devices through edge nodes in the edge node pool;
the detection module 203 is configured to collect, through a preset internet of things gateway, communication data between the internet of things nodes in the communication service process through the edge node pool, and perform data detection on the communication data, so as to obtain a communication quality value of communication between the internet of things devices through the corresponding edge nodes;
A judging module 204, configured to judge whether an edge node whose communication quality value is less than a preset quality threshold exists in the edge node pool;
the classification module 205 is configured to, if yes, input communication data corresponding to an edge node with a communication quality value smaller than a preset quality threshold into a preset anomaly detection classification model to obtain a corresponding anomaly detection type;
And the adjusting module 206 is configured to select a communication adjustment policy corresponding to the anomaly detection type to adjust a corresponding edge node or an internet of things device until a communication quality value of an edge node in the edge node pool is not less than the quality threshold.
In the embodiment of the invention, the internet of things communication device runs the internet of things communication method, and the internet of things communication device deploys edge nodes based on the range of the edge node pool to form the edge node pool and performs communication service on a plurality of internet of things devices through the edge nodes in the edge node pool; collecting communication data among all the nodes of the Internet of things in the communication service process through an edge node pool by the gateway of the Internet of things, and detecting the data to obtain a communication quality value; inputting communication data corresponding to the edge nodes with the communication quality values smaller than the quality threshold value into an anomaly detection classification model to obtain corresponding anomaly detection types; and selecting a communication adjustment strategy corresponding to the abnormality detection type to adjust the corresponding edge node or the Internet of things equipment. The method carries out self-adaptive adjustment by accurately identifying the abnormal type and selecting a corresponding communication adjustment strategy according to the abnormal type. The robustness and the self-adaptive capacity of the Internet of things system in the face of abnormal conditions are improved.
Fig. 2 above describes the internet of things communication device in the embodiment of the present invention in detail from the perspective of a modularized functional entity, and the internet of things communication device in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 3 is a schematic structural diagram of an internet of things communication device according to an embodiment of the present invention, where the internet of things communication device 300 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 310 (e.g., one or more processors) and a memory 320, and one or more storage mediums 330 (e.g., one or more mass storage devices) storing application programs 333 or data 332. Wherein memory 320 and storage medium 330 may be transitory or persistent storage. The program stored on the storage medium 330 may include one or more modules (not shown), each of which may include a series of instruction operations in the internet of things communication device 300. Still further, the processor 310 may be configured to communicate with the storage medium 330, and execute a series of instruction operations in the storage medium 330 on the internet of things communication device 300 to implement the steps of the internet of things communication method described above.
The internet of things communication device 300 may also include one or more power supplies 340, one or more wired or wireless network interfaces 350, one or more input/output interfaces 360, and/or one or more operating systems 331, such as Windows Serve, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the configuration of the internet of things communication device shown in fig. 3 is not limiting of the internet of things communication device provided by the present invention, and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, and may also be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, when the instructions are executed on a computer, cause the computer to perform the steps of the internet of things communication method.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system or apparatus and unit described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. The communication method of the Internet of things is characterized by comprising the following steps of:
acquiring an Internet of things communication request among a plurality of Internet of things devices, and determining a corresponding edge node pool range according to the Internet of things communication request;
performing edge node deployment based on the edge node pool range to form an edge node pool, and acquiring communication connection relations among all the Internet of things devices; taking the Internet of things equipment with communication adjacency relations as target Internet of things equipment, and acquiring equipment data of the target Internet of things equipment and node data of each edge node in the edge node pool; calculating loss data and benefit data of communication service of the target internet of things equipment provided by each edge node in the edge node pool based on the equipment data and the node data; selecting a first edge node corresponding to the target internet of things device from the edge node pool based on the loss data and the benefit data, and performing communication service on the plurality of internet of things devices through the first edge node;
Collecting communication data among all the Internet of things nodes in the communication service process through the edge node pool by a preset Internet of things gateway, and carrying out data detection on the communication data to obtain a communication quality value of communication of all the Internet of things devices through the corresponding edge nodes;
Judging whether an edge node with a communication quality value smaller than a preset quality threshold exists in the edge node pool or not;
If yes, inputting the communication data corresponding to the edge node with the communication quality value smaller than the preset quality threshold value into a preset abnormal detection classification model to obtain a corresponding abnormal detection type;
And selecting a communication adjustment strategy corresponding to the anomaly detection type to adjust the corresponding edge node or the Internet of things equipment until the communication quality value of the edge node in the edge node pool is not smaller than the quality threshold.
2. The method according to claim 1, wherein selecting a first edge node corresponding to the target internet of things device from the edge node pool based on the loss data and the benefit data, and performing communication service on the plurality of internet of things devices through the first edge node comprises:
Acquiring a benefit calculation function and constraint conditions of the benefit data, and taking the benefit calculation function as an objective function;
Performing particle swarm processing on edge nodes in the edge node pool to obtain particle positions and particle speeds of all particles;
Calculating the fitness value of each particle in the particle swarm based on the benefit calculation function, the constraint condition, the particle position, the particle speed and the loss data, and carrying out cyclic iteration on the particle position and the particle speed of each particle which are reproducibly allocated based on the fitness value until the preset termination condition is met;
and when a preset termination condition is met, determining a first edge node corresponding to the target Internet of things device from the edge node pool according to the optimal solution of the particle swarm processing.
3. The method according to claim 1, wherein the acquiring, by the preset gateway, communication data between the nodes of the internet of things in the communication service process through the edge node pool, and performing data detection on the communication data, and obtaining a communication quality value of communication between the devices of the internet of things through the corresponding edge nodes includes:
collecting communication data among all the nodes of the Internet of things in the communication service process through the edge node pool by a preset gateway of the Internet of things, and taking the communication data as communication data points;
Acquiring a historical data point set corresponding to each Internet of things node, and calculating the statistical distance between the communication data point and each historical data point in the historical data point set;
and calculating the communication quality value of the corresponding internet of things equipment for communication through the corresponding edge node based on the statistical distance.
4. The method of claim 1, wherein inputting the communication data corresponding to the edge node with the communication quality value smaller than the preset quality threshold into the preset anomaly detection classification model to obtain the corresponding anomaly detection type comprises:
Dividing communication data corresponding to edge nodes with communication quality values smaller than a preset quality threshold according to corresponding Internet of things equipment with communication connection relations to obtain first communication data and second communication data;
Inputting the first communication data and the second communication data into a preset abnormality detection classification model, wherein the abnormality detection classification model comprises an input layer, an attention mechanism layer, a feature fusion layer, a classification layer and an output layer;
performing data preprocessing and feature extraction on the first communication data and the second communication data through the input layer to obtain a first data feature and a second data feature;
calculating attention weight vectors corresponding to the first data features and the second data features through the attention mechanism layer;
performing feature fusion on the first data feature and the second data feature according to the attention weight vector through the feature fusion layer to obtain a corresponding fusion feature vector;
And carrying out abnormality detection classification according to the fusion feature vector through the classification layer to obtain a corresponding abnormality detection type, and outputting the abnormality detection type through the output layer.
5. The method according to claim 4, wherein the performing, by the classification layer, abnormality detection classification according to the fusion feature vector, to obtain a corresponding abnormality detection type, and outputting, by the output layer, the abnormality detection type includes:
Mapping the feature vector linear transformation to a high-dimensional feature space through the classification layer to obtain a linear transformation result;
Nonlinear transformation is carried out on the linear transformation result through a preset activation function, and a nonlinear transformation result is obtained;
mapping the nonlinear transformation result to a corresponding abnormality detection type through a full connection layer in the classification layer, and outputting the abnormality detection type through the output layer.
6. The internet of things communication method according to claim 1, wherein the anomaly detection type includes a communication interference type, and the selecting a communication adjustment policy corresponding to the anomaly detection type adjusts a corresponding edge node or an internet of things device includes:
Selecting a communication adjustment strategy corresponding to the communication interference type, and determining all edge nodes with the abnormal detection type of the communication interference type in the edge node pool as second edge nodes based on the communication adjustment strategy, and Internet of things equipment corresponding to the second edge nodes;
Acquiring node information of the second edge node and equipment information of the Internet of things equipment corresponding to the second edge node, and taking the node information and the equipment information as state representations;
Acquiring network parameters from a preset global network through each second edge node, and selecting a plurality of corresponding optimal actions from the action space of each second edge node according to the network parameters and a strategy network corresponding to each second edge node;
Updating state representations based on the plurality of optimal actions, and calculating a reward value of each optimal action by using a preset reward function;
Updating the corresponding strategy network based on the updated state representation and the rewarding value, updating the network parameters of the global network through the network parameters of the strategy networks, and returning to acquiring the network parameters from the preset global network through each second edge node until the preset iteration condition is reached;
and when a preset iteration condition is reached, adjusting node information of a second edge node and the Internet of things equipment corresponding to the second edge node based on a preset global network.
7. The utility model provides an thing networking communication device which characterized in that, thing networking communication device includes:
The request acquisition module is used for acquiring Internet of things communication requests among a plurality of Internet of things devices and determining a corresponding edge node pool range according to the Internet of things communication requests;
The deployment module is used for carrying out edge node deployment based on the edge node pool range to form an edge node pool and acquiring communication connection relations among all the Internet of things devices; taking the Internet of things equipment with communication adjacency relations as target Internet of things equipment, and acquiring equipment data of the target Internet of things equipment and node data of each edge node in the edge node pool; calculating loss data and benefit data of communication service of the target internet of things equipment provided by each edge node in the edge node pool based on the equipment data and the node data; selecting a first edge node corresponding to the target internet of things device from the edge node pool based on the loss data and the benefit data, and performing communication service on the plurality of internet of things devices through the first edge node;
The detection module is used for collecting communication data among all the Internet of things nodes in the communication service process through the preset Internet of things gateway through the edge node pool, and carrying out data detection on the communication data to obtain a communication quality value of communication of all the Internet of things devices through the corresponding edge nodes;
the judging module is used for judging whether an edge node with a communication quality value smaller than a preset quality threshold exists in the edge node pool or not;
The classification module is used for inputting the communication data corresponding to the edge nodes with the communication quality values smaller than the preset quality threshold into a preset abnormal detection classification model if the communication quality values are smaller than the preset quality threshold, and obtaining the corresponding abnormal detection types;
And the adjusting module is used for selecting a communication adjusting strategy corresponding to the abnormal detection type to adjust the corresponding edge node or the Internet of things equipment until the communication quality value of the edge node in the edge node pool is not smaller than the quality threshold.
8. The utility model provides an thing networking communication equipment which characterized in that, thing networking communication equipment includes: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the internet of things communication device to perform the steps of the internet of things communication method of any of claims 1-6.
9. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the steps of the internet of things communication method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410305756.0A CN117896384B (en) | 2024-03-18 | 2024-03-18 | Internet of things communication method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410305756.0A CN117896384B (en) | 2024-03-18 | 2024-03-18 | Internet of things communication method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117896384A CN117896384A (en) | 2024-04-16 |
| CN117896384B true CN117896384B (en) | 2024-05-14 |
Family
ID=90647780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410305756.0A Active CN117896384B (en) | 2024-03-18 | 2024-03-18 | Internet of things communication method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117896384B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109347834A (en) * | 2018-10-24 | 2019-02-15 | 广东工业大学 | Detection method, device and the equipment of abnormal data in Internet of Things edge calculations environment |
| CN111694636A (en) * | 2020-05-11 | 2020-09-22 | 国网江苏省电力有限公司南京供电分公司 | Electric power Internet of things container migration method oriented to edge network load balancing |
| CN115134403A (en) * | 2022-08-30 | 2022-09-30 | 深圳市精极工业互联网有限公司 | Internet of things communication assembly management and control system and method supporting multi-protocol access |
| CN116502162A (en) * | 2023-04-11 | 2023-07-28 | 河北工程大学 | Abnormal computing power federal detection method, system and medium in edge computing power network |
| CN116760884A (en) * | 2023-08-14 | 2023-09-15 | 海南智慧海事科技有限公司 | Ocean big data cloud service system and application method |
| CN117119484A (en) * | 2023-08-04 | 2023-11-24 | 太仓市同维电子有限公司 | Intelligent 5G network communication system |
| CN117201504A (en) * | 2023-11-08 | 2023-12-08 | 福州高新区熠云科技有限公司 | Edge node network data flow direction control method, system, equipment and medium |
| CN117221088A (en) * | 2023-10-08 | 2023-12-12 | 仙桃职业学院 | Computer network intensity detection system and device |
-
2024
- 2024-03-18 CN CN202410305756.0A patent/CN117896384B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109347834A (en) * | 2018-10-24 | 2019-02-15 | 广东工业大学 | Detection method, device and the equipment of abnormal data in Internet of Things edge calculations environment |
| CN111694636A (en) * | 2020-05-11 | 2020-09-22 | 国网江苏省电力有限公司南京供电分公司 | Electric power Internet of things container migration method oriented to edge network load balancing |
| CN115134403A (en) * | 2022-08-30 | 2022-09-30 | 深圳市精极工业互联网有限公司 | Internet of things communication assembly management and control system and method supporting multi-protocol access |
| CN116502162A (en) * | 2023-04-11 | 2023-07-28 | 河北工程大学 | Abnormal computing power federal detection method, system and medium in edge computing power network |
| CN117119484A (en) * | 2023-08-04 | 2023-11-24 | 太仓市同维电子有限公司 | Intelligent 5G network communication system |
| CN116760884A (en) * | 2023-08-14 | 2023-09-15 | 海南智慧海事科技有限公司 | Ocean big data cloud service system and application method |
| CN117221088A (en) * | 2023-10-08 | 2023-12-12 | 仙桃职业学院 | Computer network intensity detection system and device |
| CN117201504A (en) * | 2023-11-08 | 2023-12-08 | 福州高新区熠云科技有限公司 | Edge node network data flow direction control method, system, equipment and medium |
Non-Patent Citations (4)
| Title |
|---|
| 智能制造场景的5G应用展望;史彦军;韩俏梅;沈卫明;WANG Lihui;WANG Xianbin;;中国机械工程(第02期);全文 * |
| 边缘计算资源分配与任务调度优化综述;王凌等人;《知乎》;20211122;全文 * |
| 边缘计算迁移研究综述;朱友康;乐光学;杨晓慧;刘建生;;电信科学;20190423(第04期);全文 * |
| 面向物联网传感器事件监测的双向反馈系统;杨静;辛宇;谢志强;;计算机学报;20130315(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117896384A (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112287990A (en) | Model optimization method of edge cloud collaborative support vector machine based on online learning | |
| CN117156442A (en) | Cloud data security protection method and system based on 5G network | |
| Ryabko et al. | Graph model of Fog Computing system | |
| Kumar et al. | Novel Dynamic Scaling Algorithm for Energy Efficient Cloud Computing. | |
| US20240095529A1 (en) | Neural Network Optimization Method and Apparatus | |
| CN117896384B (en) | Internet of things communication method, device, equipment and storage medium | |
| Ryabko et al. | Graph theory methods for fog computing: A pseudo-random task graph model for evaluating mobile cloud, fog and edge computing systems | |
| CN115545198B (en) | Edge intelligent collaborative inference method and system based on deep learning model | |
| EP4080789A1 (en) | Enhanced uncertainty management for optical communication systems | |
| CN116109058A (en) | Substation inspection management method and device based on deep reinforcement learning | |
| EP3729765A1 (en) | System and method for predicting the state changes of network nodes | |
| CN115275975A (en) | Method and device for determining electric power data matching degree of optical storage charging station | |
| CN114490303A (en) | Fault root cause determination method and device and cloud equipment | |
| Xu et al. | Adaptive anomaly detection strategy based on reinforcement learning | |
| Martins et al. | Hercules: A context-aware multiple application and multisensor data fusion algorithm | |
| CN115776445B (en) | Traffic migration-oriented node identification method, device, equipment and storage medium | |
| Damaševičius et al. | Short time prediction of cloud server round-trip time using a hybrid neuro-fuzzy network | |
| CN117834455B (en) | Electric power Internet of things data transmission simulation method and system | |
| Sriramulugari et al. | Exploring mobility and scalability of cloud computing servers using logical regression framework | |
| Wang et al. | Efficient resources allocation and computation offloading model for ap-based edge cloud | |
| CN114448839B (en) | Self-adaptive distributed system pressure measurement method, device and system | |
| CN117376973B (en) | Regional 5G base station capacity information analysis processing method and system | |
| CN117424813B (en) | Node expansion method for block chain | |
| CN116466672B (en) | Data center machine room parameter regulation and control method based on artificial intelligence and related device | |
| Bhargavi et al. | Fuzzy Neutrosophic Soft Set Based Transfer-Q-Learning Scheme for Load Balancing in Uncertain Grid Computing Environments |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |