As an implication of rapid growth in Internet-of-Things (IoT) data, current focus has shifted towards utilizing and analysing the data in order to make sense of the data. The aim of which is to make instantaneous, automated, and informed decisions that will drive the future IoT. This corresponds to extracting and applying knowledge from IoT data which brings both a substantial challenge and high value. Context plays an important role in reaping value from data, and is capable of countering the IoT data challenges. The management of heterogeneous contextualized data is infeasible and insufficient with the existing solutions which mandates new solutions. Research until now has mostly concentrated on providing cloud-based IoT solutions; among other issues, this promotes real-time and faster decision-making issues. In view of this, this dissertation undertakes a study of a context-based approach entitled Distributed intelligence-assisted Autonomic Context Information Management (DACIM), the purpose of which is to efficiently (i) utilize and (ii) analyse IoT data.

To address the challenges and solutions with respect to enabling DACIM, the dissertation starts with proposing a logical-clustering approach for proper IoT data utilization. The environment that the number of Things immerse changes rapidly and becomes dynamic. To this end, self-organization has been supported by proposing self-* algorithms that resulted in 10 organized Things per second and high accuracy rate for Things joining. IoT contextualized data further requires scalable dissemination which has been addressed by a Publish/Subscribe model, and it has been shown that high publication rate and faster subscription matching are realisable. The dissertation ends with the proposal of a new approach which assists distribution of intelligence with regard to analysing context information to alleviate intelligence of things. The approach allows to bring few of the application of knowledge from the cloud to the edge; where edge based solution has been facilitated with intelligence that enables faster responses and reduced dependency on the rules by leveraging artificial intelligence techniques. To infer knowledge for different IoT applications closer to the Things, a multi-modal reasoner has been proposed which demonstrates faster response. The evaluations of the designed and developed DACIM gives promising results, which are distributed over seven publications; from this, it can be concluded that it is feasible to realize a distributed intelligence-assisted context-based approach that contribute towards autonomic context information management in the ever-expanding IoT realm.

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 overcome 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 simulated 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.

Hundreds of billions of things are expected to be integrated for heterogeneous Internet-of-Things (IoT) applications, which promises to drive the Future Internet. This variant IoT data mandates intelligent solutions to make sense of current data in real-time closer to the data origin. Clustering physically distributed data would enable efficient utilization where finding similarity becomes the central issue. To counter this, Jaro-Winkler and Jaccard-like algorithm have been proposed and extended to a distributed protocol to enable distributed clustering at the edge. Performance study, on a scalable IoT platform and an edge device, shows feasibility and effectiveness of the approach with respect to efficiency and applicability.

Internet-of-Things (IoT) promises to impact every aspect of our daily life by connecting and automating everyday objects which bring the notion of SmartLiving. While it is certain that the trend will grow at a rapid speed, at the same time, challenge to alleviate intelligence of things by reaping value from the data requires to be addressed. The intelligence further cannot depend only on the existing cloud-based solutions which edge computing is expected to mitigate by integrating distributed intelligence. An IoT application necessitates applying knowledge with low latency. However, to comply with the vision of autonomic IoT and real-time intelligence, extracting and applying knowledge are necessitated for which this chapter proposes to exploit mobile edge computing (MEC) to further assist distributed intelligence. Therefore, the problem that this chapter addresses is feasibility investigation of MEC to provide intelligence by reasoning contextualised data and, thereby, the role of MEC in distributed intelligence.

Future Internet is expected to be driven by prevalence of the Internet of Things (IoT). This prevalence of IoT promises to impact every aspect of human life in the foreseeable future where computing paradigm would witness huge influx of IoT data. Context is gaining growing attention to make sense of the data and it is envisaged that context-aware computing would act as an indispensable enabler for IoT. Contextualizing the collected IoT data enables to reap value from the data and to harvest the knowledge. Reasoning the contextualized data, that is, context information is imperative to the vision of harvesting knowledge. Edge computing is also expected to play a vital role in IoT to reduce dependency on cloud based solution, to achieve faster response, and to provide intelligence closer to the IoT things. The combination of context-awareness and edge solution would be inseparable in the future IoT. Furthermore, IoT vision comprises of different IoT applications controlled by a capable controller at the edge, an edge controller necessitates to counter the challenge of providing knowledge for each of the IoT applications. Therefore, such a controller requires to offer different context-aware reasoning to alleviate the intelligence-of-things. In view of this, this paper proposes a multi-modal context-aware reasoner the aim of which is to provide knowledge at the edge for each IoT application. The context-aware reasoning has been verified with rules-based and Bayesian reasoning for three IoT applications and initial results suggest that it is promising to realize such multimodal reasoning at the edge with low latency.

The Internet of Things (IoT) paradigm has so far been investigating into designing and developing protocols and architectures to provide connectivity anytime and anywhere for anything. IoT is currently fast forwarding towards embracing a paradigm shift namely Internet of Everything (IoE) where making intelligent decisions and providing services remains a challenge. Context plays an integral role in reasoning the collected data and to provide context-aware services and is gaining growing attention in the IoT paradigm. To this end, a Context-Aware reasoNer (CAN) has been proposed and designed in this chapter. The proposed CAN is a generic enabler and is designed to provide services based on context reasoning. Discovering and filtering entities, i.e. entity configuration, become pivotal in analysing context reasoning to provide right services to right context entities in right time. This chapter leverages the concept of entity configuration and CAN towards enabling an IoT controller. The chapter further demonstrates use cases and future research directions towards generic CAN development and facilitating context-aware services to IoE.

The popular concept of SmartHome means that the appliances such as lighting, heating and door locks are controllable remotely through for example remote controls or mobile phones. The concept is becoming more and more realizable due to recent advancements in Internet-enabled technologies. SmartHomes can become even more intelligent and automated by exploiting such intelligent and affordable Internet-enabled technologies. However, this necessitates a context-aware system that provides services to respond to the context changes to enable such SmartHome automation at the edge of today’s context-centric networks. To this end, this paper designs and develops a context-aware reasoning service for home automation which provides a novel way to connect SmartHomes through the use of a distributed context exchange network overlay. It enables mobility service application to communicate with and control SmartHomes remotely.

Internet of Things (IoT) is on the verge of experiencing a paradigm shift, the focus of which is the integration of people, services, context information, and things in the Connected Society, thus enabling Internet of Everything (IoE). Hundreds of billions of things will be connected to IoT/IoE by 2020. This massive immersion of things paves the way for sensing and analysing anything, anytime and anywhere. This everywhere computing coupled with Internet or web-enabled services have allowed access to a vast amount of distributed context information from heterogeneous sources. This enormous amount of context information will remain under-utilized if not properly managed. Therefore, this thesis proposes a new approach of logical-clustering as opposed to physical clustering aimed at enabling efficient context information management.

However, applying this new approach requires many research challenges to be met. By adhering to a design science research method, this thesis addresses these challenges and proposes solutions to them. The thesis first outlines the architecture for realizing logical-clustering topology for which a two-tier hierarchical-distributed hash table (DHT) based system architecture and a Software Defined Networking (SDN)-like approach are utilized whereby the clustering identifications are managed on the top-level overlay (as context storage) and heterogeneous context information sources are controlled via the bottom level. The feasibility of the architecture has been proven with an ns-3 simulation tool. The next challenge is to enable scalable clustering identification dissemination, for which a distributed Publish/Subscribe (PubSub) model is developed. The massive number of immersed nodes further necessitates a dynamic self-organized system. The thesis concludes by proposing new algorithms with regard to autonomic management of IoT to bring about the self-organization. These algorithms enable to structure the logical-clustering topology in an organized way with minimal intervention from outside sources and further ensure that it evolves correctly. A distributed IoT context information-sharing platform, MediaSense, is employed and extended to prove the feasibility of the dynamic PubSub model and the correctness of self-organized algorithms and to utilize them as context storage. Promising results have provided a high number of PubSub messages per second and fast subscription matching. Self-organization further enabled logical-clustering to evolve correctly and provided results on a par with the existing MediaSense for entity joining and high discovery rates for non-concurrent entity joining.

The increase in context information requires its proper management. Being able to cluster (i.e. filter) heterogeneous context information based on context similarity can help to avoid under-utilization of resources. This thesis presents an accumulation of work which can be comprehended as a step towards realizing the vision of logical-clustering topology.

One of the challenges for Autonomic Management in Future Internet is to bring about self-organization in a rapidly changing environment and enable participating nodes to be aware and respond to changes. The massive number of participating nodes in Internet-of-Things calls for a new approach in regard of Autonomic Management with dynamic self-organization and enabling awareness to context information changes in the nodes themselves. To this end, we present new algorithms to enable self-organization with logical-clustering, the goal of which is to ensure that logical-clustering evolves correctly in the dynamic environment. The focus of these algorithms is to structure logical-clustering topology in an organized way with minimal intervention from outside sources. The correctness of the proposed algorithm is demonstrated on a scalable IoT platform, MediaSense. Our algorithms sanction 10 nodes to organize themselves per second and high accuracy of nodes discovery. Finally, we outline future research challenges towards autonomic management of IoT.

Crowdsourcing was initially devised as a method for solving problems through soliciting contributions from a large online community. Crowdsourcing is facing new challenges to handle the increase of information in real-time from a vast number of sources in Internet-of-Things (IoT) scenarios. Thus we seek to leverage the power of social web, smart-devices, sensors, etc., fusing these heterogeneous sources into distributed context information in order to enable novel crowdsourcing scenarios. This mandates research in efficient management of heterogeneous and distributed context information through logical-clustering. Logical-clustering can efficiently filter out similar context information obtained from distributed sources based on context similarity. However, the efficiency of logical-clustering is challenged by the distribution of context information in crowdsourcing scenarios. Publish/Subscribe mechanism can counter this challenge. To this end, we propose a scalable publish/subscribe model, MediaSense, which is based on p2p technologies. This paper presents our approach to a scalable logical-clustering concept. The evaluation of our approach applied to MediaSense can achieve a rate of approximately 3530 messages/sec for publish/subscribe events. Moreover, this approach further achieves 99% increase for subscription matching and 163% improvement in memory requirements in comparison with other approaches.