Personal tools
You are here: Home Research Trends & Opportunities New Media and Technology Fog Computing

Fog Computing

(US Navy Blue Angels, San Francisco Fleet Week - Jeff M. Wang)



Pushing computing, control, data storage and processing into the cloud has been a key trend in the past decade. However, cloud alone is encountering growing limitations in meeting the computing and intelligent networking demands of many new systems and applications. Local computing both at the network edge and among the connected things is often necessary to, for example, meet stringent latency requirements, integrate local multimedia contextual information in real time, reduce processing load and conserve battery power on the endpoints, improve network reliability and resiliency, and overcome the bandwidth and cost constraints for long-haul communications.

The cloud is now "descending" to the network edge and sometimes diffused onto end user devices, which forms the "fog". Fog computing distributes computing, data processing, and networking services closer to the end users along the cloud-to-things (C2T) continuum. Instead of concentrating data and computation in a small number of large clouds, fog computing envisions many fog systems deployed close to the end users or where computing and intelligent networking can best meet user needs. Fog computing and networking present a new architecture vision where distributed edge and user devices collaborate with each other and with the clouds to carry out computing, control, networking, and data management tasks.

Realizing fog computing and networking imposes many new challenges. For example, how to compose, deploy, and manage distributed fog services, how to enable highly scalable and manageable fog networking and computing, how to secure fog computing systems, how should the fog interact with the cloud, and how to enable users to control their fog services provided by fog operators. Addressing these challenges necessitates rethinking of the end-to-end network and computing architecture.


[Cisco]: Fog Computing and the Internet of Things:

The Internet of Things (IoT) is generating an unprecedented volume and variety of data. But by the time the data makes its way to the cloud for analysis, the opportunity to act on it might be gone. This white paper explains a new model for analyzing and acting on IoT data. It is called either edge computing or Fog computing:

  • Analyzes the most time - sensitive data at the network edge, close to where it is generated instead of sending vast amounts of IoT data to the cloud.
  • Acts on IoT data in milliseconds, based on policy.
  • Sends selected data to the cloud for historical analysis and longer


Embedded and Distributed Intelligence Capability


The capability of embedded and distributed intelligence in the network is a core architectural component of the IoT for three main reasons:

  • Data Collection: Centralized data collection and smart object management do not provide the scalability required by the Internet. For example, managing several million sensors and actuators in a Smart Grid network cannot efficiently be done using a centralized approach.
  • Network Resource Preservation: Because network bandwidth may be scarce and collecting environmental data from a central point in the network unavoidably leads to using a large amount of the network capacity.
  • Closed Loop Functioning: For some use cases, the IoT requires reduced reaction times. For instance, sending an alarm via multiple hops from a sensor to a centralized system (which runs analytics) before sending an order to an actuator would entail unacceptable delays.

This distributed intelligence capability is known as Fog Computing, an architecture specifically designed to process data and events from IoT devices closer to the source as opposed to a central data center (also known as "Cloud"). In summary, Fog Computing is an expansion of the cloud paradigm. It is similar to cloud computing but closer to the ground. The Fog Computing architecture extends the cloud out into the physical world of things.


Pervasive Computing


Pervasive computing (also called ubiquitous computing) (means "existing anytime and everywhere") is the growing trend towards embedding microprocessors in everyday objects so they can communicate information. Pervasive computing devices are completely connected and constantly available. Pervasive computing relies on the convergence of Internet, advanced middleware, operating system, mobile code, sensors, microprocessors, new I/O and user interfaces, networks, mobile protocols, location and positioning and new materials.








Document Actions