Edge computing refers to the use of an open platform integrating network, computing, storage and application core capabilities to provide the nearest service on the side close to the object or data source.hisapplication programInitiated at the edge side to produce fasternetwork serviceRespond to meet the basic needs of the industry in real-time business, application intelligence, security and privacy protection.Edge computing is between physical entities and industrial connections, or at the top of physical entities.Cloud computing can still access the historical data of edge computing.[1]
Edge computing is not a new word.As a content distribution network CDN and cloud service provider, AKAMAI has cooperated with IBM on "edge computing" since 2003.As one of the largest distributed computing service providers in the world, it undertook 15-30% of the global network traffic at that time.In one of its internal research projects, it proposed the purpose and problem solving of "edge computing", and provided edge based services on its WebSphere through AKAMAI and IBM.[1]
For the Internet of Things, the breakthrough in edge computing technology means that many controls will be realized through local devices without being handed over to the cloud, and the processing will be completed in the local edge computing layer.This will undoubtedly greatly improve the processing efficiency and reduce the load on the cloud.As it is closer to users, it can also provide users with faster response and address the needs at the edge.[2]
Vs Cloud Computing
Announce
edit
In foreign countriesCiscoThe representative network companies mainly focus on fog computing.Cisco is no longer a founding member of the Industrial Internet Alliance, but it has focused on leading the OpenFog Alliance.[3]
Cloud Computing Paradigm
Whether it is cloud, fog or edge computing, it is only a method or mode to realize the computing technology required by the Internet of Things and intelligent manufacturing.Strictly speaking, there is no essential difference between fog computing and edge computing, which are both close to the calculations provided by the field application end.In essence, they are all relative to cloud computing.
Paradigm of Edge Computing
From the computing paradigms of the two, we can see that the data computing on the edge has suddenly become rich
Come on.A new imagination space has been created here.
Application of Internet of Things
Announce
edit
The rapid development of global smart phones has promoted the development of mobile terminals and "edge computing".And the intelligent society of the Internet of Things and the perception of everything is born with the development of the Internet of Things, and the edge computing system also came into being.
in fact,Internet of ThingsThe concept of Internet of Things has been put forward for more than 15 years. However, the Internet of Things has not become a hot application.There is a long process from a concept to real application, and the matching technology, product equipment cost, acceptance, trial and error process are all long, so it is often unable to quickly form a mass market.
Position of edge calculation in the whole calculation
according toGartnerAccording to the theory of technology maturity curve, IoT has reached its peak in concept in 2015.Therefore, the large-scale application of the Internet of Things has begun to accelerate.Therefore, IoT will enter an application explosion period in the next 5-10 years, and edge computing is also expected to get more applications.
Gartner technology maturity curve
framework
Announce
edit
In China, the Edge Computing Alliance ECC is trying to promote the integration of three technologies, namely, the integration of OICT (operational, information, and communication technology).Its computing objects mainly define four areas. The first is the problem of the device domain,[1]Compared with automatic I/O acquisition, the pure IoT devices that appear are different but also overlap.The data that can be directly used for optimization at the top level, but not involved in control itself, can be directly placed at the edge to complete processing;The second is the network domain.stayTransport layerThe transmission mode, mechanism and protocol of the direct end IoT data and the data from the automated production line will be different. Therefore, the problem of data standards for transmission should be solved here. Of course, the underlying automated data can be directly accessed under the OPC UA architecture. However, for the interaction of Web data, there will be coordination between IT and OT,Although some leading automation enterprises have provided mechanisms for data transmission in the Web mode, most of the on-site data still have these problems.The third is the data domain. The data storage, format and other problems that need to be solved in the data domain after data transmission, as well as the mechanism and strategy of data query and data interaction, are all problems that need to be considered in this field.
The last one is the most difficult application domain, which may be the most difficult problem to solve. There are not many practical applications of application models in this field.
Edge Computing Reference Architecture 1.0
The definition of the reference architecture of Edge Computing Alliance ECC for Edge Computing includes four domains: device, network, data and application. Platform providers mainly provide software and hardware infrastructure in network interconnection (including bus), computing capacity, data storage and application.
And fromIndustrial value chainFrom the perspective of integration, ECC proposed CROSS, which is to realize real-time business, data optimization, application intelligence, security and privacy protection on the basis of agile connection, and bring value and opportunities to users at the edge of the network, which is the focus of the alliance members.
Nature of calculation
Announce
edit
In fact, automation takes "control" as its core.Control is based on "signal", while "calculation" is based on data, which means more "strategy" and "planning". Therefore, it focuses more on "scheduling, optimization and path".Just like the system for dispatching high-speed trains across the country, each increase in train number will triggerdispatching systemIt is an operation research and planning problem based on time and nodes.The application of edge computing in the industrial field is more of this kind of "computing".
In brief, traditional automatic control is based on signal control, while edge computing can be understood as "information based control".
It is worth noting that although edge computing and fog computing talk about low latency, their cycles of 50mS and 100mS are still very delayed for such "control tasks" as 100 μ S of high-precision machine tools, robots, and high-speed graphic printing systems. The so-called "real-time" of edge computing is unfortunate from the perspective of the automation industry,It is still classified as "non real-time" applications.
Cloud computing - edge computing differentiates data processing
industry
Announce
edit
Edge computing is a technology developed in the context of high bandwidth, time sensitive, and integration of the Internet of Things. The concept of "Edge" was indeed mentioned earlier by automation/robot manufacturers such as ABB, B&R, Schneider, and KUKA. It is intended to cover "IT resources close to users and data sources".This is a design that extends from traditional automation vendors to IT vendors. On April 5, 2016, Schneider claimed that it can define physical infrastructure for edge computing - although its focus is still on the concept of "micro data center".Other automation vendors mention computing, which shows a trend of integration with IT, and also has the concept of edge and ubiquity.
In fact, IT and OT are also interpenetrating each other. Automation manufacturers have begun to extend their IT capabilities in their products, including Bosch, SIEMENS, GE and other large manufacturers in terms of informatization and digital software platforms, as well as products and technologies such as Bachelet and Rockwell in terms of IoT integration and integration of Web technologies that provide the foundation.In fact, IT technology has also begun to integrate bus interfaces, HMI functions, industrial field transmission equipment gateways, switches and other products in its products.
IoT is regarded as an area of rapid growth in the future, including various Internet based technologies that have emerged at the forefront. Qualcomm has proposed the Internet of Everything, which can be called IoX.Therefore, a new industrial pattern is emerging. As far as the boundary definition of the Edge Computing Alliance ECC is concerned, Huawei's main purpose is to provide computing platforms, including basic networks, clouds, edge servers, transmission equipment and interface standards, while IntelARM provides chip and processing capability guarantee for edge computing, ICT Academy plays the role of integration of transmission protocol and system implementation, while Shenyang Automation Institute and Softcom Power play the role of practical application.
However, edge computing/fog computing should be implemented. Especially in industry, "application" is the core issue. The so-called integration of IT and OT emphasizes more on the application on the OT side, that is, the goal of the operating system.
Division of labor under great integration
Announce
edit
In the industrial field, edge application scenarios include energy analysis, logistics planning, process optimization analysis, etc.In terms of production task allocation, it is necessary to make optimal equipment scheduling for production according to the production order. This is the basic task unit of APS or generalized MES, and requires a lot of calculation.Whether these calculations depend on the software platform of a specific MES manufacturer or the "edge computing" platform - an analysis platform built on Web technology, there will not be much difference in the future.In a sense, the MES system itself is a traditional architecture, and its core can be in the dedicated software system, cloud, fog or edge side.[2]
In such an application scenario, in general, in the application of the entire intelligent manufacturing and industrial Internet of Things, the respective division of labor is as follows.
Connection architecture of edge computing (orange part)
Automation manufacturers provide "acquisition", including the function of data source, which is to use the native "information" generated by automation in distributed I/O acquisition, bus interconnection, and control machine production, status, quality, etc.
ICT manufacturers provide "transmission" to realize industrial connection.Because in terms of how to provide data transmission, storage and computing, ICT manufacturers have their traditional advantages, including cost, and cloud platform advantages.
The business experience and knowledge of traditional industrial enterprises provide "analysis" basis for analysis software (independent or internal) manufacturers.Understanding these business processes is still essential.The ultimate goal of industrial chain coordination is still to solve the core problem of "quality, cost and delivery".
Experts from China Unicom Group said that 2020 is the first year for commercial use of 5G SA networks in China. In the next few years, 5G networks will carry more industry demands and bring more business opportunities.Industrial applications need to have differentiated, deterministic, independent and flexible private networks. Different industry services have different requirements for bandwidth, delay, reliability, etc. This requires 5G private networks to have deterministic experience, self service, rapid development and launch of new services and other network capabilities.In the trend of cloud network integration, edge computing will help 5G industry applications to accelerate the landing practice.[4]
Development prospect
Announce
edit
On December 2, 2022, edge computing was selected as one of the ten key technologies released by the "Zhizhan 2023" forum that will have a significant impact on the development of society, economy and industry in the next few yearssingle[5]。
