A survey on facilities for experimental internet of things research

Abstract

The initial vision of the Internet of Things (IoT) was of a world in which all physical objects are tagged and uniquelly identified by RFID transponders. However, the concept has grown into multiple dimensions, encompassing sensor networks able to provide real-world intelligence and goal-oriented collaboration of distributed smart objects via local networks or global interconnections such as the Internet. Despite significant technological advances, difficulties associated with the evaluation of IoT solutions under realistic conditions, in real world experimental deployments still hamper their maturation and significant roll out. In this article we identify requirements for the next generation of the IoT experimental facilities. While providing a taxonomy, we also survey currently available research testbeds, identify existing gaps and suggest new directions based on experience from recent efforts in this field.

Workload Modeling for Computer Systems Performance Evaluation

“…Likewise, Gluhak at al. realize the need for including human behavior in the loop of experimentation on the Internet of things, because the location, mobility, and activity of the "things" are related to humans [287].…”

Padoc: Enabling social networking in proximity

“…The process of gathering performance evaluation from actual mobile devices without the help of location and connection emulators also highlight the logistical difficulty of performing such real life tests given the lack of dedicated testbed tools. Indeed, even though experiments have become more prominent in the community [24], most of the open available testbeds are sensor oriented [14] and few include smartphones (an exception includes SmartSantander [27] which provides a SmartCity testbed) and to the best of our knowledge none of them is targetted at off-theshelf mobile devices on which people centric social media in proximity would run. Thus, we argue that this is an important research gap, which needs to be addressed in order to support larger scale validation of communication middleware and services for mobile social newtorking in proximity.…”

Leveraging virtualization for scenario based IoT application testing

“…For example, in cloud platforms [5] such as Samsung Artik or IBM IoT there are the device simulation modules which are able to generate randomized data in order to verify the processing in the clouds. At the same time, WSN testbeds [6] are designed to verify low level interactions between devices. Such testbeds constitutes of several, sometimes even hundreds or thousands, of nodes deployed in the particular place.…”