Fog Computing: Outcomes at the Edge with Machine Learning
Edge computing (or Fog Computing) is a method of optimizing cloud computing systems by performing data processing at the edge of the network, near the source of the data. Edge computing is a natural next step after cloud computing. It wouldn’t be practical for each device to use the cloud like smartphones do. Today phones send everything to the cloud to be processed, the data is stored in the cloud, and the results are returned to the device.
There are several examples where edge computing gives IoT a competitive edge. For example, in industrial internet of things applications such as aviation, smart traffic lights, or manufacturing, the edge devices capture streaming data that can be used to prevent a part from failing, reroute traffic, optimize production, and prevent product defects. When data analysis is done at the edge of a network, that’s known as “Edge Analytics.”
Data is more valuable at the Edge:
Time value of data means that the data you have right now won’t mean as much a week, day or even hour from now. This coupled with the proliferation of IoT sensors, video cameras, social, and other streaming data is driving organizations to use edge computing to provide the real-time analytics that impact the bottom line, or in some cases, stop a disaster from happening before it starts.
Organizations are currently reliant on large and complex clusters for data analytics, and these clusters have bottlenecks including data pipelining, indexing and extract, as well as transform and load processes. While centralized infrastructures work for analyses that rely on static or historical data, it is critical for many of today’s organizations to have fast and actionable insight by correlating newly obtained information with legacy information in order to gain and maintain a strong competitive advantage.
An increasing amount of data is priceless in the seconds after it’s collected — consider the instance of a financial fraud or hacker accessing accounts — but it loses all value during the time it takes to move it to the centralized data center infrastructure or upload it to the cloud. Losing value from that data due to slow decisions is not acceptable, especially when an edge-computing platform that eliminates moving data provides the near-instant intelligence needed. Data analytics at the edge, gives organizations tools to prevent fraud or fight data breaches in real time.
Three Use Cases for Fog Computing:
Remote monitoring for Oil & Gas operations: Edge computing for Oil & Gas operations can mean the difference between normal operations and a disaster. Traditional centralized data analytics infrastructures can tell you what caused downtime or can predict failure based on supervised learning applied to different types of operations or failures based on a trained dataset. But setting up of rules that can do near-instant analysis at the site as the data is being created can see the signs of a disaster and take measures to prevent a catastrophe before it even starts.
Machine Learning Models: Anomaly Detection models (eg. Kalman Anomaly), Predictive models(eg. Bayesian change detection), Optimization Methods (eg. Linear optimization)
Retail customer behavior analyses: Retail Analytics to lessen cart abandonment and improve customer engagement using near-instant edge analytics — where sales data, images, coupons used, traffic patterns, and videos are created — provides unprecedented insights into consumer behavior. This intelligence can help retailers better target merchandise, sales, and promotions and help redesign store layouts and product placement to improve the customer experience. For example use beacons to collect information such as transaction history from a customer’s smartphone, then target promotions and sales items as customers walk through the store.
Machine Learning Models: Statistical Methods (eg. market basket analysis, Apriori), Time series clustering, etc.
Self Driving Cars: With next-generation advanced driver assistance systems (ADAS), cars will become much safer and more efficient as they grow increasingly aware of and react to the surrounding driving environment and conditions. Real success will mean the democratization of ADAS in which the technology is available in entry-level to premium vehicles, for first-time drivers to seniors, in passenger and commercial vehicles, and everywhere in between.
Cars must compute to compete with the development and deployment of next-generation technologies — and self-driving vehicles in the not too distant future — it is important to look at how the collective set of systems within the car can deliver a better experience versus approaching the car as a handful of independent technologies.
Machine Learning Models: Image processing, Anomaly detection (eg. Isolation forest outlier detection), Reinforced learning, VLSAM Technologies, etc.
NB: All opinions expressed here are explicitly my own, not related to work done for any of my employers or past clients. Twitter: @Telecomcloud_5g
