A Cognitive Management Framework for Empowering the Internet of Things

Abstract

Abstract. This work presents a Cognitive Management framework for empowering the Internet of Things (IoT). This framework has the ability to dynamically adapt its behaviour, through self-management functionality, taking into account information and knowledge (obtained through machine learning) on the situation (e.g., internal status and status of environment), as well as policies (designating objectives, constraints, rules, etc.). Cognitive technologies constitute a unique and efficient approach for addressing the technological heterogeneity of the IoT and obtaining situation awareness, reliability and efficiency. The paper also presents a first indicative implementation of the proposed framework, comprising real sensors and actuators. The preliminary results of this work demonstrate high potential towards self-reconfigurable IoT.

MIFaaS: A Mobile-IoT-Federation-as-a-Service Model for dynamic cooperation of IoT Cloud Providers

“…. , C l } on the set of players N and the preference relation defined in equation (6), an ICP i ∈ N decides to switch coalition (and consequently modifies the coalition structure), leaving its current coalition C Π (i) to join another different coalition C k ∈ Π\C Π (i) ∪ ∅ if and only if it prefers being part of the new coalition according to the preference relation, i.e., C k ∪ {i} ≻ i C Π (i). When a switch operation is applied by a player i, the history of the visited coalitions H(i) is updated so that also C Π (i) is included.…”

“…In the first analysis we consider a sample scenario where the number of ICPs in the system is set to 4 and each ICP has 3 devices. Each device is endowed with a minimum of 1 and a maximum of 3 resources, randomly selected among the six types of resources we considered, i.e., [1][2][3][4][5][6][7][8][9][10] MFLOPS for computation, MBytes of storage capacity, and embedded sensors of four possible types (e.g., humidity, temperature, pressure, movement). The number of task requests generated are reported in Table 2.…”

“…In the context of Mobile Cloud Computing (MCC) [3] [4] supporting task offloading and energy savings is the usual key objective. Instead, in the IoT domain [5] [6] the main goal is the provision of solutions that best exploit the huge amount of data and services offered by heterogeneous IoT devices.…”

Cognitive decision making in smart industry

“…Cognitive IoT have also been discussed by various authors in Refs. [1,14,15,18,45,50]. Different models are used by authors for decision making such as consensus model [27], agent based model [38], Bayesian decision making model [37], neural networks [40], game model [10], and many more [5,19,23].…”

The “Object-as-a-Service” paradigm

“…But the distance between the virtualization and the real Objects may have an impact in term of networks load, especially because of the number of connected objects involved. This network loads could be an issue for the constrained and unreliable networks IoT applications require (see for example IoT-6 european project [29] [33], Future Internet FI-Ware [1] [30], i-Core [13] or Actinium [18]). …”