A Review On Workload Characterization Methodology Using Supervised And Unsupervised Deep Learning

Aniket Dattatrey Deshmukh; N S Bagal

A Review On Workload Characterization Methodology Using Supervised And Unsupervised Deep Learning

Author(s)	Aniket Dattatrey Deshmukh, Dr. N S Bagal
Country	India
Abstract	Effective workload characterization and prediction are crucial for enhancing system performance, scalability, and resource usage in today's dynamic computing environments. In order to accomplish precise workload prediction and intelligent resource management, this project proposes a Workload Characterization Methodology utilizing CNN-LSTM that combines statistical analysis, clustering, deep learning, and optimization techniques. To make sure that only pertinent characteristics are taken into account, the procedure starts with data preparation and feature selection using Pearson Correlation. Fuzzy C-Means Clustering is then used to group the chosen features, successfully identifying comparable workload patterns. To improve prediction accuracy, a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) model is used to incorporate both temporal and spatial correlations in the workload data. In order to provide equitable workload distribution and effective resource use, the Hungarian Model is finally used for optimal job allocation. Applications in cloud computing, data centers, edge systems, and large-scale distributed environments can benefit from the suggested methodology's enhanced predictive capability, adaptability, and decision-making efficiency.
Keywords	CNN-LSTM , Supervised learning , deep learning
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-09

View / Download PDF File

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

A Review On Workload Characterization Methodology Using Supervised And Unsupervised Deep Learning

Share this