Original Article Enabling distributed intelligence assisted Future Internet of Things Controller (FITC) Hasibur Rahman ⇑ , Rahim Rahmani Department of Computer and Systems Sciences (DSV), Stockholm University, Nod Building, SE-164 55 Kista, Sweden article info Article history: Received 25 January 2017 Revised 1 May 2017 Accepted 2 May 2017 Available online 8 May 2017 Keywords: Future Internet Internet of Things Edge computing Distributed intelligence Belief-network abstract The unprecedented prevalence of ubiquitous sensing will revolutionise the Future Internet where state- of-the-art Internet-of-Things (IoT) is believed to play the pivotal role. In the fast forwarding IoT paradigm, hundreds of billions of things are estimated to be deployed which would give rise to an enormous amount of data. Cloud computing has been the prevailing choice for controlling the connected things and the data, and providing intelligence based on the data. But response time and network load are on the higher side for cloud based solutions. Recently, edge computing is gaining growing attention to over- come this by employing rule-based intelligence. However, requirements of rules do not scale well with the proliferation of things. At the same time, rules fail in uncertain events and only offer pre-assumed intelligence. To counter this, this paper proposes a novel idea of leveraging the belief-network with the edge computing to utilize as an IoT edge-controller the aim of which is to offer low-level intelligence for IoT applications. This low-level intelligence along with cloud-based intelligence form the distributed intelligence in the IoT realm. Furthermore, a learning approach similar to reinforcement learning has been proposed. The approach, i.e. enabling a Future IoT Controller (FITC) has been verified with a simu- lated SmartHome scenario which proves the feasibility of the low-level intelligence in terms of reducing rules domination, faster response time and prediction through learning experiences at the edge. Ó 2017 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). 1. Introduction Future Internet is expected to be driven by the prevalence of Internet of Things (IoT) where it is envisioned that anything can be connected [1]. The hype around IoT is that it is the next techno- logical revolution of the current world [2] where hundreds of bil- lions of things will be interconnected. IoT has started to shape into reality from its hype by and large due to recent advancements in ubiquitous technologies such as Radio Frequency Identification (RFID)/Near Field Communication (NFC), Wireless Personal Area Network (WPAN), high speed communication (4G/5G), Bluetooth Low Energy (BLE), etc. Advanced developments in the sensing and actuating technologies also contribute to the rise of the IoT popularity. This rise in connected things has already taken its number beyond current world’s population and expected to impact every aspect of human life. Currently, there are almost two con- nected things for every human. The ratio is expected only to accel- erate in the coming days. The challenge of collecting and sharing the context information (ConIn) from these connected things has been addressed in earlier research [3–8]. The challenge has been addressed by architecting IoT platforms via mostly middleware solutions. Each middleware solution addresses different IoT chal- lenges; for example, device management, context information col- lection and sharing, context-awareness, interoperability, etc. [4]. However, there is no single middleware solution or IoT platform that solves all these IoT challenges. An ideal IoT platform capable of providing solutions to all IoT aspects has not yet been designed [4]. Furthermore, most of the IoT platforms solutions are cloud cen- tric [3–5,8]; recently Cisco coined the term fog computing, i.e. edge computing closer to the actual devices [9]. Lately resource constrained devices such as SmartDevices and raspberry pi have enriched in computational capabilities and at the same time price has become more affordable. These devices have the potential to be exploited as IoT gateways and have already been demonstrated in earlier research [10,11]. Emergence of these devices paves the way for computing at the edge of http://dx.doi.org/10.1016/j.aci.2017.05.001 2210-8327/Ó 2017 The Authors. Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). ⇑ Corresponding author. E-mail addresses: hasibur@dsv.su.se (H. Rahman), rahim@dsv.su.se (R. Rahmani). Peer review under responsibility of King Saud University. Production and hosting by Elsevier Applied Computing and Informatics 14 (2018) 73–87 Contents lists available at ScienceDirect Applied Computing and Informatics journal homepage: www.sciencedirect.com