For task-scheduling problems in cloud computing, a multi-objective optimization method is proposed here. First, with an aim toward the biodiversity of resources and tasks in cloud computing. This paper propose a resource cost model that defines the demand of tasks on resources with more details. A multi-objective optimization scheduling method has been proposed based on this resource cost model. This method considers the makespan, wall clock time , execution time and the costs as constraints of the optimization problem. This paper proposed a multi-objective improved genetic algorithm (MOIGA) to address multi-objective task scheduling problems. The experiment results showed that the MOIGA algorithm minimizes makespan, wall clock time, execution time and cost when compared with First Come First Serve (FCFS), Round Robin (RR) and Shortest Job First (SJF).

No abstract

The proliferation of internet-connected devices has led to the accumulation of vast volumes of data, known as “big data.” While cloud computing has been effective in managing and processing this data, it falls short in meeting the demands of real-time, low-latency applications and network constraints. To address these limitations, a new computing paradigm called “fog computing” has emerged. Fog computing aims to enhance speed, adaptability, throughput, cryptography, and confidentiality by bringing computation, connection, and memory closer to edge devices and end-users. This chapter provides an overview of the network infrastructure, key technologies, applications, challenges, and unresolved issues associated with fog computing.

The internet of things (IoT) has revolutionized various aspects of human life, such as smart cities, home automation, and energy efficiency. However, fully realizing the potential of IoT necessitates overcoming significant challenges. This article provides a comprehensive evaluation of IoT from both technological and societal perspectives, delving into its architecture, applications, and critical difficulties. It highlights the contributions of different IoT components and emphasizes the value of IoT and data analytics. The findings contribute to a better understanding of IoT applications and challenges, benefiting both consumers and researchers in the field.

Cloud data centers (CDC) have become an increasingly critical issue because of their large-scale deployment, which has resulted in increased energy consumption (EC) and SLA. The SLA and EC can be greatly reduced by using an efficient virtual machine consolidation (VMC) approach. This study presents a multi-objective adaptive upper threshold (UTh) technique for identifying overloaded hosts. The dynamic virtual machine consolidation (DVMC) is then obtained by combining a modified overloaded host detection technique with a different VM selection method (i.e., minimum migration time (Mmt) and minimum utilization (Mu)). The simulation results indicate that the modified Interquartile range (Iqr) overloaded host detection algorithm outperforms the existing overloaded host detection algorithms (i.e., InterQuartile range (Iqr), local regression (Lr), and dynamic voltage frequency scale (DVFS) algorithms) in terms of EC, SLA, and the number of virtual machine (VM) migrations.