<> Edge computing

Edge computing is close to objects or data sources
Network edge side of , Converged network , calculation , storage , Distributed open platform for core competence application , Providing edge intelligent services nearby , Meet the needs of industry digitalization in agile connection , Real time service , Data optimization , Applied Intelligence , Key requirements for security and privacy protection .



<> Development background

cloud computing
Cloud computing 2005 After the proposal of , And we started to change our lives step by step , study , The way it works . Cloud center has powerful processing performance , It can handle massive data .
but , The system performance bottleneck of cloud computing model lies in the limitation of network bandwidth , It takes time to transfer massive data , Cloud centers also need time to process data , This will increase the response time of the request , Poor user experience .
Internet of things
With the rapid development of the Internet of things, we have entered the post cloud era , Almost all electronic devices can now be connected to the Internet , These electronic devices will produce huge amounts of data .
Internet of things applications may require extremely fast response times , Data privacy and so on .
but , If the data generated by the Internet of things is transmitted to the cloud computing center , It will increase the network load , The Internet can cause congestion , These data can not be processed timely and effectively .
The birth of edge computing
With the promotion of Internet of things and cloud services , We assume a new model for dealing with problems , Edge computing . On the edge of the network
produce , handle , Analysis data . Processing these data at the edge node will lead to minimal response time , Reduce network load , Ensure the privacy of user data .

Cloud computing for non real time , Long period data , Business decision scenario ; And edge computing is real-time , Short period data , Local decision-making and other scenarios play an irreplaceable role .



<> Edge computing reference architecture

ECC Edge computing reference architecture developed by the organization 2.0 The version is as follows .

From the horizontal level of Architecture , It has the following characteristics :
• Model driven unified service framework for intelligent services , Intelligent collaboration of development and deployment is realized by developing service framework and deploying operational service framework , It can realize the consistency of software development interface and the automation of deployment and operation ;
• Intelligent business choreography through business Fabric Define end to end business flow , Achieving business agility ;
• Connection calculation CCF(Connectivity and Computing
Fabric) The implementation architecture is very simple , Complexity of intelligent distributed architecture for business masking edge ; realization OICT Automation and visualization of infrastructure deployment operations , Intelligent collaboration supporting edge computing resource services and industry business requirements ;
• intelligence ECN(Edge Computing Node) Compatible with multiple heterogeneous connections , Support real-time processing and response , Provide software and hardware integration security ;

The edge computing reference architecture provides a modelled open interface at each layer , The architecture is open at all levels ; Edge computing reference architecture through vertical management services , Data lifecycle services , Security services , Realize the whole process of business , Intelligent service in the whole life cycle .


<> Related applications

Cloud offloading
: In traditional content distribution networks , The data will be cached to the edge node . With the development of Internet of things , The production and consumption of data are in the edge node , That is to say, the edge nodes also need to undertake certain computing tasks . The process of offloading the computing tasks in the cloud center to the edge nodes is called cloud offloading .
Video analysis
smart city
: For some location-based applications , The performance of edge computing depends on cloud computing . Like navigation , According to its real-time location, the terminal equipment can send the relevant location information and data to the edge node for processing , Edge nodes make decision based on existing data . The network overhead in the whole process is minimal . User requests are responded to very quickly .
Smart home ...



<> Related technologies

Edge collaboration
: Using multiple edge nodes to cooperate , Create a virtual view of shared data , Use a predefined common service interface to integrate the data . At the same time through this interface , We can write applications to provide users with more complex services

Let's give an example of cooperation and win-win of multiple edge nodes :

Like when the flu broke out , Hospital as an edge node and pharmacy , Pharmaceutical companies , government , Insurance industry and other nodes share data , The current number of infected people , Symptoms of influenza , The treatment cost is shared to the above edge nodes .
Pharmacies adjust their purchasing plans through these information ;
Pharmaceutical companies, on the other hand, can learn which medicines are important through shared data , Raise the priority of the production of such drugs ;
The government can also take further action to control the spread of the flu outbreak ;
in short , Any node in the edge node has got some benefits in this data sharing .