Why Nokia and Stanley Black & Decker’s IoT is smarter than yours

Many businesses deploy IoT systems to collect data for analytics. However, insights gained from an analysis is only useful if it is delivered at the right time.

To get the timing right, tech companies are focussing on what is known as the “intelligent edge”.

It solves the issue of IoT devices needing a constant connection to the cloud when operating in areas with a limited network connection.

Intelligent edge is basically a “smarter” Internet of Things (IoT) where sensors recognize patterns and detect anomalies with the help of machine learning (ML).

In basic forms of IoT, sensors that go offline create pockets of lost data and make it impossible to detect changes in data patterns for analytics.

Amazon AWS has a solution. Companies can use AWS Greengrass to deploy ML models at the edge devices to detect anomalies in data right where the sensor is and transmit alerts to the cloud only when needed.

The training for the algorithm remains in the cloud, and updates to the model are sent over the air when it is needed. This reduces the need for data to be constantly transferred between the cloud and the device.

Intelligent edge can help businesses in many ways. Michael Garcia, Senior Technical Program Manager of AWS IoT, shared with Tech HQ some examples of AWS Greengrass implementation and how it has helped businesses:

Nokia

Nokia provides video surveillance streams for the oil and gas industry.

Due to high bandwidth costs, it needed a way to analyze video streams at the edge to reduce costs.

Using the ML models trained on its proprietary platform, the oil industry was able to pair real-time drilling data with production data of nearby wells.

With AWS Greengrass, Nokia can send data to remote centers only when anomalies are detected.

It was also able to optimize data sent to other wells, and to the cloud, based on rules and alerts set up on the locally processed data.

Stanley Black & Decker

Industrial tools manufacturer Stanley Black & Decker needed to monitor tools in real time to detect failures.

Relying on traditional cloud-based IoT was an issue for construction sites in rural areas due to constrained network resources.

Using AWS Greengrass, the company was able to monitor and filter where the sensors are.

Applications can now send information about the health of asset and predict mechanical failures before they occur.

It also detects and compares vibrations of tools to historical signatures that could indicate potential failure.

Analytics where your business is

Whether in cost savings or getting better yield, deploying ML at the edge helps increase efficiency in business. Ultimately, it allows businesses to focus on their outcome and strategy. Improving your IoT can help speed up the process.