CN112511592B - Edge artificial intelligence computing method, Internet of things node and storage medium - Google Patents
Edge artificial intelligence computing method, Internet of things node and storage medium Download PDFInfo
- Publication number
- CN112511592B CN112511592B CN202011210802.7A CN202011210802A CN112511592B CN 112511592 B CN112511592 B CN 112511592B CN 202011210802 A CN202011210802 A CN 202011210802A CN 112511592 B CN112511592 B CN 112511592B
- Authority
- CN
- China
- Prior art keywords
- internet
- things
- node
- neural network
- artificial neural
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/63—Routing a service request depending on the request content or context
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/502—Proximity
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses an edge artificial intelligence computing method, an Internet of things node and a storage medium, wherein the method comprises the following steps: the method comprises the steps of obtaining input data of at least one group of artificial neural network models, creating routing tables among a plurality of internet of things nodes according to the artificial neural network models, creating correlation information of computing tasks of the internet of things nodes and the artificial neural network models according to the routing tables, sending distribution information of the computing tasks to the corresponding internet of things nodes respectively according to the correlation information of the computing tasks of the internet of things nodes and the artificial neural network models, completing the computing tasks at the internet of things nodes according to the input data, weight information and activation function information, and sending computing results to the next internet of things node according to the routing tables, so that distributed computing of the computing tasks of the artificial intelligent computing models at the edge end is achieved, computing power of the internet of things nodes is fully utilized, and various defects of the computing tasks of the artificial intelligent computing models are avoided being completed at the cloud end.
Description
Technical Field
The invention relates to the technical field of edge computing, in particular to an edge artificial intelligence computing method, an Internet of things node and a storage medium.
Background
With the development of the internet of things technology, the number of nodes of the internet of things is more and more, the nodes of the internet of things are more and more dense, and the nodes of the internet of things are usually powered by batteries, so that the computing power of the nodes of the internet of things is often limited, and due to the limitation of the service life of the batteries, the nodes of the internet of things are not suitable for independently undertaking more complex artificial intelligence computing tasks based on a machine learning model, such as computing tasks based on an artificial intelligence environment monitoring model of an artificial neural network. Therefore, in order to avoid local processing of the computing tasks at the nodes of the internet of things, the data collected by the nodes of the internet of things are often sent to the cloud for processing, so that a large amount of communication delay is caused, and a special gateway or a wireless communication module needs to be equipped for the nodes of the internet of things, so that the hardware cost is increased, and meanwhile, the computing capacity of the nodes of the internet of things is not fully utilized.
Disclosure of Invention
The invention aims to provide an edge artificial intelligence computing method, which is characterized in that a distributed edge computing network is established in a multi-hop network, the computing power of nodes of the Internet of things is fully utilized, and an artificial intelligence computing task is completed at an edge end.
In order to solve the above-mentioned problems, the present invention adopts a technical solution of: an edge artificial intelligence computing method for a multi-hop network comprising a plurality of internet of things nodes, the method comprising: acquiring input data of at least one group of artificial neural network models; establishing a routing table among a plurality of nodes of the Internet of things according to the artificial neural network model; establishing association information of the Internet of things nodes and the calculation tasks of the artificial neural network model according to the routing table; according to the correlation information of the calculation tasks of the Internet of things node and the artificial neural network model, respectively sending a plurality of calculation task allocation information to the corresponding Internet of things nodes, wherein the calculation task allocation information comprises a routing table, input data, weight information of at least one neuron of the artificial neural network model and excitation function information; and completing a calculation task at the node of the Internet of things according to the input data, the weight information and the activation function information, and sending a calculation result to the next node of the Internet of things according to the routing table.
Further, the step of creating a routing table among the plurality of nodes of the internet of things according to the artificial neural network model comprises the following steps:
broadcasting a request packet to an internet of things node of the multi-hop network according to the artificial neural network model, wherein the request packet contains calculation demand information about the artificial neural network model;
Receiving reply packets which are sent by other Internet of things nodes in the multi-hop network and respond to the request packets, wherein the reply packets comprise node information of the Internet of things nodes sending the reply packets and path information from the Internet of things nodes sending the reply packets to the Internet of things nodes sending the request packets, and the node information comprises node resource information, node identification and/or node type;
and establishing a routing table between the nodes of the Internet of things according to the reply packet.
Further, the establishing a routing table between nodes of the internet of things according to the reply packet includes:
according to the node information in the reply packet and the artificial neural network model, designating the corresponding Internet of things node as an input node corresponding to an input neuron of the artificial neural network model;
according to the path information and the artificial neural network model, the corresponding Internet of things node is designated as an intermediate node corresponding to a hidden neuron of the artificial neural network model;
according to the path information and the artificial neural network model, designating the corresponding Internet of things node as an output node corresponding to an output neuron of the artificial neural network model;
and determining connection routes among the input nodes, the output nodes and the intermediate nodes according to the path information to form a routing table.
Further, the method further comprises the step of optimizing the correlation information of the computing tasks of the Internet of things node and the artificial neural network model by utilizing an ant colony algorithm.
Further, the artificial neural network model is an environment monitoring model based on an artificial neural network.
Further, the monitoring data is one of the following data: temperature data, humidity data, oxygen concentration data, toxic gas concentration data, infrared intensity data, and illumination data.
Further, the multi-hop network is a mesh network.
The other technical scheme adopted by the invention is as follows: an internet of things node comprises a processor and a memory, wherein a computer program is stored in the memory, and the processor is used for any one of the edge artificial intelligence computing methods by calling the computer program stored in the memory.
The invention adopts another technical scheme that: a storage medium having stored therein a computer program which, when run on a computer, causes the computer to execute any one of the edge artificial intelligence calculation methods described above.
Compared with the prior art, the invention has the beneficial effects that: the invention obtains input data of at least one group of artificial neural network models, creates a routing table among a plurality of nodes of the Internet of things according to the artificial neural network models, creating the correlation information of the Internet of things nodes and the calculation tasks of the artificial neural network model according to the routing table, according to the correlation information of the calculation tasks of the Internet of things nodes and the artificial neural network model, respectively sending the distribution information of the plurality of calculation tasks to the corresponding Internet of things nodes, completing a calculation task at the node of the Internet of things according to the input data, the weight information and the activation function information, sending a calculation result to the next node of the Internet of things according to the routing table, therefore, distributed computation of the computation task of the artificial intelligence computation model at the edge end is achieved, the computing power of the nodes of the Internet of things is fully utilized, the processing speed of the artificial intelligence computation task is improved, and various defects of completing the computation task of the artificial intelligence computation model at the cloud end are avoided.
Drawings
FIG. 1 is a flowchart of a method for computing edge artificial intelligence according to an embodiment of the present invention;
fig. 2 is a flowchart of step S2 in fig. 1;
fig. 3 is a flowchart of step S23 in fig. 2;
fig. 4 is a schematic diagram of an internet of things node according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The following detailed description of the implementation of the present invention is made with reference to specific embodiments:
fig. 1 is a flowchart of an edge artificial intelligence calculation method according to an embodiment of the present invention. As shown in fig. 1, an edge artificial intelligence computing method for a multi-hop network including a plurality of internet of things nodes, the method includes:
and S1, acquiring input data of at least one group of artificial neural network models.
And S2, creating a routing table among the nodes of the Internet of things according to the artificial neural network model.
And S3, creating the associated information of the calculation tasks of the Internet of things nodes and the artificial neural network model according to the routing table.
S4, according to the correlation information of the calculation tasks of the Internet of things node and the artificial neural network model, sending a plurality of calculation task allocation information to the corresponding Internet of things nodes respectively, wherein the calculation task allocation information comprises a routing table, input data, weight information of at least one neuron of the artificial neural network model and excitation function information.
And S5, completing a calculation task at the node of the Internet of things according to the input data, the weight information and the activation function information, and sending a calculation result to the next node of the Internet of things according to the routing table.
Specifically, in this embodiment, the artificial neural network model may be an environment monitoring model based on an artificial neural network, and the environmental status, such as fire, weather, and the like, is identified through monitoring data collected by the nodes of the internet of things. Different artificial neural network models require different monitoring data. In step S1, specifically, according to the calculation requirement of the artificial neural network model, real-time monitoring data of corresponding environmental monitoring parameters may be collected, for example, input data in the fire monitoring model often includes data of temperature, combustible gas concentration, infrared ray intensity, etc., data about the temperature, combustible gas concentration, infrared ray intensity, etc. of the monitored area may be collected in real time through the internet of things node, and then these data are processed as necessary to be input data of a set of artificial neural network model, and the probability of fire occurrence, i.e., the calculation task of the artificial neural network model, may be calculated and identified according to the artificial neural network model and the input data.
In this embodiment, the node information of the internet of things node in the reply packet includes node resource information, node identification, and/or node type. The node resource information may include information such as node memory capacity, processor frequency, battery life, etc. The node identification may be a wireless network ID or a unique identification code of the node of the internet of things. The monitoring data may be one of the following: temperature data, humidity data, oxygen concentration data, toxic gas concentration data, infrared ray intensity data and illuminance data, it is corresponding, the thing networking node can be according to the difference of the monitoring data of its collection, distributes different node types, for example the type of the thing networking node of gathering temperature data is the temperature sensing node.
In this embodiment, the multi-hop network may be a Mesh network, in the Mesh network, any internet of things node may simultaneously serve as an AP and a router, each internet of things node in the network may send and receive a signal, and each node may directly or indirectly communicate with one or more internet of things nodes.
Specifically, referring to fig. 2, step S2 includes:
s21, broadcasting a request packet to Internet of things nodes of the multi-hop network according to the artificial neural network model, wherein the request packet contains calculation requirement information about the artificial neural network model;
S22, receiving reply packets which are sent by other Internet of things nodes in the multi-hop network and respond to the request packets, wherein the reply packets comprise node information of the Internet of things nodes sending the reply packets and path information from the Internet of things nodes sending the reply packets to the Internet of things nodes sending the request packets, and the node information comprises node resource information, node identification and/or node type;
and S23, establishing a routing table between the nodes of the Internet of things according to the reply packet.
Specifically, referring to fig. 3, step S23 includes:
and S231, according to the node information in the reply packet and the artificial neural network model, designating the corresponding Internet of things node as an input node corresponding to an input neuron of the artificial neural network model. For example, if the artificial neural network model is a fire monitoring model, the nodes of the internet of things such as a temperature sensor, a humidity sensor, a toxic gas sensor, and an infrared sensor can be designated as input nodes. Each input node corresponds to an input neuron of the artificial neural network model one by one. The computational tasks of the corresponding input neurons may be performed by the input nodes.
And S232, according to the path information and the artificial neural network model, designating the corresponding Internet of things node as an intermediate node corresponding to the hidden neuron of the artificial neural network model. Specifically, according to the connection route between the nodes of the internet of things in the path information, the neighbor node communicating with the input node is selected as the intermediate node, and the connection route between the intermediate node and the input node is recorded. And transmitting the calculation result to the Internet of things node executing the calculation task of the next layer of neurons according to the connection route by the Internet of things node executing the calculation task.
And S233, according to the path information and the artificial neural network model, designating the corresponding Internet of things node as an output node corresponding to an output neuron of the artificial neural network model. Specifically, other neighbor internet of things nodes communicating with the intermediate node can be selected as output nodes according to the connection route between the internet of things nodes in the path information, and the connection route between the intermediate node and the output nodes is recorded.
And S234, determining connection routes among the input nodes, the output nodes and the intermediate nodes according to the path information to form a routing table. And the intermediate node, the input node and the output node forward the calculation intermediate result to the next node for calculation according to the routing table.
In this embodiment, association information of the computing tasks of the internet of things node and the artificial neural network model is created according to the routing table, specifically, the computation of each neuron of the artificial neural network model may be used as one computing task, and the association information of the computing tasks of the internet of things node and the artificial neural network model is created according to the routing table, that is, a corresponding relationship between the computing tasks of the internet of things node and the neuron is established. Specifically, a plurality of pieces of calculation task allocation information can be respectively sent to corresponding internet of things nodes according to associated information of calculation tasks of the internet of things nodes and the artificial neural network model, wherein the calculation task allocation information includes a routing table, input data, weight information of at least one neuron of the artificial neural network model, and excitation function information. And the nodes of the Internet of things operate corresponding activation functions, weight information and input data according to the corresponding relations to complete distributed calculation tasks, and then the calculation results are sent to the next node of the Internet of things to perform corresponding calculation, so that the nodes of the Internet of things can complete the calculation of the corresponding mathematical models of the neurons, and the calculation results are sent to the next node of the Internet of things to perform the calculation of the corresponding mathematical models.
In this embodiment, the method further includes a step of optimizing association information of the internet of things node and the calculation task of the artificial neural network model by using an ant colony algorithm. Specifically, firstly, modeling is performed on the correlation information of the internet of things nodes and the calculation tasks of the artificial neural network model, the problem is converted into an optimal task allocation strategy, the artificial neural network model can be decomposed into N calculation tasks, the N calculation tasks are allocated to M internet of things nodes with different processing capacities according to a certain strategy, and the total task processing time of the N tasks is shortest. And the completion time of the calculation task is used as an index for measuring the excellence of the distribution strategy. Each task allocation strategy is a viable solution to this problem. Then the allocation strategy with the smallest completion time is the optimal solution to the problem. And the calculation of the neuron is distributed to an Internet of things node as an independent calculation task. The ant colony algorithm needs to perform multiple iterations, and in each iteration, all ants need to complete the allocation of all tasks according to a certain strategy, for example, a calculation task may be randomly allocated to a certain internet of things node, or allocated according to the pheromone concentration, that is, the task is allocated to the internet of things node with the highest pheromone concentration for processing. And after each iteration is completed, calculating and recording the task processing time of all ants, and updating the pheromone matrix. After each iteration is finished, a current optimal scheme is selected, pheromones of the scheme are promoted, and a global optimal solution can be found through multiple iterations, namely the calculation task distribution scheme with the shortest task processing time is obtained, so that the execution efficiency of the artificial intelligent calculation task is improved.
In summary, the request packet is broadcasted to other internet of things nodes of the multi-hop network according to the artificial neural network model, the reply packet which is sent by the other internet of things nodes and responds to the request packet is received, the routing table among the internet of things nodes is established according to the reply packet, the correlation information of the internet of things nodes and the calculation task of the artificial neural network model is established according to the routing table, and the calculation task distribution packet is broadcasted according to the routing table, so that the distributed calculation of the calculation task of the artificial intelligent calculation model at the edge end is realized, the calculation force of the internet of things nodes is fully utilized, the processing speed of the artificial intelligent calculation task is improved, and various defects of completing the calculation task of the artificial intelligent calculation model at the cloud end are avoided.
Referring to fig. 4, an embodiment of the present invention further provides an internet of things node. As shown, the internet of things node includes a processor, a communication module, and a memory. The processor is electrically connected with the communication module and the memory. The processor is a control center of the node of the internet of things, various interfaces and lines are used for connecting all parts of the whole terminal, and various functions of the terminal and data processing are executed by running or calling a computer program stored in the memory and calling data stored in the memory, so that the node of the internet of things is monitored integrally. Different internet of things nodes may communicate with each other via a communication module.
In this embodiment, a processor in the node of the internet of things loads instructions corresponding to processes of one or more computer programs into a memory, and the processor executes the computer programs stored in the memory, so as to implement the steps in the edge artificial intelligence computing method according to various exemplary embodiments of the present application described above in this specification, for example, the node of the internet of things may perform the steps shown in fig. 1.
Embodiments of the present application provide a storage medium, and when being executed by a processor, the computer program performs the method in any optional implementation manner of the foregoing embodiments to implement the steps in the edge artificial intelligence calculation method according to various exemplary embodiments of the present application described above in this specification, for example, an internet of things node may perform the steps shown in fig. 1. The storage medium may be implemented by any type of volatile or nonvolatile storage device or combination thereof, such as a Static Random Access Memory (SRAM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), an Erasable Programmable Read-Only Memory (EPROM), a Programmable Read-Only Memory (PROM), a Read-Only Memory (ROM), a magnetic Memory, a flash Memory, a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present 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 solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (7)
1. An edge artificial intelligence computing method is used for a multi-hop network comprising a plurality of nodes of the Internet of things, and is characterized by comprising the following steps:
acquiring input data of at least one group of artificial neural network models;
establishing a routing table among a plurality of nodes of the Internet of things according to the artificial neural network model;
establishing association information of the Internet of things nodes and the calculation tasks of the artificial neural network model according to the routing table;
according to the correlation information of the calculation tasks of the Internet of things node and the artificial neural network model, respectively sending a plurality of calculation task allocation information to the corresponding Internet of things nodes, wherein the calculation task allocation information comprises a routing table, input data, weight information of at least one neuron of the artificial neural network model and activation function information;
Completing a calculation task at the node of the Internet of things according to the input data, the weight information and the activation function information, and sending a calculation result to the next node of the Internet of things according to the routing table;
the step of creating a routing table among a plurality of nodes of the internet of things according to the artificial neural network model comprises the following steps:
broadcasting a request packet to an internet of things node of the multi-hop network according to the artificial neural network model, wherein the request packet contains calculation demand information about the artificial neural network model;
receiving reply packets which are sent by other Internet of things nodes in the multi-hop network and respond to the request packets, wherein the reply packets comprise node information of the Internet of things nodes sending the reply packets and path information from the Internet of things nodes sending the reply packets to the Internet of things nodes sending the request packets, and the node information comprises node resource information, node identifiers and/or node types; the node identification is a wireless network ID of the node of the Internet of things or a unique identification code;
establishing a routing table among the nodes of the Internet of things according to the reply packet;
and optimizing the correlation information of the calculation tasks of the Internet of things node and the artificial neural network model by using the ant colony algorithm.
2. The edge artificial intelligence computing method of claim 1, wherein the establishing a routing table between nodes of the internet of things according to the reply packet comprises:
According to the node information in the reply packet and the artificial neural network model, designating the corresponding Internet of things node as an input node corresponding to an input neuron of the artificial neural network model;
according to the path information and the artificial neural network model, the corresponding Internet of things node is designated as an intermediate node corresponding to a hidden neuron of the artificial neural network model;
according to the path information and the artificial neural network model, designating the corresponding Internet of things node as an output node corresponding to an output neuron of the artificial neural network model;
and determining connection routes among the input nodes, the output nodes and the intermediate nodes according to the path information to form a routing table.
3. The edge artificial intelligence calculation method of claim 1, wherein the artificial neural network model is an artificial neural network-based environment monitoring model.
4. The edge artificial intelligence calculation method of claim 3, wherein the monitoring data of the artificial neural network model is one of the following data: temperature data, humidity data, oxygen concentration data, toxic gas concentration data, infrared intensity data, and illumination data.
5. The edge artificial intelligence calculation method of any one of claims 1-4, wherein the multi-hop network is a mesh network.
6. An internet of things node comprising a processor and a memory, the memory having stored therein a computer program, the processor being configured to perform the method of any of claims 1 to 5 by invoking the computer program stored in the memory.
7. A storage medium having stored thereon a computer program which, when run on a computer, causes the computer to perform the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011210802.7A CN112511592B (en) | 2020-11-03 | 2020-11-03 | Edge artificial intelligence computing method, Internet of things node and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011210802.7A CN112511592B (en) | 2020-11-03 | 2020-11-03 | Edge artificial intelligence computing method, Internet of things node and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112511592A CN112511592A (en) | 2021-03-16 |
| CN112511592B true CN112511592B (en) | 2022-07-29 |
Family
ID=74955224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011210802.7A Active CN112511592B (en) | 2020-11-03 | 2020-11-03 | Edge artificial intelligence computing method, Internet of things node and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112511592B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112486668B (en) * | 2020-11-03 | 2024-06-25 | 深圳市中博科创信息技术有限公司 | Distributed artificial intelligence computing method, internet of things node and storage medium |
| CN113222134B (en) * | 2021-07-12 | 2021-10-26 | 深圳市永达电子信息股份有限公司 | Brain-like computing system, method and computer readable storage medium |
| CN114356511B (en) * | 2021-08-16 | 2023-06-27 | 中电长城网际***应用有限公司 | Task allocation method and task allocation system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784469A (en) * | 2019-01-25 | 2019-05-21 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of smart city safety monitoring system and its method based on mist calculating |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170091615A1 (en) * | 2015-09-28 | 2017-03-30 | Siemens Aktiengesellschaft | System and method for predicting power plant operational parameters utilizing artificial neural network deep learning methodologies |
| CN110365753B (en) * | 2019-06-27 | 2020-06-23 | 北京邮电大学 | Low-delay load distribution method and device for Internet of things service based on edge calculation |
-
2020
- 2020-11-03 CN CN202011210802.7A patent/CN112511592B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784469A (en) * | 2019-01-25 | 2019-05-21 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of smart city safety monitoring system and its method based on mist calculating |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112511592A (en) | 2021-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112511592B (en) | Edge artificial intelligence computing method, Internet of things node and storage medium | |
| CN112486665B (en) | Edge artificial intelligence computing task scheduling method based on peer-to-peer network | |
| Karagiannis et al. | Comparison of alternative architectures in fog computing | |
| CN113316118A (en) | Unmanned aerial vehicle cluster network self-organizing system and method based on task cognition | |
| Sangaiah et al. | SALA-IoT: Self-reduced internet of things with learning automaton sleep scheduling algorithm | |
| Venkataramanan et al. | LWBA: Lévy-walk bat algorithm based data prediction for precision agriculture in wireless sensor networks | |
| Mardini et al. | Mining Internet of Things for intelligent objects using genetic algorithm | |
| Cuka et al. | An integrated intelligent system for IoT device selection and placement in opportunistic networks using fuzzy logic and genetic algorithm | |
| Yu et al. | A multi-objective metaheuristics study on solving constrained relay node deployment problem in WSNS | |
| Suresh et al. | F2SO: an energy efficient cluster based routing protocol using fuzzy firebug swarm optimization algorithm in WSN | |
| Hans et al. | Controller placement in software defined internet of things using optimization algorithm | |
| CN112486668B (en) | Distributed artificial intelligence computing method, internet of things node and storage medium | |
| Kasabova et al. | On modeling the psychology of wireless node interactions in the context of internet of things | |
| CN109120523A (en) | Multi-node path selection method, device, cloud platform resource regulating method and device | |
| CN112486669B (en) | Self-organizing mobile edge computing platform and method | |
| Eliiyi et al. | Parallel identification of central nodes in wireless multi-hop networks | |
| Zaza et al. | Modern QoS solutions in WSAN: an overview of energy aware routing protocols and applications | |
| Hu et al. | Minimum cost multicast routing using ant colony optimization algorithm | |
| Nazi et al. | Exploiting gene regulatory networks for robust wireless sensor networking | |
| Moorthy et al. | A Hybrid Data Acquisition Model for Precision Agriculture using IoT, Engineering Nanomaterials and Artificial Intelligence | |
| Geetha et al. | Cronbach alpha reliability factor based reputation mechanism for mitigating byzantine attack in manets | |
| Kim et al. | Generative service provisioning for IoT devices using line graph structure | |
| Sobral et al. | Automated design of fuzzy rule base using ant colony optimization for improving the performance in Wireless Sensor Networks | |
| Landa-Torres et al. | A preliminary approach to near-optimal multi-hop capacitated network design using grouping-dandelion encoded heuristics | |
| Rajpoot et al. | An enhanced approach for energy optimization using protocol based on multi factors |
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 |