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

Abstract

The IoT platforms must allow the communication between the Applications and Devices according to their non-functional requirements. One of the main non-functional requirements is the Quality of Service (QoS). In a previous work has been defined an Autonomic Internet of Things (IoT) platform for the QoS Management, based on the concept of autonomic cycle of data analysis tasks. In this platform have been defined two autonomic cycles, one based on a classification task that determines the current operational state to define the set of tasks to execute in the communication system to guarantee a given QoS. The other one is based on a clustering task that discovers the current operational state, and based on it, determines the set of tasks to be executed in the communication system. This paper analyzes the diagnostic capabilities of the system based on both approaches, using different metrics. For that, a real scenario has been considered, with simulations that have generated data to test both tasks. Each technique has different aspects to be considered for a correct QoS management in the context of IoT platforms. The classification technique can determine very well the learned operational states, but the clustering approach can carry out a more detailed description of the operational states. Additionally, due to the classification and clustering technique used, called LAMDA (Learning Algorithm for Multivariate Data Analysis), the paper analyzes the operational state profile determined by them, which is very useful in a diagnostic process. IntroductionThe classical components of an IoT ecosystem, according to the standards are [1][2]: Devices, Network, IoT platform, and Application. Devices are the responsible of the collection of the data, and in some case, the preprocessing of these data and the execution of specific tasks; the Applications exploit the advantage of a set of interconnected Devices in order to carry out actions in the environment; the Network allows the communication between the different components in the IoT platform, particularly, between the devices and applications; and finally, the IoT platform manages smart capabilities like the autonomy, security, among other things, and can support heterogeneous non-functional requirements of Applications and Devices. On the one hand, the IoT platforms are based on European Telecommunications Standards Institute (ETSI) SmartM2M and OneM2M [1][2] specifications, which define that an IoT platform consists mainly of two types of entities, IoT server(s) and gateway(s). These entities are implemented as Chain of Network Functions (NFs) that achieve a connection between applications and devices. Namely, NFs are processing functions, with defined functional behaviors and interfaces (e.g. a load balancing function applied on Internet protocol (IP) packets). On the other hand, these platforms are not able to sustain Quality of Service (QoS) to IoT missions critical Applications like remote surgery [34]. As per [34], QoS in IoT is one of the critical factors, which nee...

Smart Education: A Review and Future Research Directions

“…Many papers have taken advantage of this to make predictions about students' behavior or to develop security measures to detect network intrusions. For this reason, some papers used more specific methods in their data collection and analysis techniques: Decision Tree [14][15][16], Random Tree [17], Random Forest [15,17,18], Artificial Neural Network (ANN) [15,18], Convolution Neural Networks (CNNs) [12,19], Naïve Bayes [15,20,21], K-means Clustering [20,22], k-Nearest Neighbor (K-NN) [21,23] and others [24][25][26][27] including Bayesian Network, Graph-based Clustering, Local Binary Patterns Histograms and Multimedia and Agents based Question Answering System (MAQAS) (see Table 4).…”

An Autonomic Cycle of Data Analysis Tasks for the Supervision of HVAC Systems of Smart Building

“…The work brings data-based ACODAT concept from other fields and applies it to a multi-HVAC model, for the building HVAC management. The ACODAT concept was successfully proven in telecommunications [6], Education with smart classroom [7,8], but it is still unknown in HVAC management [1].…”

An Automatic Merge Technique to Improve the Clustering Quality Performed by LAMDA

“…The GADs define the cluster where the individual is assigned. LAMDA can work in supervised (classification) and unsupervised learning (clustering), which is an important advantage over other fuzzy techniques [20], [21], [61]. In unsupervised learning, the algorithm can create new clusters automatically.…”

“…The application of Eq. (11) in LAMDA, for = ̅ and = , (descriptor of the centroid of the cluster ), now redefines the as (see [21] for more details):…”

“…This parameter corresponds to the product of the and a penalty factor , computed for each cluster . To obtain , , two parameters are required: the first one is the distance of the individual to the center of each cluster k ( , ), which is calculated as [21]:…”