「霧計算」比雲計算更接地氣

  • July 17th, 2014

霧計算 (Fog Computing) 是雲計算 (Cloud Computing) 的延伸概念,由思科 (Cisco) 首創。這個因「雲」而「霧」的命名源自「霧是更貼近地面的雲」這一名句。

霧計算和雲計算一樣,十分形象。雲在天空飄浮,高高在上,遙不可及,刻意抽象;而霧卻現實可及,貼近地面,就在你我身邊。霧計算並非由性能強大的服務器組成,而是由性能較弱、更為分散的各類功能計算機組成,滲入工廠、汽車、電器、街燈及人們物質生活中的各類用品。

與雲計算相比,霧計算所採用的架構更呈分佈式,更接近網絡邊緣。霧計算將數據、數據處理和應用程序集中在網絡邊緣的設備中,而不像雲計算那樣將它們幾乎全部保存在雲中。數據的存儲及處理更依賴本地設備,而非服務器。所以,雲計算是新一代的集中式計算,而霧計算是新一代的分佈式計算,符合互聯網的「去中心化」特徵。

霧計算不像雲計算那樣,要求使用者連上遠端的大型數據中心才能存取服務。除了架構上的差異,雲計算所能提供的應用,霧計算基本上都能提供,只是霧計算所採用的計算平台效能可能不如大型數據中心。

雲計算承載著業界的厚望。業界曾普遍認為,未來計算功能將完全放在雲端。然而,將數據從雲端導入、導出實際上比人們想像的要更為複雜和困難。由於接入設備 (尤其是移動設備) 越來越多,在傳輸數據、獲取信息時,帶寬就顯得捉襟見肘。隨著物聯網和移動互聯網的高速發展,人們越來越依賴雲計算,聯網設備越來越多,設備越來越智能,移動應用成為人們在網絡上處理事務的主要方式,數據量和數據節點數不斷增加,不僅會佔用大量網絡帶寬,而且會加重數據中心的負擔,數據傳輸和信息獲取的情況將越來越糟。

因此,搭配分佈式的霧計算,通過智能路由器等設備和技術手段,在不同設備之間組成數據傳輸帶,可以有效減少網絡流量,數據中心的計算負荷也相應減輕。霧計算可以作為介於M2M (機器與機器對話) 網絡與雲計算之間的計算處理,以應對M2M網絡產生的大量數據—運用處理程序對這些數據進行預處理,以提升其使用價值。

  霧計算不僅可以解決聯網設備自動化的問題,更關鍵的是,它對數據傳輸量的要求更小。霧計算這一「促進云數據中心內部運作的技術」有利於提高本地存儲與計算能力,消除數據存儲及數據傳輸的瓶頸,非常值得期待。

What is fog computing (fogging) ?

  • July 17th, 2014

Fog computing, also known as fogging, is a model in which data, processing and applications are concentrated in devices at the network edge rather than existing almost entirely in the cloud.

That concentration means that data can be processed locally in smart devices rather than being sent to the cloud for processing. Fog computing is one approach to dealing with the demands of the ever-increasing number of Internet-connected devices sometimes referred to as the Internet of Things (IoT).

In the IoT scenario, a thing is any natural or man-made object that can be assigned an IP address and provided with the ability to transfer data over a network. Some such things can create a lot of data. Cisco provides the example of a jet engine, which they say can create 10 terabytes (TB) of data about its performance and condition in a half-hour. Transmitting all that data to the cloud and transmitting response data back puts a great deal of demand on bandwidth, requires a considerable amount of time and can suffer from latency. In a fog computing environment, much of the processing would take place in a router, rather than having to be transmitted.

Fog Computing extends the cloud computing paradigm to the edge of the network. While fog and cloud use the same resources (networking, compute, and storage) and share many of the same mechanisms and attributes (virtualization, multi-tenancy) the extension is a non-trivial one in that there exist some fundamental differences stemming from the reason fog computing was developed: to address applications and services that do not fit the paradigm of the cloud.

These applications and services include:

.Applications that require very low and predictable latency. The cloud frees the user from many implementation details, including the precise knowledge of where the computation or storage takes place. However, this freedom from choice, welcome in many circumstances becomes a liability when any significant degree of latency is unacceptable(gaming, videoconferencing).

.Geographically distributed applications (pipeline monitoring, sensor networks to monitor the environment). Fast mobile applications (smart connected vehicle, connected rail).

.Large-scale distributed control systems (smart grid, connected rail, smart traffic light systems).

Cisco’s Ginny Nichols coined the term fog computing. The metaphor comes from the fact that fog is the cloud close to the ground, just as fog computing concentrates processing at the edge of the network. According to Cisco, fog computing extends from the edge to the cloud, in a geographically distributed and hierarchical organization.

"Cisco Fog Computing" is a registered name; “fog computing” is open to the community at large.