Clustering Approaches for Pragmatic Two‐Layer IoT Architecture

Abstract

Connecting all devices through Internet is now practical due to Internet of Things. IoT assures numerous applications in everyday life of common people, government bodies, business, and society as a whole. Collaboration among the devices in IoT to bring various applications in the real world is a challenging task. In this context, we introduce an application-based two-layer architectural framework for IoT which consists of sensing layer and IoT layer. For any real-time application, sensing devices play an important role. Both these layers are required for accomplishing IoT-based applications. The success of any IoT-based application relies on efficient communication and utilization of the devices and data acquired by the devices at both layers. The grouping of these devices helps to achieve the same, which leads to formation of cluster of devices at various levels. The clustering helps not only in collaboration but also in prolonging overall network lifetime. In this paper, we propose two clustering algorithms based on heuristic and graph, respectively. The proposed clustering approaches are evaluated on IoT platform using standard parameters and compared with different approaches reported in literature.

Experimental comparison of the diagnostic capabilities of classification and clustering algorithms for the QoS management in an autonomic IoT platform

“…In IoT, pattern recognition algorithms have been used in several works. This paper is interested in the application of the two main types of pattern recognition algorithms: classification [6][7][8][9][10][11][12][13][14][15], and clustering [16][17][18][19][20] algorithms. The survey in this section makes possible, on the one hand, to clear the scope of the current use of these algorithms and, on the other hand, to motivate the application of these algorithms to sustain of non-functional requirements, such as QoS in IoT platforms.…”

“…The second group of works is about clustering techniques applied in the context of IoT. Kumar et al [16] introduce an application-based two-layer architecture for IoT, which consists of a sensing layer and an IoT layer. Both layers are required for accomplishing IoTbased applications.…”

“…This parameter corresponds to the MAD calculated by the fuzzy Cauchy function presented in Eq. (16).…”

A Decentralized Latency-Aware Task Allocation and Group Formation Approach With Fault Tolerance for IoT Applications

“…H. Guo et al [25] proposed transparent computing based architecture for scalable and manageable IoT applications. Authors in [6] have proposed clustering approaches in both bottom to top and top to bottom ways depending on the need of an IoT application. All of these research works have used centralized methods for management of different resources like OS, application and data.…”

“…By distributing complex (compute-intensive) processing (e.g., speech recognition, object detection, planning navigation, machine learning) in multiple edge resources closer to IoT end devices might result in lower latency, and also a staggering cut down in overall network traffic can be achieved, as data will be restricted in local network rather than routing towards cloud in default mobile edge computing. Techniques for resource leveraging at the edge [5] or clustering solutions [6] to group IoT devices might solve the above problem to some extent, but they rely on master-slave architecture or involve hierarchal grouping of devices. One common property of current grouping or clustering methods is that they operate in a non-distributed and centralized manner, which can cause problems in heterogeneous edge nodes environment.…”