KR102506644B1 - INTELLIGENT IoE EDGE COMPUTION SYSTEM FOR HIGH RELIABLE IoT SERVICE - Google Patents

Abstract

The present invention relates to an intelligent IoE edge computing system for highly reliable IoT services.
The intelligent IoE edge computing system for high-reliability IoT service according to the present invention configures modularized edge computing to be applied to various applications, and has technical features capable of intelligent traffic analysis and prediction.

Description

Intelligent IoE edge computing system for highly reliable IoT service

The present invention relates to an intelligent IoE edge computing system for highly reliable IoT services.

The IoT environment has a problem in that it is a limited environment by the device itself and wireless networking technology.

According to the prior art, various technologies for providing connectivity in the IoT environment have been proposed, but numerous IoT platforms developed in various IoT service fields are compatible with various Edge/Fog computing technologies, providing an integrated IoT platform. There is a problem I am not doing.

The present invention is proposed to improve the above-mentioned problems of the prior art, proposes an autonomous configurable Intelligent IoT Information framework and network control technology for IoT services, and modularization applicable to various applications The purpose of this study is to provide an intelligent IoE edge computing system capable of analyzing and predicting traffic.

The present invention is an autonomous configurable Intelligent IoT Information framework, edge node based time-series data prediction and decision technology, and services based thereon (e.g. smart IoT construction monitoring) is provided.

According to an embodiment of the present invention, unlike the prior art in which edge computing must be manually configured to meet business operator requirements, edge computing is automatically configured by receiving business operator requirements through language or pictures.

In addition, it automatically predicts at the minimum cost through rule-based, ML-based, and DL-based convergence predictions according to service requirements, and hybridizes prediction and decision to provide policy-based It has a traffic control feature.

Examples of policies include traffic minimization, cost minimization (rate-based, pay-as-you-go), QoS control according to user class, and exact alarm detection.

According to an embodiment of the present invention, there is a feature of automatically selecting prediction and decision algorithms to meet service requirements.

In addition, according to an embodiment of the present invention, it can be used for various services as well as smart construction service, and a video traffic control service for uplink traffic can be provided as a smart construction service.

The intelligent VR cache can provide a service that transmits the places frequently viewed by users in high quality and the rest in low quality through space-based video traffic control and image recognition.

VR video is highly likely to be watched by people at a specific location, and, for example, in a martial arts game, people tend to watch it.

As a smart transportation service, mobility control and QoS control can be performed by targeting self-driving cars.

With valuables transmission control service, it is possible to provide uninterrupted video service.

With the personal broadcasting uplink service, it is possible to control uplink traffic optimized for the level of multiple users.

According to the present invention, as an automatically configured intelligent information framework and a time-series-based prediction and decision technology are proposed, there is an effect that can be extended to various services based on the intelligent information framework.

According to an embodiment of the present invention, there is an effect of providing an intelligent IoT site live monitoring service that quickly synchronizes and provides on-line noise, vibration, gas levels, and on-site images at a construction site when civil complaints occur.

In addition, there is an effect of preventing overflow and efficiently storing field images in the cloud.

According to the present invention, there is an effect of switching from the past passive monitoring method to an active and immediate collaboration service, and there is an effect of using collected data as basic data of machine learning.

The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a configuration diagram of an automatically configured intelligent IoT information framework according to an embodiment of the present invention.
2 is a block diagram of an intelligent IoT edge computing system according to an embodiment of the present invention.
3 is a functional configuration diagram of an intelligent IoT edge computing system according to an embodiment of the present invention.
4 shows a reference point of an intelligent IoT edge computing system according to an embodiment of the present invention.
5 illustrates a message format of a reference point according to an embodiment of the present invention.
6 shows a message specification of a reference point according to an embodiment of the present invention.
7 shows a flow chart of an autonomous initialization process according to an embodiment of the present invention.
8 shows a flowchart of intelligent data processing according to an embodiment of the present invention.
9 is a flowchart of intelligent data processing for terminal control according to an embodiment of the present invention.
10 shows a flow chart of ML model update processing according to an embodiment of the present invention.
11 illustrates a configuration for predicting and determining edge node-based time-series data according to an embodiment of the present invention.
12 illustrates a process of predicting and determining time-series data based on an edge node according to an embodiment of the present invention.
13A and 13B show a decision algorithm according to an embodiment of the present invention.
14 illustrates configurations of training and serving for edge node-based time-series data prediction and determination according to an embodiment of the present invention.
15 shows a flowchart of training and serving for edge node-based time-series data prediction and determination according to an embodiment of the present invention.
16 and 17 show a configuration diagram of smart IoT construction monitoring based on an intelligent IoT information framework according to an embodiment of the present invention.
18 is a configuration diagram of an intelligent VR cache service based on an intelligent IoT information framework according to an embodiment of the present invention.
19 illustrates utilization of an intelligent VR cache service based on an intelligent IoT information framework according to an embodiment of the present invention.

The foregoing and other objects, advantages and characteristics of the present invention, and a method of achieving them will become clear with reference to the detailed embodiments described below in conjunction with the accompanying drawings.

However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms, and only the following embodiments provide the purpose of the invention, As only provided to easily inform the configuration and effect, the scope of the present invention is defined by the description of the claims.

Meanwhile, terms used in this specification are for describing the embodiments and are not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, “comprises” and/or “comprising” means the presence of one or more other components, steps, operations, and/or elements in which a stated component, step, operation, and/or element is present. or added.

Hereinafter, in order to help the understanding of those skilled in the art, the background in which the present invention is proposed will be described first, and then the embodiments of the present invention will be described.

According to the prior art, IoT has a limited environment by the environment of the device itself and the network.

The limited environment of the device (things) itself means a limited environment of CPU performance and memory capacity.

In the case of a network, it includes a limited environment of wireless networking technologies such as a low power wide area network (LPWA) and a low power lossy network (LLN).

According to the prior art, in order to provide connectivity in such an IoT environment, a TCP/IP or UDP/IP stack is mounted to provide networking and data transmission services.

In addition, to allocate IP addresses to numerous IoT devices, IPv6, not the existing Internet protocol IPv4, is used.

In addition, a convergence layer between the IPv6 layer and the MAC layer is newly developed and standardized to mount a new wireless technology such as LPWA.

In addition, for the application layer, technologies such as CoAP, which makes HTTP lightweight, are provided.

In the future, various IoT devices will increase, and a lot of data will be generated through these terminals.

In order to handle this amount of data, scalable and effective networking and computing platform technologies are needed.

In accordance with these needs, edge/fog computing technology for processing data near users and IoT devices is becoming popular.

In the case of edge computing, Mobile Edge computing (MEC) technology for mobile communication corresponds to this.

This is to directly perform functions required for a service in a device, an access gateway, and a base station.

Fog computing is a distributed computing platform located between IoT devices and a central cloud computing structure provided over the Internet.

Edge computing and fog computing are often used in parallel, and edge computing and fog computing technologies are also described together below.

In a situation where numerous IoT platforms in various existing IoT service fields are compatible with these various edge/fog computing technologies, development to continuously integrate them and support inter-working is in progress.

As a specific example, numerous IoT services such as smart city, smart factory, and smart healthcare are being developed centering on separate IoT platforms.

As a result, numerous IoT platforms have been scattered, and as they do not share a common technology, development and maintenance costs are expected to continuously increase.

In particular, IoT devices are developed to operate together with gateways or actuators, and have a disadvantage in that they are fixed like a dedicated service along with a specific company's product.

There are activities to support the integration of IoT platforms through international standardization, and platforms such as oneM2M and OCF's IoTivity are also being developed, but it is still not an integrated IoT platform.

In conclusion, there is a limitation that cannot handle numerous IoT terminals and data and cannot support scalable connectivity only with IPv6, CoAP, and central cloud server technology, which are IP technologies such as the Internet.

In addition, the existing IoT platforms are also developed specifically for different technologies and service wholesalers, and it is difficult to develop solutions to integrate them.

Therefore, there is a need for a technology that supports effective connectivity and mobility in a resource-constrained and networking-constrained environment of numerous IoT devices, and collects and processes numerous data generated from these devices through a distributed structure.

In addition, for compatibility with technologies such as existing IoT platforms or cloud servers, it provides functions such as networking and security through simple message techniques such as RESTful used in application services such as web, and can be applied to various service domains. An integrated framework is needed.

In particular, in the field of smart construction, several construction companies are forming an alliance to jointly develop IoT and smart home technologies under the leadership of the government.

Samsung Electronics, LG Electronics, Coway, Cuchen, and other home appliance companies, as well as telecommunications companies SKT and KT, MDS Technology, Samyoung S&C, Wise Nut, Korea Land and Housing Corporation (LH), and Seoul National Housing Corporation (SH) Smart home related companies are participating.

They are collaborating for interoperability and linkage between smart home platforms in the future, and are participating in the development of public information utilization and smart home business models.

On this basis, technologies for smart construction are continuously being developed.

It will be expanded to a system that manages the overall process in real time by introducing IoT to various construction sites such as housing, architecture, civil engineering, and plants, and utilizing mobile and wearable devices and drones (unmanned aerial vehicles).

It provides smart construction services by converging mutual technologies between internet operators and construction companies, and provides technologies and services that provide real-time air quality information at construction sites.

This shows the neighboring residents the technology to prevent various civil complaints at the construction site.

Existing edge computing has the characteristics of reducing delay by lowering cloud computing to the edge, reducing unnecessary traffic sent to the cloud, and strengthening security.

However, in order to satisfy various service requirements for each service provider, there was a difficulty in receiving and configuring technology consulting separately, and there is a problem in that machine learning techniques are also sporadically applied to each service.

The present invention has been proposed to solve the above problems, and proposes an autonomous configured IoT information framework and an information intelligence network control system for IoT services.

In addition, it has technical features of providing a modular intelligent IoT information framework for application to various applications and performing intelligent traffic analysis and prediction.

According to an embodiment of the present invention, 1) intelligent IoT information framework, 2) edge node-based time-series data prediction and determination, 3) various services based on these technologies (e.g., smart construction monitoring considering the reusability of edge technology) system) is available.

An intelligent IoT information framework according to an embodiment of the present invention includes a gateway that transmits IoT device data and information processed as a result of data analysis to a cloud server.

According to an embodiment of the present invention, the structure, procedure, composition and operation of intelligent IoE edge computing are proposed.

According to an embodiment of the present invention, after collecting information from various sensors through an intelligent IoT information framework device, analyzing the situation in the field through statistical analysis and machine learning, and then transmitting the image quality of the network camera illuminating the field It is possible to save network usage by selecting

As an example, it can be applied to a construction site. Observe noise, vibration, and gas information and provide a service that transmits high-definition video when the standard value is reached, and transmits high-definition video after detecting an intruder through a motion sensor and human body sensor as a security system.

According to an embodiment of the present invention, operation is possible only by installing an IoT gateway without installing an additional protocol stack or application program in a sensor.

In addition, compared to the cloud-based IoT service according to the prior art, security is improved, server maintenance costs can be reduced, and there are effects that can be linked with various cloud services.

¹⁰ Based on the information-centric networking-based Edge/Fog intelligent networking platform that provides scalability, mobility, and real-time (low latency) connectivity to more than 10 devices (Things), it manages and manages the distributed Edge/Fog intelligent networking platform. We propose an intelligent IoE information framework including control functions.

Based on the Edge/Fog intelligent networking platform, it is possible to collect, store, and process information generated from devices (things), control devices, or transmit analysis results to a cloud server.

According to the present invention, connectivity with a device is directly supported through a device networking (thing networking) section.

To support the connectivity of devices with various types and environments, we propose a networking structure in the form of edge/fog computing to support scalability, real-time (low latency), and mobility.

It has the effect of supporting low-latency and time-critical IoE services by loading components for machine learning and reinforcement learning for intelligent processing of collected data.

1 is a configuration diagram of an automatically configured intelligent IoT information framework according to an embodiment of the present invention.

An intelligent IoT information framework according to an embodiment of the present invention is an intelligent data processing device that provides artificial intelligence (AI) services by itself and performs edge analysis through big data analysis.

To support edge analytics, through intelligent data processing including data collection, dynamic storage and real-time data processing. The utilization rate of data should be increased, and in particular, the analysis model should be updated periodically.

Technical features of the self-organizing intelligent IoT information framework according to an embodiment of the present invention are microservice-based reconfiguration, QnA / Object interface, voice and video recognition-based edge computing configuration, and core intelligent IoE information framework.

According to an embodiment of the present invention, when there is a specific requirement of a domain service provider, an intelligent information framework suitable for a domain service is automatically requested through voice and image recognition.

Referring to FIG. 1, the automatically configured intelligent IoT information framework according to an embodiment of the present invention includes a voice/video recognition and analysis module 20, an autonomous domain configuration analyzer module 30, and a core intelligent information frame. It consists of work (40, Core Intelligent Information Framework).

The voice recognition and analysis module 20 receives a request of a domain operator from the service provider 10 in voice form.

For example, service requests are received by voice, such as “I want to recognize an alarm” or “I want to reduce costs by reducing traffic because video traffic is high.”

The voice received through the voice recognition unit 21 is transferred to the context analysis module 23 through the QnA I/F, and the context analysis module 23 analyzes the domain service requirements through morphological analysis. Analyze

The analyzed service requirements are delivered to the automatic domain configuration analysis module 30 .

Also, the image recognition and analysis module 20 recognizes the current equipment and service conditions of the service provider 10 through images.

For example, when an image including “sensors”, “cloud equipment”, “management screen”, “access equipment”, etc. is sent, the image recognition unit 22 (image recognition) performs an object for components such as the corresponding equipment ( object) is automatically recognized.

Recognized objects are provided to the object analysis module 24 (object analysis) through the object I/F.

The object analysis module 24 analyzes device/cloud requirements such as the type and specifications of the corresponding object.

The analyzed device/cloud requirements are delivered to the automatic domain configuration analysis module 30 .

The automatic domain configuration analysis module 30 refers to the collected service, device, and cloud requirements, and requests “configuration of appropriate Core Intelligent Information Framework equipment” from domain service providers.

The Core Intelligent Information Framework 40 is configured in the form of various microservices (MS, Micro Service) and can be reconstructed.

The automatic domain configuration analysis module 30 invokes appropriate microservices according to requests and operates as an automatically configured intelligent IoT information framework.

Hereinafter, with reference to FIG. 2, the configuration of the Core intelligent information framework 40 will be described.

2 is a block diagram of an intelligent IoT edge computing system according to an embodiment of the present invention.

According to an embodiment of the present invention, edge networking entity (210, ENE), intelligent computing entity (220, intelligent computing entity, ICE), edge gateway entity (230, edge gateway entity, EGE) and edge identifier management It includes the entity 240 (Edge Identify Entity, EME).

Basically, the intelligent edge computing system 200 is disposed between the terminal entity 100 (Terminal Entity, TE) and the big data analysis server 300 that analyzes big data in the Internet and cloud computing.

Edge networking entity 210 provides connectivity to terminal entity 100 that must take into account heterogeneous radio technology and resource constrained environments.

Accordingly, implementations are implemented for various wireless technologies and protocols between the terminal entity 100 and the intelligent edge computing system 200.

The intelligent computing entity 220 itself provides an edge analysis function provided through an AI service or provides other analysis functions such as cloud computing big data analysis.

The intelligent computing entity 220 performs a data analysis function through information collection, and controls the terminal entity 100 through analysis results in addition to edge analysis.

When an abnormal situation or some event is predicted according to edge analysis of data collection, the intelligent computing entity 220 transmits a request message for an action type predefined in a service profile.

The edge gateway entity 230 provides an interworking function for external organizations including other IECs, and provides a big data analysis function using cloud computing.

The edge identifier management entity 240 stores/manages ID types of the terminal entity 100, the edge networking entity 210, the intelligent computing entity 220, and the edge gateway entity 230 by including data names as IDs.

Edge identifier management entity 240 maps these identifiers to metadata corresponding to the location of intelligent edge computing system 200 and edge gateway entity 230 .

Therefore, mobility management such as mobility of the terminal entity 100 is performed.

According to an embodiment of the present invention, an intelligent information processing manager (orchestrator), a data storage unit (DB), and a reward and action unit are included.

3 is a functional configuration diagram of an intelligent IoT edge computing system according to an embodiment of the present invention.

Referring to FIG. 3 , an edge networking entity 210a, an intelligent computing entity 220a, and an edge gateway entity 230a include various functional blocks.

Terminal entity control and management function of edge networking entity 210a, data collection function, data analysis function of intelligent computing entity 220a, edge analysis model function, storage management function, data aggregation function, forwarding of edge gateway entity 230a The management function is a function related to data processing.

The terminal entity identifier management function of the edge networking entity 210a, the edge networking entity identifier management function of the intelligent computing entity 220a, and the intelligent edge computing identifier management function of the edge gateway entity 230a are functions related to identifier management.

The terminal entity link management function of the edge networking entity 210a, the PULL message management function and the PUSH message management function of the intelligent computing entity 220a, and the Internet walking management function of the edge gateway entity 230a are functions related to edge networking.

4 shows a reference point of an intelligent IoT edge computing system according to an embodiment of the present invention.

There are three main types of reference points: Dx, Cx, and Ux.

Dx is a reference point that governs data flow and includes Da, Db, Dc, Dd, De, Df, and Dg.

Da is the interface between the terminal entity 100 and the data collection function of the edge networking entity 210a for collecting raw data.

Db is the interface between the data collection function of edge networking entity 210a and the data aggregation function of intelligent computing entity 220a.

Dc is an interface between the data aggregation function of the intelligent computing entity 220a and the forwarding management function of the edge gateway entity 230a.

Dd is an interface between the data aggregation function of the intelligent computing entity 220a and the storage management function of the intelligent computing entity 220a.

De is an interface between the data aggregation function and the intelligent data analysis function of the intelligent computing entity 220a.

Df is an interface between the data analysis function and the storage management function of the intelligent computing entity 220a.

Dg is an interface between the data analysis function of the intelligent computing entity 220a and the forwarding management function of the edge gateway entity 230a.

Dh is an interface between the forwarding management function of the edge gateway entity 230a and the big data analysis server 300 located in the cloud, and Di is an interface between the forwarding management function of the edge gateway entity 230a and another IEC 200b. .

Cx is a reference point that manages the control flow, and includes Ca and Cb.

Ca is the interface between the terminal entity control and management function of edge networking entity 210a and the data analysis function of intelligent computing entity 220a.

Cb is the interface between the terminal entity 100 and the terminal entity control and management function of the edge networking entity 210a.

Ux is a reference point that manages model update, and includes Ua and Ub.

Ua is an interface between the edge analysis model function of the intelligent computing entity 220a and the forwarding management function of the edge gateway entity 230a.

Ub is an interface between the data analysis function and the edge analysis model function of the intelligent computing entity 220a.

5 illustrates a message format of a reference point according to an embodiment of the present invention, and FIG. 6 illustrates a message specification of a reference point according to an embodiment of the present invention.

The message uses the Type-Length-Value (TLV) encoding format, and the type and length fields are encoded in 2 bytes.

7 shows a flow chart of an autonomous initialization process according to an embodiment of the present invention.

The edge networking entity 210, the intelligent computing entity 220, and the edge gateway entity 230, which are components of intelligent edge computing, are connected to the edge identifier management entity 240 through a control channel (S705).

The terminal entity 100 generates an identifier using a hierarchical name such as a URI type (S710).

The terminal entity 100 transmits a request for connectivity to the edge networking entity 210 (S715).

The edge networking entity 210 stores the identifier of the terminal entity 100 in the table (S720).

The edge networking entity 210 transmits a registration message for the identifier of the terminal entity 100 to the intelligent computing entity 220 and transmits the identifier of the edge networking entity 210 (S725).

The intelligent computing entity 220 stores identifiers of the terminal entity 100 and the edge networking entity 210 (S730).

The intelligent computing entity 220 transmits a registration request for identifiers of the terminal entity 100, the edge networking entity 210, and the intelligent computing entity 220 (S735).

The edge identifier management entity 240 maps and stores the identifier of the terminal entity 100, the identifier of the edge networking entity 210, and the identifier of the intelligent computing entity 220 (S740), and returns a response to the registration request to the terminal entity 100. ) (S745).

Through this, connectivity between the terminal entity 100 and the edge networking entity 210 is established (S750).

8 shows a flowchart of intelligent data processing according to an embodiment of the present invention.

The terminal entity 100 generates raw data (or single unit data) through some trigger events (S805).

The terminal entity 100 transfers the raw data to the edge networking entity 210 (S810).

At this time, the divided raw data is collected by the edge networking entity 210 through a connection between the terminal entity 100 and the edge networking entity 210 (S815).

Edge networking entity 210 collects the segmented data.

The edge networking entity 210 delivers the collected data to the intelligent computing entity 220 (S820).

The intelligent computing entity 220 analyzes the aggregated data (S825) and delivers the analysis result to the edge gateway entity 230 (S830).

Aggregated data can be stored in storage or analyzed directly through stream data processing.

Aggregate data is first processed with data quality and pre-processing steps such as extraction, transformation and loading.

In addition, the normalized data is processed using an AI model.

For example, ML predictive models can be applied to edge analytics to predict future events.

As a result of the edge analysis, the intelligent computing entity 220 forwards the analyzed data to the big data analysis server 300 .

At this time, the traffic load between the intelligent computing entity 220 and the big data analysis server 300 is reduced using a video quality adaptation function such as a video transcoding function by controlling transmission data according to the result of ML prediction.

The analyzed edge data is stored through the storage function of the intelligent computing entity 220 (S835).

The big data analysis results can be confirmed with new functions such as AI model update (S840).

9 is a flowchart of intelligent data processing for terminal control according to an embodiment of the present invention.

According to the edge analysis of data collection, an abnormal situation or some event is predicted (S905).

The intelligent computing entity 220 performs a task by transmitting a request message (S910).

At this time, there are job types that can be defined as service profiles.

For example, in the case of a video security surveillance system, the intelligent computing entity 220 may directly control the security surveillance camera.

The terminal entity 100 takes an immediate action (S915), for example, the camera can directly encode high-quality video according to the prediction time.

The terminal entity 100 transmits a response to the request to the intelligent computing entity 220 (S920).

10 shows a flow diagram of a machine learning (ML) model update process according to an embodiment of the present invention.

Before achieving edge analysis, the intelligent computing entity (220) requests an AI model through big data analysis on a cloud server or model storage (S1005).

The intelligent computing entity 220 sends a request message including a service profile to the AI model (S1010).

As the service profile is confirmed, an appropriate AI model is built in the big data analysis server 300 or model storage (S1015).

The big data analysis server 300 transmits a response to the request (S1020), which is a response to the request to attach the AI model and parameters.

The intelligent computing entity 220 performs edge analysis by applying the model (S1025).

After an appropriate period, the model update is promoted in the big data analysis server 300 (S1030).

Intelligent computing entity 220 may explicitly request a new AI model.

The intelligent computing entity 220 applies the model (S1035).

11 illustrates a configuration for edge node-based time-series data prediction and determination according to an embodiment of the present invention.

Edge node-based time series data prediction and decision configurations according to an embodiment of the present invention are: 1) rule-based, ML based, DL-based convergence prediction, 2) hybrid prediction and decision algorithm, 3) policy-based traffic control, traffic It has the characteristics of minimization, cost minimization (quantity system, volume system), and service quality satisfaction.

Referring to FIG. 11, a configuration for predicting and determining edge node-based time-series data according to an embodiment of the present invention includes a sensing box 110, a camera 120, an edge computing system 200, and a cloud server 400 It is composed by

The sensing box 100 is a set of a plurality of sensors such as a vibration sensor, a noise sensor, and a gas sensor.

The sensing box 100 provides information of various sensors such as noise, vibration, and gas to the edge computing system 200 .

The camera 120 captures images of the construction site in real time at FHD level and provides them to the edge computing system 200 .

The edge computing system 200 provides connectivity for receiving data from a device network (Things network) as well as an IoE information processing function.

Also, it acts as a networking platform between constituent nodes and components of each framework.

In addition, it operates as a platform that provides networking with cloud servers existing on the Internet.

The edge computing system 200 includes a sensing data collection unit 250, a prediction unit 260 (static prediction, ML-based prediction), a decision unit 270, and a video quality application unit 280. adaptation).

The cloud server 400 receives sensor information through AWS IoT or video information through RTMP.

12 illustrates a process of predicting and determining time-series data based on an edge node according to an embodiment of the present invention.

According to an embodiment of the present invention, data (raw data or single unit data) generated from the sensor 110 is processed through the procedure shown in FIG. 12 .

Data received through the sensor 110 is stored in the DB 291 via the sensing data collector 250 (S1201 and S1202).

In addition, data is transmitted from the sensing data collection unit 250 to the prediction unit 260 (S1203).

The prediction unit 260 predicts data of the next period based on the collected data, and transfers the predicted data to the determination unit 270 (S1204).

The decision unit 270 determines whether to send high quality video data or low quality video data according to the algorithm of FIG. 13 to be described later, and transmits the determined result to the video quality application unit 280 (S1205).

The video quality application unit 280 applies the video quality according to the result received from the determination unit 270 (S1206) and transmits the video data to the cloud server.

The prediction algorithm for the decision is as follows, and according to an embodiment of the present invention, an optimal algorithm is selected from among a plurality of algorithms.

Rule-based algorithms include Last Value (LV) and Moving Average (MA).

Multi Variable Regression Prediction (MV_RP) is included in the machine learning based algorithm.

Deep Learning based algorithms include Multi Variable Regression Prediction (MV_RP), Long Short Term Memory (LSTM), and General Recurrent Unit (GRU).

13A and 13B show a decision algorithm according to an embodiment of the present invention, and the parameters of each algorithm are automatically selected.

FIG. 13A is based on SA-DCS (Static Alarm based Data transmission Control Scheme), and FIG. 13B is based on DA-DCS (Dynamic Alarm based Data transmission Control Scheme).

As the parameters of FIGS. 13A and 13B, S is the threshold noise (dB), C is the quality change sensitivity (0< C <1), Ns is the sampling number per second, Tw is the noise prediction window size (sec), and Td is Reference time for deterioration of image quality (sec), Uth is the network usage rate limit The reference value (Kbps), FNth is the reference value (number of times) to limit the number of false negatives.

Referring to FIG. 13A , sampling data is received (S1301), and noise levels ( s ₁ , s _{2, ...,} s _{Tw * Ns} ) for Tw seconds in the future are calculated (S1302).

The noise level calculation result is greater than the calculation result of threshold noise and picture quality change sensitivity, and the network utilization rate so far is the limit of the network utilization rate. It is checked whether it is smaller than the reference value (S1303).

If yes in step S1303, t' (the last point in time when Max( s _i ) > S*C occurred) is updated to the current time ( t ) (S1304), and it is checked whether video is currently being transmitted at low quality. (S1305).

If yes in step S1305, the image quality is raised to high quality (S1306), and if no in step S1305, the process returns to step S1301.

If it is no in step S1303, it is checked whether the result of calculating the difference between t' (the last point in time when Max( s _i ) > S*C occurred) and the current time ( t ) is equal to or greater than the standard time for deteriorating image quality (S1307 ).

In case of no in step S1307, the process returns to step S1301, and in case of yes in step S1307, it is checked whether a video is currently being transmitted in high quality (S1308).

If no in step S1308, it returns to step S1301, and if yes in step S1308, the image quality is reduced to a lower quality (S1309).

Referring to FIG. 13B , sampling data is received (S1311), and noise levels ( s ₁ , s _{2, ...,} s _{Tw * Ns} ) for the next Tw seconds are predicted (S1312).

Next, the sensitivity to change the picture quality is adjusted (S1313).

Then, the predicted noise level is greater than the calculation result of the threshold noise and picture quality change sensitivity, and the network usage rate up to now is the limiting network usage rate. It is checked whether it is smaller than the reference value (S1314).

If yes in step S1314, t' (the last point in time when Max ( s _i ) > S * C occurred) is updated to the current time ( t ) (S1315), and it is checked whether video is currently being transmitted at low quality. (S1316).

If yes in step S1316, the image quality is raised to high quality (S1317), and if no in step S1306, the process returns to step S1311.

If it is no in step S1314, it is checked whether the difference operation result between t' (the last point in time when Max( s _i ) > S*C occurred) and the current time ( t ) is equal to or greater than the standard time for deteriorating image quality (S1318 ).

In case of no in step S1318, the process returns to step S1311, and in case of yes in step S1318, it is checked whether a video is currently being transmitted in high quality (S1319).

In case of no in step S1319, the process returns to step S1311, and in case of yes in step S1319, the image quality is reduced to a low quality (S1320).

According to the above-described algorithm, for example, when S = 60dB , C = 0.8, Tw = 30sec, Td = 10sec, if a point exceeding 48dB is expected for the next 30 seconds, high-definition video transmission is guaranteed for 10 seconds.

14 illustrates configurations of training and serving for edge node-based time-series data prediction and determination according to an embodiment of the present invention.

Referring to FIG. 14 , looking at the training process, information from several sensors in the sensing box 110 is transferred to the intelligent edge computing system 200 .

The training processing method of the sensing data collection unit 250 is divided into a streaming processing method and a batch processing method.

The streaming processing method transfers the collected data to the machine learning training processing module 285 on-line to perform learning, and stores the learned result in the machine learning model DB 292.

The batch processing method stores the sensing data in the DB 291 in the sensing data collection unit 250, processes the entire machine learning training processing module 285 after the data is regularly accumulated, and transfers the learning results to the machine learning model DB ( 292) to save.

Looking at the serving process with reference to FIG. 14 , information from several sensors in the sensing box 110 is transmitted to the intelligent edge computing system 200 .

The sensing data collection unit 250 sends sensing data to the prediction unit 260 .

The prediction unit 260 brings the latest learning result from the machine learning model DB 292, predicts a future value, and delivers the predicted result to the decision unit 270.

15 shows a flowchart of training and serving for edge node-based time-series data prediction and determination according to an embodiment of the present invention.

During the training process, the sensor 110 transmits a PUT message to the sensing data collection unit 250 in a REST manner (S1501).

The sensing data collection unit 250 stores the corresponding data in the DB 291 (S1502), and at the same time transmits a PUT message to the machine learning training processing module 285 in a REST manner (S1503).

Examples of message formats to be transmitted in each PUT message include sensor_id, timestamp, noise, and gas.

The machine learning training processing module 285 performs learning based on the corresponding data and then stores the data in the machine learning model DB 292 (S1504).

The prediction unit 260 loads the latest stored machine learning model for serving (S1505).

During the serving process, the sensor 110 transfers the sensing data to the sensing data collection unit 250 (S1511).

The sensing data collection unit 250 transmits the REST method PUT message to the prediction unit 260 (S1512).

The prediction unit 260 predicts the result of the next step and transmits the corresponding data to the determination unit 270 (S1513).

Hereinafter, a domain service based on an intelligent IoE information framework according to an embodiment of the present invention will be described.

According to an embodiment of the present invention, it is possible to provide various services based on the above-described automatic configuration intelligent IoT information framework and edge node-based time-series data prediction and determination technology.

16 and 17 show a configuration diagram of smart IoT construction monitoring based on an intelligent IoT information framework according to an embodiment of the present invention.

Referring to FIG. 16 , smart IoT construction monitoring based on an intelligent IoT information framework is illustrated.

In a common structure, there is an intelligent edge computing system 200 and a machine learning framework system 600, a sensing box 110 in the west, and a cloud server 400 in the east.

Devices 500 of civil petitioners, site supervisors, and system managers use services through the cloud.

Referring to FIG. 17, the intelligent edge computing system 200 includes an input/output interface processing module (HTTP, AWS IoT, etc.), a data collection and storage processor of a sensor 110 or camera 120, a time series data analysis and predictor (TS sensor) Alarm prediction of data), video data transformer controller (Rest API for FHD, HD, SD transformer), sensor data transmission module (sensor data transmission and Rest API suitable for AWS IoT transmission method), scalable video data transmission module (alarm interval and Scalable data transmission and Rest API) for non-intervals are included.

According to an embodiment of the present invention, in order to increase reusability, it is implemented using open source-based edge computing (eg, EdgeX).

According to an embodiment of the present invention, in terms of data flow, it is possible to efficiently transmit and store construction site data (noise, vibration, gas, video), thereby reducing traffic in a wireless communication section.

From the user's point of view, it is possible to check information (noise, vibration, gas, video) in real time through search by location and time upon request from civil petitioners, field supervisors, and local government managers.

18 is a block diagram of an intelligent VR cache service based on an intelligent IoT information framework according to an embodiment of the present invention, and FIG. 19 is an intelligent VR cache based on an intelligent IoT information framework according to an embodiment of the present invention. Shows the use of services.

Viewpoint information can be collected on a statistical basis, and viewpoint information is analyzed based on machine learning.

Finally, the user has to set a spatial viewpoint.

Differential encoding performs encoding differentially at three levels: high, middle, and low.

Users can receive low-latency VR streaming in the edge computing server, and it is possible to receive data at a faster time compared to the prior art.

According to an embodiment of the present invention, a video traffic control policy for cost reduction and traffic shaping control for high reliability are possible based on an intelligent IoT information framework.

In addition, smart car self-driving service including mobility control and QoS control, valuables transmission control service to provide uninterrupted video service, uplink traffic control optimized for multi-user class, personal broadcasting uplink service can be provided. do.

Meanwhile, the intelligent IoE edge computing method according to an embodiment of the present invention may be implemented in a computer system or recorded in a recording medium. A computer system may include at least one processor, a memory, a user input device, a data communication bus, a user output device, and a storage. Each of the aforementioned components communicates data through a data communication bus.

The computer system may further include a network interface coupled to the network. The processor may be a central processing unit (CPU) or a semiconductor device that processes instructions stored in memory and/or storage.

The memory and storage may include various types of volatile or non-volatile storage media. For example, memory may include ROM and RAM.

Therefore, the intelligent IoE edge computing method according to an embodiment of the present invention can be implemented in a computer executable method. When the intelligent IoE edge computing method according to an embodiment of the present invention is executed in a computer device, computer readable instructions may execute the intelligent IoE edge computing method according to the present invention.

Meanwhile, the above-described intelligent IoE edge computing method according to the present invention can be implemented as computer readable codes on a computer readable recording medium. Computer-readable recording media includes all types of recording media in which data that can be decoded by a computer system is stored. For example, there may be read only memory (ROM), random access memory (RAM), a magnetic tape, a magnetic disk, a flash memory, an optical data storage device, and the like. In addition, the computer-readable recording medium may be distributed in computer systems connected through a computer communication network, and stored and executed as readable codes in a distributed manner.

So far, we have looked mainly at the embodiments of the present invention. Those skilled in the art to which the present invention pertains will be able to understand that the present invention can be implemented in a modified form without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments should be considered from an illustrative rather than a limiting point of view. The scope of the present invention is shown in the claims rather than the foregoing description, and all differences within the equivalent scope will be construed as being included in the present invention.

Claims (15)

An edge networking entity that provides a connection to a terminal entity, receives an identifier of the terminal entity generated using the layer name and raw data divided from the terminal entity, and delivers data collected from the terminal entity;
an intelligent computing entity receiving the data collected from the terminal entity from the edge networking entity and providing an edge analysis function;
An edge gateway entity that performs interworking with an external organization; and
An edge identifier management entity that stores and manages identifiers;
the edge networking entity sends a registration message for the identifier of the terminal entity and the identifier of the edge networking entity to the intelligent computing entity;
the intelligent computing entity stores the identifiers of the terminal entity and the edge networking entity, and transmits a registration request for the identifiers of the terminal entity, the edge networking entity and the intelligent computing entity;
The edge identifier management entity maps and stores identifiers of the terminal entity, the edge networking entity, and the intelligent computing entity.
is an intelligent IoE edge computing system.
According to claim 1,
the edge networking entity providing connectivity to the terminal entity taking heterogeneous radio technologies into account;
is an intelligent IoE edge computing system.
According to claim 1,
The intelligent computing entity provides an edge analysis function and a big data analysis function provided through an AI service.
is an intelligent IoE edge computing system.
According to claim 1,
The edge gateway entity provides an interworking function for external organizations including other IECs and a big data analysis function using cloud computing.
is an intelligent IoE edge computing system.
According to claim 1,
The edge identifier management entity maps and manages identifiers to meta data.
is an intelligent IoE edge computing system.
According to claim 1,
The intelligent computing entity analyzes aggregate data and transmits the analyzed data to a big data analysis server.
is an intelligent IoE edge computing system.
According to claim 1,
The intelligent computing entity transmits a request message for an action type predefined in a service profile when an abnormal situation or some event is predicted according to edge analysis of data collection.
is an intelligent IoE edge computing system.
According to claim 1,
The intelligent computing entity transmits a request message including a service profile, applies the AI model built according to the service profile confirmation, performs edge analysis, and after a certain period, according to the model update promoted by the big data analysis server, the model to apply
is an intelligent IoE edge computing system.
delete delete delete delete delete delete delete

Images