ABSTRACT The increase in popularity and demand for cloud services has caused a huge growth of cloud data centers, and this has caused the challenge of energy management in data centers. Virtual Machine (VM) consolidation is a critical process aimed at optimizing resource utilization and minimizing energy usage. VM consolidation with the turnoff of underloaded hosts and reducing the load of overloaded hosts establishes a balance between energy consumption and SLA violations. In fact, the consolidation process includes three sub‐problems: determining overloaded and underloaded hosts, VM selection in overloaded hosts, and finding a new destination for VMs that will be migrated (VM placement). This paper introduces an entropy‐based approach to VM selection and placement to improve efficiency in cloud data centers. Entropy is a quantifiable characteristic often linked to disorder, randomness, or unpredictability. By leveraging entropy as a measure of workload distribution and uncertainty, the proposed method effectively predicts future resource demands, enabling informed decisions that enhance energy efficiency and reduce SLA violations. A key advantage of this approach is the significant reduction in the number of VM migrations, which decreases overhead and minimizes potential service disruptions. Experimental results demonstrate that our entropy‐based method outperforms the VM consolidation process in terms of energy consumption, SLA compliance, and system stability. The findings suggest that this approach offers a more sustainable and cost‐effective solution for managing cloud resources, contributing to the development of efficient and reliable cloud computing environments.

Summary Applications of intelligent systems installed in vehicles require substantial computational processing for various tasks. These intensive computations result in high energy consumption and power demands within vehicles. Computational offloading based on Vehicle‐to‐Vehicle (V2V) communication in vehicular fog computing (VFC) has been proposed as a promising solution to enhance energy efficiency in transportation applications. In this paper, the primary objective is addressing this concern by identifying the optimal nearby vehicle that minimizes energy consumption for the offloading and execution of computational tasks. Therefore, a decision‐making and intelligent task offloading mechanism based on queueing theory is proposed. By modeling the problem environment based on queueing theory and modeling the behavior of distributed tasks with discrete‐time Markov chain, the proposed solution can predict the future behavior of vehicles in selecting the most energy‐efficient processing node. Therefore, this paper investigates three energy decision parameters based on queueing theory extracted from the Markov model to enhance the performance of the proposed algorithm. Experimental results demonstrate that the computational energy parameter achieves the most significant improvement. The proposed algorithm outperforms previous methods, improving energy‐efficient system performance by 6.25% and 2.67%, and reducing delivery failure rate by 6.52% and 2.72%. It also decreases overall transportation system processing energy consumption by 0.05% for 100–500 vehicle arrival rates, resulting in an average total processing energy consumption of 0.48%.

Abstract In recent years, cloud computing has become more popular because of advancements in virtualization technology. By increasing the number of servers in cloud computing environment, cloud data centers have expanded and consumed much energy. Virtual machine consolidation is a solution for energy management in cloud environment. On the other hand, by increasing resource utilization in virtual machine consolidation, service level agreement assurance is difficult to obtain. Two main challenges in virtual machine consolidation are timely detection of overloaded servers and proper immigrant virtual machine selection from detected servers. In this paper, a new model is proposed based on MAPE‐k loop for autonomous virtual machine selection. The presented model uses a proposed ensemble prediction algorithm in the analysis phase. Also, in the planning phase, a new multi‐heuristics algorithm with flexible weights using learning automata is proposed. The effectiveness of the proposed model is evaluated by CloudSim simulator under real workload as compared with well‐known algorithms in this domain. The experimental results indicate that, the proposed approach has averagely improved the balance between service level agreement violations, energy and migration counts by 47.39% compared to other methods.

An effective workflow application scheduling on shared resources largely contributes to achieving a high performance in Utility Grids. Users share resources and these resources are autonomously managed in these environments. There is no explicit control on allocating resources to application-tasks on the part of users, the fact that results make users fail in optimizing the application make span and allocation cost. In the current paper, a Minimum First-fit Cost-Make span Trade-off (MinFCMT) heuristic algorithm is developed in order to effectively schedule an application in Utility Grids so that the application make span and allocation-cost can be minimized. To evaluate the MinFCMT heuristic algorithm, widespread simulation of the synthetic workflow is exploited. The results show that the MinFCMT algorithm is more effective than the present algorithms due to optimizing the application make span and allocation-cost in a very low runtime.