In 2020, about 75 billion different devices will be connected to the Internet and together they make the Internet of Things. The process industry can really take advantage of the increased data availability in terms of both productivity and energy efficiency. In this project, researchers will focus on the development of data analysis system for large-scale sensor networks. The aim is to increase capacity for the industry's data management by developing new data mining algorithms.

Background

Currently, large amounts of data from numerous sensors stream rapidly into interconnected IT systems for processing and storage. Gartner project that the 0.9 billion sensors and 1.6 billion personal devices that were connected via the Internet in 2009 will become up to 75 billion devices in 2020, constituting the Internet of Things.

Process industries can significantly benefit from the distributed data availability in both, productivity and energy efficiency, if the knowledge that is hidden within the diverse and rapidly growing data can be mined and can be appropriately applied to the business. To make a case, imagine smart grids that base their decisions on live data from smart meters and sensors on machines or vehicles which can lead to a substantially more efficient use of energy.

Unlike today’s "big-data" analysis systems which are commonly operating on manually pre-processed empirical data, the data analysis systems for the Internet of Things have to address some unique challenges. The continuous big-data analysis has to be scalable to support millions or even billions of sensors and still provide real time guarantees. Moreover, the system is required to be highly secure, for instance with respect to privacy. No existing system can so far satisfy those requirements as of today.

Within the context of the DAWN project, we will focus on researching and developing data analysis systems for large-scale networks of sensors. Our plan is to find solutions which can dramatically increase the data handling capability for industry by developing a new data mining algorithm and integrating the data analysis with our Internet of Things platform, SensibleThings.

Objectives

In the DAWN-project researcher will focus on:

• How can relations among attributes be revealed on live sensor data and the causal factors are reduced to ensure a correct and feasible live data analysis?
• How is it possible to enable distribution techniques in order to decentralize the analysis on large scale industry networks?

Researchers will develop distributed solutions that enable real time big data analysis in process and automation industries. Overall, the created framework will allow for distributed analyses on extreme scale data to be conducted in an efficient and easy manner. DAWN will enable collaborative and automated decisions in near real-time for geographically distributed teams with the potential to improve both productivity and energy efficiency.