The phrase ‘Internet of Things’, or IoT, can be explained as a connected network of distributed sensors over the internet. IoT devices generate a lot of data that needs to be analyzed in order to be useful. This kind of insight is what makes the connected devices smart and allow them to take intelligent actions. As with all data there is a requirement to analysis. The ‘Analytics of Things’, or AoT, refers to the use of analytics in making connected devices smart and enable them to take intelligent action.
Analytics in AoT
The advantage of AoT is that you can aggregate data from multiple devices and make comparisons across time and users, leading to better decisions. Big Data Analytics analyzes huge volumes of user-generated data in order to support long-term use cases such as predictive maintenance, capacity planning, customer 360 feedback and revenue protection. AoT meanwhile, points to the collecting and compressing of massive amounts of low latency, short duration, and high volume machine generated data coming from a wide variety of sensors, to support real time use cases such as operational optimization, real-time ad bidding, as well as fraud and security breach detection. (*source: Dell EMC)
Example
The example of the Smart Parking and Smart Routing Services feeding new data to AoT, illustrated how this provides a very different view of parking and traffic activities.
Smart Services not only find a static answer when the question is asked, but will continue to actively maintain a best choice throughout the journey in respect of dynamic changes in parking bay availability. AoT adds entirely new and original data sets, which have not been available from traditional sources, from Smart Service requests and outcomes. Some examples of the data available from the above use case are:
1. Starting and destination geo-location shared by the citizen.
2. The true total demand for parking including requests that were unfulfilled.
3. The routes used.
4. The journeys abandoned due to non-availability of a parking bay.
The example of the Smart Parking and Smart Routing Services feeding new data to AoT, illustrated how this provides a very different view of parking and traffic activities.
The computing capacity of ‘Things’ has grown exponentially over the last few years and this has resulted in a change in the way data is analyzed. Many of the early IoT applications were about collecting data from ‘Things’ and sending them elsewhere for analysis. But now the increased computing capacity of ‘Things’ allows complex computation to run on-site. This new trend is referred as Edge computing, as part of the work happens right at the edge of the network where IoT connects the physical world to the Cloud. Edge computing is not just limited to data processing and computation on IoT devices. The vital part of it is a strong and seamless integration between IoT and cloud. Edge computing preserve privacy, reduce latency and is robust to connectivity issues.
Internet of Things is useful only if the “things” are smart, and this will happen through the Analytics of Things. Companies that have taken a data-driven approach are making a lot more progress when compared to traditional businesses. Many large companies are investing in IoT edge analytics as it is the answer to maintenance and usability of data.