Workload Prediction in Cloud Data Centers Using Complex‐Valued Spatio‐Temporal Graph Convolutional Neural Network Optimized With Gazelle Optimization Algorithm

Transactions on Emerging Telecommunications Technologies, Год журнала: 2025, Номер 36(3)

Опубликована: Март 1, 2025

ABSTRACT Workload prediction is the necessary factor in cloud data center for maintaining elasticity and scalability of resources. However, accuracy workload very low, because redundancy, noise, low center. In this manuscript, Prediction Cloud Data Centers using Complex‐Valued Spatio‐Temporal Graph Convolutional Neural Network Optimized with Gazelle Optimization Algorithm (CVSTGCN‐WLP‐CDC) proposed. Initially, input collected from two standard datasets such as NASA Saskatchewan HTTP traces dataset. Then, preprocessing Multi‐Window Savitzky–Golay Filter (MWSGF) used to remove noise redundant data. The preprocessed fed CVSTGCN a dynamic environment. work, proposed Approach (GOA) enhance weight bias parameters. CVSTGCN‐WLP‐CDC technique executed efficacy based on structure evaluated several performances metrics accuracy, recall, precision, energy consumption correlation coefficient, sum index (SEI), root mean square error (RMSE), squared (MPE), percentage (PER). provides 23.32%, 28.53% 24.65% higher accuracy; 22.34%, 25.62%, 22.84% lower when comparing existing methods Artificial Intelligence augmented evolutionary approach espoused centres architecture (TCNN‐CDC‐WLP), Performance analysis machine learning centered techniques (PA‐BPNN‐CWPC), Machine effectual utilization centers (ARNN‐EU‐CDC) respectively.

Язык: Английский

A Modified Genetic-Based solution for Power-Aware Placement of Virtual Machines

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Июль 4, 2024

Cloud computing has developed as a ubiquitous technology for delivering services like storage, computing, etc. via the Internet. With rising demand by customers cloud computation and associated services, service providers are developing various approaches that enhance performance, reliability, availability of systems. uses virtualization to optimise resource usage minimise power utilisation in data centers (DC). Efficient virtual machine (VM) placement strategies crucial, especially when using advanced genetic techniques. This research paper introduces use meta-heuristic approach, named PowerGA, integration machines onto least number physical (PMs) DCs. PowerGA optimises VM deployment DCs energy Service Level Agreement (SLA) breaches, considering factors such migration, host shutdown, overload count, active machines. Extensive simulations real workload showed significant improvements over traditional PABFD, with achieving 25% reduction consumption (EC), 43% fewer migrations, 58% improvement SLA violations, 72% shutdowns ten days from PlanetLab. These results highlight PowerGA's effectiveness management enhancement, demonstrating benefits algorithm optimising efficiency.

Язык: Английский