ai边缘计算入门_边缘计算入门

ai边缘计算入门

Edge Computing is a distributed computing paradigm in which processing and computation are performed mainly on classified device nodes known as smart devices or edge devices as opposed to processed in a centralized cloud environment or data centers. It helps to provide server resources, data analysis, and artificial intelligence to data collection sources and cyber-physical sources like smart sensors and actuators. Is edge computing seen as necessary? In the realization of physical computing, smart cities, computing, multimedia applications such as augmented reality and cloud gaming, and the Internet of Things (IoT). It is a way to streamline the movement of traffic from IoT devices and implement real-time local data analysis.

边缘计算是一种分布式计算范例，其中处理和计算主要在称为智能设备或边缘设备的分类设备节点上执行，而不是在集中式云环境或数据中心中进行处理。 它有助于为数据收集源和网络物理源(例如智能传感器和执行器)提供服务器资源，数据分析和人工智能。 边缘计算是否必要？ 在物理计算，智能城市，计算，增强现实和云游戏等多媒体应用以及物联网(IoT)的实现中。 这是一种简化来自物联网设备的流量移动并实施实时本地数据分析的方法。

Data produced by the Internet of Things (IoT) devices to be processed where it is created instead of taking away to the routes to data centers with the help of edge computing. It also benefits Remote Office/Branch Office (ROBO) environments and organizations that have dispersed user base geographically. A significant benefit is that it improves time to action and reduces response time to milliseconds, while also conserving network resources.

物联网(IoT)设备产生的数据将在创建时进行处理，而不是借助边缘计算带走到数据中心的路由。 它还使远程办公室/分支机构(ROBO)环境和在地理位置上分散用户群的组织受益。 一个显着的好处是它可以缩短行动时间，并将响应时间缩短至毫秒，同时还可以节省网络资源。

“Practice of processing data near the edge of your network locally or on own server produced by IoT(Internet of Things) instead of centralized data processing warehouse. ”

“在本地或在IoT(物联网)生产的自己的服务器上而不是集中式数据处理仓库中，在网络边缘附近处理数据的实践。 ”

物联网(IoT)和边缘计算 (Internet of Things (IoT) and Edge Computing)

In IoT, with the help of edge computing, intelligence moves to the edge. Like if you have massive amounts of data and for this, you have to leverage in such end to endways or highly sensor intensive or data-intensive environments where data is generated at the edge, which is due to IoT as data sensing at the edge.

在物联网中，借助边缘计算，情报将移至边缘。 就像您拥有大量数据一样，为此，您必须在端到端或传感器密集型或数据密集型环境中利用数据，这些数据是在边缘生成的，这是由于物联网作为边缘的数据感知而造成的。

And also, with real-time information, the increasing unstructured data of which sensor and IoT data are part, traditional approaches don’t meet the requirements which are needed. There are various scenarios where speed and high-speed data are the main components for management, power issues, analytics, and real-time need, etc. helps to process data with edge computing in IoT.

而且，对于实时信息而言，越来越多的非结构化数据(其中的传感器和IoT数据已成为其中的一部分)，传统方法无法满足所需的要求。 在各种情况下，速度和高速数据是管理，电源问题，分析和实时需求等的主要组成部分，有助于通过IoT中的边缘计算来处理数据。

为物联网(IoT)启用边缘计算的好处 (Benefits of Enabling Edge Computing for the Internet of Things (IoT))

• Lesser Network Load
  较小的网络负载
• Zero Latency
  零延迟
• Reduced Data Exposure
  减少数据泄露
• Computational Efficient
  计算效率
• Costs and Autonomous Operation
  成本与自主经营
• Security and Privacy
  安全与隐私

物联网(IoT)计算的未来方向 (Future Directions of Computing for the Internet of Things (IoT))

• Edge-to-Cloud data exchange capabilities
  边缘到云的数据交换功能
• Common-on-Edge data exchange capabilities
  通用边缘数据交换功能
• Streaming Data Analytics and Batch frameworks and APIs
  流数据分析以及批处理框架和API
• Controlled rolling and Versioning upgrades of applications
  应用程序的受控滚动和版本升级
• Status of application monitoring from an Ad-Hoc Cloud Dashboard
  通过Ad-Hoc Cloud仪表板监视应用程序的状态
• Cloud-Based Deployments of Edge Computing Applications
  边缘计算应用程序的基于云的部署

边缘计算为何如此重要？ (Why is Edge Computing Important?)

• New Functionalities are offered.
  提供了新功能。
• Easier configurations.
  配置更简单。
• Hacking Potential is increased.
  黑客潜能增加。
• The load on the server is reduced.
  服务器上的负载减少了。
• Load on Network is reduced.
  网络负载减少了。
• Application Programming Interface.
  应用程序接口。
• Increases Extensibility.
  增加可扩展性。
• Centralized Management.
  集中管理。
• Costs of Licensing.
  许可费用。
• Support and Updates.
  支持和更新。

启用边缘计算的优势 (Advantages of Enabling Edge Computing)

• Speed is increased.
  速度增加。
• Reliability is increased.
  可靠性提高。
• The random issue is reduced.
  减少了随机性问题。
• The compliance issue is reduced.
  减少了合规性问题。
• Hacking issues are reduced.
  减少黑客问题。
• Random issues are reduced.
  减少了随机问题。

云计算vs.边缘计算vs.雾计算 (Cloud Computing vs. Edge Computing vs. Fog Computing)

Edge Computing and Fog Computing are the extensions of Cloud Networks, which are a collection of servers comprising a distributed network. Such networks allow organizations to exceed the resources that would be otherwise available to them. The main advantage of cloud networks is that they allowed data to be collected from multiple sources, which is accessible anywhere over the internet. While Fog Computing and Edge Computing are almost similar, where the talk about intelligence and processing of data at the time of creation.

边缘计算和雾计算是云网络的扩展，云网络是包含分布式网络的服务器的集合。 这样的网络使组织可以超出原本可用于他们的资源。 云网络的主要优势在于，它们允许从多个来源收集数据，这些数据可以在Internet上的任何位置进行访问。 尽管雾计算和边缘计算几乎相似，但是在创建时谈论的是智能和数据处理。

However there is a crucial difference between these two in terms of intelligence and computing power, where Fog Computing focus more on intelligence at local area network and this architecture transmits data from endpoints to a gateway where it is sent to sources for processing and return to transmission while Edge Computing focus more on computing power and processing of data locally at the edge of a network. It performs processing on embedded computing platforms interfacing to sensors and controllers.

但是，在智能和计算能力方面，这两者之间存在至关重要的区别，其中Fog Computing更加侧重于局域网的智能，并且该体系结构将数据从端点传输到网关，然后将其发送到源以进行处理并返回传输而边缘计算则更侧重于网络边缘本地的计算能力和数据处理。 它在与传感器和控制器接口的嵌入式计算平台上执行处理。

边缘计算的安全性 (Security in Edge Computing)

There are two sides of security in edge computing –

边缘计算的安全性有两个方面–

One of them is that the security in edge computing is better than any other part of the data storage application because data is not traveling over the network; it stays where it is created.

其中之一是边缘计算的安全性比数据存储应用程序的任何其他部分都要好，因为数据不在网络上传输。 它停留在创建位置。

The flip side of it is that security in edge computing is less secure because the edge devices in themselves can be more vulnerable.

不利的一面是边缘计算的安全性较差，因为边缘设备本身可能更容易受到攻击。

In conclusion, data encryption, access control, and the use of virtual private networks are crucial elements to protect the edge computing system.

总之，数据加密，访问控制和虚拟专用网络的使用是保护边缘计算系统的关键要素。

边缘计算变得至关重要的用例 (Use Cases where Edge Computing becomes critical)

• Having low latency, e.g., Closed-loop interaction between machine insights.
  具有低延迟，例如，机器分析之间的闭环交互。
• For real-time analytics, access to temporal data.
  对于实时分析，访问时间数据。
• Low connectivity, e.g., Remote Location.
  连接性低，例如“远程位置”。
• The high cost of transferring data to the cloud.
  将数据传输到云的高成本。
• Bandwidth.
  带宽。
• Cybersecurity constraints.
  网络安全约束。
• Compliance and Regulation.
  合规性。
• The immediacy of Analysis, e.g., To check machine performance.
  立即进行分析，例如检查机器性能。
• Predictive Maintenance.
  预测性维护。
• Energy Efficiency Management.
  能源效率管理。
• Flexible Device Replacement.
  灵活的设备更换。

为什么边缘计算很重要？ (Why Edge Computing Matters?)

• When IoT devices have poor connectivity.
  物联网设备连接不良时。
• Not efficient for IoT devices to be in constant touch with the central cloud.
  IoT设备与中央云保持持续联系的效率不高。
• The latency factor reduces latency because data doesn’t have to traverse over a network to a central cloud for processing.
  延迟因子减少了延迟，因为数据不必通过网络遍历到中央云进行处理。
• Where latencies are untenable like manufacturing or financial services.
  延迟难以维持的地方，例如制造业或金融服务业。
• As soon as data is produced, it doesn’t need to send over a network; instead, it compiles the data and sends daily reports to the cloud for long term storage, i.e., reduces the data traversing.
  数据一旦生成，就不需要通过网络发送； 相反，它编译数据并将每日报告发送到云以进行长期存储，即减少了数据遍历。
• The buildout of the next-generation 5G cellular networks by telecommunication companies.
  电信公司正在建设下一代5G蜂窝网络。
• Direct access to gateway into the telecom provider’s network, which connects to a public IaaS cloud provider.
  直接访问网关到电信提供商的网络，该网关连接到公共IaaS云提供商。

翻译自: https://medium.com/dataseries/a-primer-on-edge-computing-3ef550c3d84e

ai边缘计算入门