Dynamic Resource Allocation Using Improved Firefly Optimization Algorithm in Cloud Environment

Applied Artificial Intelligence, Journal Year: 2022, Volume and Issue: 36(1)

Published: March 24, 2022

Today, cloud computing has provided a suitable platform to meet the needs of users. One most important challenges facing is Dynamic Resource Allocation (DSA), which in NP-Hard class. goals DSA utilization resources efficiently and maximize productivity. In this paper, an improved Firefly algorithm based on load balancing optimization introduced solve problem called IFA-DSA. addition workloads between existing virtual machines, IFA-DSA also reduces completion time by selecting appropriate objectives fitness function. The best sequence tasks for resource allocation formulated as multi-objective problem. intended are balancing, time, average runtime, migration rate. order improve initial population creation firefly algorithm, heuristic method used instead random approach. method, created priority tasks, where each task determined pay you use model fuzzy results experiments show superiority proposed makespan criterion over ICFA 3%.

Language: Английский

---

A novel controller placement algorithm based on network portioning concept and a hybrid discrete optimization algorithm for multi-controller software-defined networks

Cluster Computing, Journal Year: 2021, Volume and Issue: 24(3), P. 2511 - 2544

Published: April 11, 2021

Language: Английский

---

Bio-inspired computation for big data fusion, storage, processing, learning and visualization: state of the art and future directions

Neural Computing and Applications, Journal Year: 2021, Volume and Issue: unknown

Published: Aug. 3, 2021

Language: Английский

---

A range‐free localization algorithm for IoT networks

International Journal of Intelligent Systems, Journal Year: 2021, Volume and Issue: 37(12), P. 10336 - 10379

Published: June 14, 2021

Internet of things (IoT) is a ubiquitous network that helps the system to monitor and organize world through processing, collecting, analyzing data produced by IoT objects. The accurate localization objects indispensable for most applications, especially healthcare monitoring. Utilizing GPS as positioning not cost-efficient does apply some environments (e.g., deep forests, oceans, inside buildings, etc.). Hereupon, copious position estimation approaches are developed in literature. Among range-free approaches, distance vector-Hop (DV-Hop) widely used algorithm due its straightforward applicability can estimate unknown far-off anchors. Due low accuracy, various techniques were proposed increase accuracy basic DV-Hop. In recent approach, meta-heuristic algorithms used, results which promising. present paper, Tunicate Swarm Algorithm Harris hawk optimization initially hybridized. Afterthought, resulting hybrid was enhanced appending new phase. Then, intermingled with DV-Hop algorithm. first set experiments, evaluated on 50 test functions using average, SD, box plot, p-value criteria. second part, algorithm's efficiency investigated twenty-eight different manners node error, average error variance metrics. effectiveness contributions evident from experimental results.

Language: Английский

---

A hierarchical distributed trusted location service achieving location k-anonymity against the global observer

Computer Networks, Journal Year: 2024, Volume and Issue: 243, P. 110301 - 110301

Published: March 1, 2024

As widely known in the literature, location-based services can seriously threaten users' privacy. Privacy-aware be obtained by protecting user's identity, so that queries cannot linked with users. A way to do this is place a trusted third party, called Location Trusted Service, between user and service provider, role of mediating coming from users proxying them provider. Before query, Service builds cloaking area includes sufficient number such it represent an anonymity set. This way, identity protected against untrusted Unfortunately, wide-area scenarios, centralized location-trusted might serious threat security privacy because represents single point failure manages very critical massive information. Moreover, protection also global adversary capable monitor whole traffic, would result excessive amount cover traffic network (being necessary model). To overcome above limitations we propose hierarchical whose implementation benefits edge–cloud paradigm. In our proposal, territory organized zones possibly managed different autonomous organizations. Organizations manage higher are involved when lower-level organizations not able satisfy requests only lowest-level exact location data, while ones operate on aggregate values, risk associated solution drastically reduced. leveraging system, better confined edge network, making observer feasible. nice feature method parametric respect any existing construction technique. However, as method, for non-local queries, operates certain degree approximation introduced. validate conducted experimental campaign real-life map applying top well-known technique Casper. The results turned out positive. For wide range sizes set, (expressed metric effectiveness) less than 10%. On other hand, concerning performance, have observed improvement latency throughput ranging 20% 170% (depending size set). highest density distribution, achieve 66% saving overall (non-local) compared approach.

Language: Английский

---

A novel approach for energy consumption management in cloud centers based on adaptive fuzzy neural systems

Cluster Computing, Journal Year: 2024, Volume and Issue: 27(10), P. 14515 - 14538

Published: July 21, 2024

Language: Английский

---

A novel virtual machine placement algorithm based on grey wolf optimization

Journal of Cloud Computing Advances Systems and Applications, Journal Year: 2025, Volume and Issue: 14(1)

Published: Feb. 13, 2025

Language: Английский

---

A discrete chaotic multi-objective SCA-ALO optimization algorithm for an optimal virtual machine placement in cloud data center

Journal of Ambient Intelligence and Humanized Computing, Journal Year: 2020, Volume and Issue: 12(10), P. 9323 - 9339

Published: Nov. 11, 2020

Language: Английский

---

Intelligent SLA-Aware VM Allocation and Energy Minimization Approach with EPO Algorithm for Cloud Computing Environment

Mathematical Problems in Engineering, Journal Year: 2021, Volume and Issue: 2021, P. 1 - 13

Published: May 29, 2021

Cloud computing is the most prominent established framework; it offers access to resources and services based on large-scale distributed processing. An intensive management system required for cloud environment, should gather information about all phases of task processing ensuring fair resource provisioning through levels Quality Service (QoS). Virtual machine allocation a major issue in environment that contributes energy consumption asset utilization computing. Subsequently, this paper, multiobjective Emperor Penguin Optimization (EPO) algorithm proposed allocate virtual machines with power heterogeneous environment. The method analyzed make suitable data center Binary Gravity Search Algorithm (BGSA), Ant Colony (ACO), Particle Swarm (PSO). To compare other strategies, EPO energy-efficient there are significant differences. results have been evaluated JAVA simulation platform. exploratory outcome presents EPO-based very effective limiting consumption, SLA violation (SLAV), enlarging QoS requirements giving capable service.

Language: Английский

---

An efficient host overload detection algorithm for cloud data center based on exponential weighted moving average

International Journal of Communication Systems, Journal Year: 2021, Volume and Issue: 34(4)

Published: Jan. 10, 2021

Summary The major aim of data center (DC) is to optimize the three parameters, viz., energy consumption, resource utilization, and quality service (QoS). Our objective balance these parameters by managing virtual machine (VM) efficiently. Therefore, this paper presents a holistic view VM consolidation explains its constituent subprocesses: (i) host overload detection, (ii) selection for migration from overloaded host, (iii) placement provisioning selected VMs on new set hosts. Later, attempts mentioned above proposing detection algorithm based exponential weighted moving average (EWMA) variants. performance proposed EWMA compared with state‐of‐the‐art algorithms local regression, median absolute deviation, interquartile range. efficacy evaluated in combination four different existing policies: minimum time, maximum correlation, (iv) random selection. evaluation metrics comprise count hosts representing level agreement (SLA) violations describing QoS, execution time. Simulation experiments are carried out CloudSim simulator using PlanetLab real cloud trace as workload. consumes 18.33% less energy, causes 47.81% migration, makes 9.91% SLA violation, takes 43.44% average‐time entire workload algorithms.

Language: Английский

---