The Internet of Things (IoT) has emerged with an ultimate goal of automating human life by providing its services. This incredible technology has a huge potential by which it can make human life simpler and easier. To increase the popularity of any type of services, first, their quality metrics need to be defined clearly. In IoT also, Quality of Service (QoS) metrics are needed to be defined first then only user will be able to understand and express their requirement using these metrics. This work is a step in this direction. This work identifies and describes various QoS metrics of IoT keeping the fact in mind that Computing, Communication and Things are three pillars of IoT. This work helps IoT providers to describe their services, users to describe their needs and researchers and professionals to develop the models in IoT considering the importance of QoS metrics.

Quality of Service (QoS) in Internet of Things

The dynamic resource requirement of applications has forced a large number of business organizations to join the cloud market and provide cloud services. It has posed a challenge for cloud users to select the best service providers and to minimize losses occurring due to its improper selection. This paper aims to propose a robust rank reversal technique for order of preference by similarity to ideal solution (TOPSIS) method based on Gaussian distribution and used to develop a cloud service selection framework. The proposed framework ranks cloud services based on the quality of services provided by cloud service providers and cloud user’s priority. A case study is performed on a real dataset obtained from CloudHarmony to show the effectiveness and correctness of the proposed framework. The results obtained demonstrate that the proposed framework ranks cloud services similar to TOPSIS-based frameworks. A sensitivity analysis has also been performed to check its robustness in six different cases causing rank reversal and found that the proposed framework is robust to handle rank reversal phenomenon in all the scenarios in comparison with other studies available in the literature.

G-TOPSIS: a cloud service selection framework using Gaussian TOPSIS for rank reversal problem

Type-aware virtual machine management for energy efficient cloud data centers

Particle swarm optimization algorithm (PSO) has been optimized from various aspects since it was proposed. Optimization of PSO can be realized by optimizing its iterative process or the initial parameters and heuristic methods have been combined with the initial PSO algorithm to improve its performance. In this paper, we introduce the Simplicial Algorithm (SA) of fixed point theory into the optimization of PSO and proposed a FP-PSO (Fixed-point PSO) improved algorithm. In FP-PSO algorithm, the optimization of target function is converted into the problem of solving a fixed point equation set, and the solution set obtained by Simplicial Algorithm (SA) of fixed point theory is used as the initial population of PSO algorithm, then the remaining parameters can be obtained accordingly with classical PSO algorithm. Since the fixed point method has sound mathematical properties, the initial population obtained with FP-PSO include nearly all the approximate local extremes which maintain the diversity of population and can optimize the flight direction of particles, and shows their advantages on setting other initial parameters. We make an experimental study with five commonly used testing functions from UCI (University of California Irvine) which include two single-peak functions and three multi-peak functions. The results indicate that the convergence accuracy, stability, and robustness of FP-PSO algorithm are significantly superior to existing improve strategies which also optimize PSO algorithm by optimizing initial population, especially when dealing with complex situations. In addition, we nest the FP-PSO algorithm with four classical improved PSO algorithms that improve PSO by optimizing iterative processes, and carry out contrast experiments on three multi-peak functions under different conditions (rotating or non-rotating). The experimental results show that the performance of the improved algorithm using nested strategy are also significantly enhanced compared with these original algorithms.

Optimized PSO algorithm based on the simplicial algorithm of fixed point theory

A multi‐agent system based for solving high‐dimensional optimization problems: A case study on email spam detection

The growing popularity of cloud services has attracted large number of business organizations to enter into the cloud market. The varied availability of cloud service providers, for various services, leaves the cloud customers into skepticism. Service measurement index (SMI) framework, which is based on the analytic hierarchical process, is developed for the ranking of cloud services. As there are multiple dependencies among the criteria for the selection of cloud service provider, analytic hierarchical process formulation is not efficient. In the proposed work, analytic network process that captures the cloud service‐provider selection problem in a more realistic way is integrated in the ranking component of SMI framework. In this method, interactions among the criteria are used for the ranking of the cloud services. Few new criterions are also added into the existing SMI framework to make the framework more effective. A case study is conducted to analyze the proposed technique for the cloud provider selection.

Integration of analytic network process with service measurement index framework for cloud service provider selection

The ease and affordability offered by the cloud computing has attracted large number of customers towards it. Cloud service providers offer its services, to the cloud customers, usually in form of Virtual Machines (VMs). With the growth in the number of customers, cloud data centers encounter overwhelming number of VM requests. These requests need to be mapped on the real cloud hardware and therefore, VM placement has been an important research area in the cloud research community. Virtual machine placement, being an NP hard problem, is modelled as an optimization problem with the objective to optimize resource wastage. Dragonfly Algorithm (DA), a nature inspired technique, originates from static and dynamic swarming behavior of dragonfly and is well suited to solve VM placement problem. Therefore, in the proposed work, a modified dragonfly algorithm is applied for VM placement for better resource utilization at cloud data centers. The performance of the proposed model is analyzed through simulation and comparative study. Observations, obtained from the experiments, exhibit the superiority of the proposed model in solving VM placement problem.

Modified Dragonfly Algorithm for Optimal Virtual Machine Placement in Cloud Computing

Energy Efficient VM Placement for Effective Resource Utilization using Modified Binary PSO

A model for virtual network embedding using Artificial Bee Colony

Cloud resources are increasing enormously with the growth in cloud technology. Allocating the resources is a cumbersome job as multiple criteria are involved. These criteria most often are dependent on each other. Analytic Network Process is well suited to solve such problems as it caters to dependent criteria that often give the feedback. The work proposes a task allocation model using Analytic Network Process for cloud resources. The model has been simulated and quite good results are obtained.

Atul Tripathi

Papers

Integration of analytic network process with service measurement index framework for cloud service provider selection

Modified Dragonfly Algorithm for Optimal Virtual Machine Placement in Cloud Computing

Energy Efficient VM Placement for Effective Resource Utilization using Modified Binary PSO

A model for virtual network embedding using Artificial Bee Colony

Task allocation on cloud resources using analytic network process