Sustainable computing across datacenters: A review of enabling models and techniques

Computer Science Review, Journal Year: 2024, Volume and Issue: 52, P. 100620 - 100620

Published: Feb. 13, 2024

Language: Английский

---

Priority based job scheduling technique that utilizes gaps to increase the efficiency of job distribution in cloud computing

Sustainable Computing Informatics and Systems, Journal Year: 2023, Volume and Issue: 41, P. 100942 - 100942

Published: Nov. 30, 2023

Language: Английский

---

Multi-Objective Prioritized Task Scheduler Using Improved Asynchronous Advantage Actor Critic (a3c) Algorithm in Multi Cloud Environment

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 11354 - 11377

Published: Jan. 1, 2024

Task scheduling is a crucial challenge in cloud computing paradigm as variety of tasks with different runtime processing capacities generated from various heterogeneous devices are coming up to application console which effects system performance terms makespan, resource utilization, cost. Therefore, traditional algorithms may not adapt this efficiently. Many existing authors developed task schedulers by using metaheuristic approaches solve problem(TSP) get near optimal solutions but still TSP highly dynamic challenging scenario it NP hard problem. To tackle challenge, paper introduces multi objective prioritized scheduler improved asynchronous advantage actor critic(a3c) algorithm uses priorities based on length tasks, and VMs electricity unit cost environment. Scheduling process carried out two stages. In the first stage, all incoming VM calculated at manager level second Priorities fed (MOPTSA3C) generate decisions map effectively onto considering schedule cost, makespan available Extensive simulations conducted Cloudsim toolkit giving input trace fabricated data distributions real time worklogs HPC2N, NASA datasets scheduler. For evaluating efficacy proposed MOPTSA3C, compared against techniques i.e. DQN, A2C, MOABCQ. From results, evident that MOPTSA3C outperforms for reliability.

Language: Английский

---

Optimizing Task Scheduling and Resource Utilization in Cloud Environment: A Novel Approach Combining Pattern Search With Artificial Rabbit Optimization

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 67130 - 67148

Published: Jan. 1, 2024

The increasing demand for Cloud service with sudden resource requirements of Virtual Machines (VMs) different types and sizes may create an unbalanced state in the datacenters. In turn, it will lead to low utilization slow down server's performance. This research article proposes enhanced version Artificial Rabbit Optimization (ARO) called Improved based on Pattern Search (IARO-PS), where ARO has been utilized schedule dynamically independent requests (tasks) overcoming challenges discussed above a (PS) method hybridized address shortcomings provide better exploration-exploitation balance. initial step proposed approach is employ load balancing strategy by dividing workloads (user requests) across available VMs. next utilizes IARO-PS map onto optimal VMs scheduling process carry out diverse resources. A standard benchmark function (CEC2017) used assess technique's efficacy. comprehensive evaluation carried taking real-world dataset having specifications tasks CloudSim evaluate performance methodology. Additionally, simulation-based comparison various metaheuristic-based workload methods like Genetic Algorithm (GA), Bird Swarm (BSO), Modified Particle Q-learning (QMPSO), Multi-Objectives Grey Wolf Optimizer (MGWO). Based simulations, algorithm performed than previously mentioned algorithms, reducing makespan 10.45% 2.31% 4.35% (MGWO), 15.35% 4.17% 1.03% 1.44% 7.33% both homogeneous heterogeneous surroundings, respectively, improving 36.74% 14.31% 19.75% 45.23% (BSO) 12.17% 6.02% 9.10% 19.39% (BSO). Furthermore, statistical through Friedman's test Holm's also showcasing decrease increase VM utilization, which are outcomes simulated experimental study.

Language: Английский

---

Reinforcement learning based Secure edge enabled multi task scheduling model for internet of everything applications

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 20, 2025

The fast growth of the Internet Everything (IoE) has resulted in an exponential rise network data, increasing demand for distributed computing. Data collection and management with job scheduling using wireless sensor networks are considered essential requirements IoE environment; however, security issues over data on online platform energy consumption must be addressed. Secure Edge Enabled Multi-Task Scheduling (SEE-MTS) model been suggested to properly allocate jobs across machines while considering availability relevant copies. proposed approach leverages edge computing enhance efficiency applications, addressing growing need manage huge generated by devices. system ensures user protection through dynamic updates, multi-key search generation, encryption, verification result accuracy. A MTS mechanism is employed optimize usage, which allocates slots various processing tasks. Energy assessed tasks queues, preventing node overloading minimizing disruptions. Additionally, reinforcement learning techniques applied reduce overall task completion time minimal data. Efficiency have improved due reduced energy, delay, reaction, times. Results indicate that SEE-MTS achieves utilization 4 J, a delay 2s, reaction 4s, at 89%, level 96%. With computation 6s, offers security, reducing times, although real-world implementation may limited number devices incoming

Language: Английский

---

A Novel, Self-Adaptive, Multiclass Priority Algorithm with VM Clustering for Efficient Cloud Resource Allocation

Computers, Journal Year: 2025, Volume and Issue: 14(3), P. 81 - 81

Published: Feb. 24, 2025

Priority in task scheduling and resource allocation for cloud computing has attracted significant attention from the research community. However, traditional algorithms often lack ability to differentiate between tasks with varying levels of importance. This limitation presents a challenge when servers must handle diverse distinct priority classes strict quality service requirements. To address these challenges environments, particularly within infrastructure models, we propose novel, self-adaptive, multiclass algorithm VM clustering allocation. implements four-tiered prioritization system optimize key objectives, including makespan energy consumption, while simultaneously optimizing utilization, degree imbalance, waiting time. Additionally, load-balancing model based on technique. The proposed work was validated through multiple simulations using CloudSim simulator, comparing its performance against well-known algorithms. simulation results analysis demonstrate that effectively optimizes consumption. Specifically, our achieved percentage improvements ranging +0.97% +26.80% +3.68% +49.49% consumption also improving other metrics, throughput, load balancing. novel demonstrably enhances efficiency, complex scenarios tight deadlines priorities.

Language: Английский

---

An optimal three-tier prioritization-based multiflow scheduling in cloud-assisted smart healthcare

Journal of Network and Computer Applications, Journal Year: 2025, Volume and Issue: unknown, P. 104143 - 104143

Published: Feb. 1, 2025

Language: Английский

---

Data center multidimensional management strategy based on descending neighborhood DBSCAN algorithm in unsupervised learning

Journal of Industrial Information Integration, Journal Year: 2025, Volume and Issue: unknown, P. 100830 - 100830

Published: March 1, 2025

Language: Английский

---

Multi‐Criteria Optimization of Scientific Workflow Schedules for Improved Energy Efficiency in Cloud Infrastructures

Concurrency and Computation Practice and Experience, Journal Year: 2025, Volume and Issue: 37(9-11)

Published: April 9, 2025

ABSTRACT Rising global dependence on cloud services has become crucial for enterprises, aiming to guarantee continuous data accessibility while pursuing enhanced energy efficiency and minimized carbon emissions from centers. However, the persistent challenge of high‐energy consumption in these facilities necessitates a concentrated approach toward reduction. This paper introduces an innovative multi‐objective scheduling strategy scientific workflows, tailored heterogeneous computing environments. Our method employs hybrid genetic algorithm, incorporating Hill Climbing generate initial population chromosomes. Subsequently, algorithm optimizes task assignments most suitable virtual machines, utilizing meticulously designed fitness function evaluate each chromosome's suitability solving problem. Through extensive experimentation, we demonstrate that our proposed outperforms other techniques terms solution quality, contributing reduced consumption, processing duration, cost. We contend this holds substantial potential mitigating footprint associated with centers, offering sustainable environmentally conscious workflow scheduling.

Language: Английский

---

Parallel Enhanced Whale Optimization Algorithm for Independent Tasks Scheduling on Cloud Computing

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 23529 - 23548

Published: Jan. 1, 2024

Cloud computing has been imperative for systems worldwide since its inception. The researchers strive to leverage the efficient utilization of cloud resources execute workload quickly in addition providing better quality service. Among several challenges on cloud, task scheduling is one fundamental NP-hard problems. Meta-heuristic algorithms are extensively employed solve as a discrete optimization problem and therefore meta-heuristic have developed. However, they their own strengths weaknesses. Local optima, poor convergence, high execution time, scalability predominant issues among algorithms. In this paper, parallel enhanced whale algorithm proposed schedule independent tasks with heterogeneous resources. improves solution diversity avoids local optima using modified encircling maneuver an adaptive bubble net attacking mechanism. parallelization technique keeps time low despite internal complexity. minimizes makespan while improving resource throughput. It demonstrates effectiveness PEWOA against best performing (WOAmM) Multi-core Random Matrix Particle Swarm Optimization (MRMPSO). consistently produces results varying number GoCJ dataset, indicating scalability. experiments conducted CloudSim utilizing variety HCSP instances. Various statistical tests also evaluate significance results.

Language: Английский

---