Embedded Middleware for Distributed Raspberry Pi Device to Enable Big Data Applications

Applications making use of embedded systems are anticipated to become extremely important as we advance towards realizing the vision of "Internet of Things" with smart devices such as Raspberry Pi, and compute-anywhere paradigm where principles of distributed systems play pivotal roles. A case we envision here is a distributed network of low powered devices to accomplish various tasks autonomously. Driven by a distributed embedded system architecture, each of the devices can work on independent local data, which is device specific, to perform similar compute tasks simultaneously so a common goal can be achieved. This collaborative problem solving in the embedded setting is similar in concept to the big data paradigm now commonly proposed for commodity hardware and large databases. As the embedded devices become more capable and powerful the two concepts will combine. However, they are currently worlds apart, and thus forms the motivation of our research. In this project, a middleware layer is developed and tested to make the devices work collaboratively on local data within a network of Raspberry Pi devices. The middleware layer splits, distributes, computes and merges the computing tasks to accomplish a shared computing goal while performing the operations locally in a "shared nothing" architecture.