Edge and Artificial Intelligence

With AI at the edge, not only can network nodes ingest a range of sensor, video, and other input data and output real-time decisions, the millisecond latency of 5G technology allows those responses to be integrated in control applications. Edge AI will allow real time operations including data creation, decision, and action where milliseconds matter. Real time operations are important for self-driving cars, robots, and many other areas.

More AI is being incorporated into edge devices, from Internet of Things (IoT) devices to smartphones, as AI algorithms improve.

Artificial intelligence (AI) is a data-heavy, compute-intensive technology – a perfect candidate for edge computing. Edge benefits AI by helping overcome the technological challenges associated with AI-enabled applications and it is specifically well positioned to deliver on:  Reduced data transfer to the central cloud: Machine learning algorithms must ingest very large amounts of data in order to detect trends and provide accurate recommendations. Rather than streaming all of this to the cloud, more processing can happen at the edge, thus reducing backhaul costs.

 Real-time decision making (with reduced latency) : where machine learning is triggering real-time actions, latency must be kept to a minimum. Rather than streaming all raw data to a remote cloud for centralised processing, edge computing can enable these decisions to be made close to the source of the data and resulting actions triggered at the edge:

 Local data storage and processing. By using edge computing, sensitive or proprietary information, such as customer location data, is stored locally rather than in the cloud. By performing AI at the edge, only aggregated data sets and key insights need to be streamed to the cloud and the rest of the data is remains local.

When instantaneous action is required viz. braking in self-driving cars with near-zero latency, Edge becomes an optimal option. MCUs (Micro Controller Unit) are very low-cost tiny computational devices. They are often found in the heart of IoT edge devices. They hold a large amount of idle untapped potential. This power can be perfectly tapped by AI. AI can be added to Edge devices.

AI has become a major player in the market for adoption of edge computing. Sensitive data that could not be sent to the cloud for analysis and processing is also handled at the edge.

Edge computing has been able to deliver three essential capabilities, that of faster decision making, filtered data transfer and local data processing. Since most decision- making has recently been taking advantage of AI, edge is becoming the perfect destination for deploying machine learning models trained in the cloud.

For services and applications that require exceptionally low latency or have a limited “pipe” through which to pipe data, there are some downsides to the cloud that are better addressed at the edge.