A Hybrid Deep Learning and Metaheuristic Model for Dynamic Load Balancing in Cloud Data Centers

Cloud computing environments face significant challenges in maintaining optimal performance due to dynamic workloads and heterogeneous resource configurations. Traditional load balancing algorithms often fail to adapt to real-time fluctuations, leading to suboptimal resource utilization, increased latency, and degraded performance. This paper presents a novel hybrid load balancing model that integrates Long Short-Term Memory (LSTM) networks with Ant Colony Optimization (ACO) and Throttle algorithms. The proposed approach leverages LSTM's predictive capabilities to forecast workload patterns, ACO's metaheuristic optimization for intelligent task scheduling, and Throttle mechanisms for dynamic resource allocation. Experimental evaluation using CloudSim-based simulation demonstrates that the hybrid model achieves a response time of 120 ms, throughput of 150 tasks/second, and resource utilization of 85%, significantly outperforming configurations lacking individual components. The LSTM model achieved a Mean Absolute Percentage Error of 2.17% and inference time of 0.7249 seconds, confirming its suitability for real-time applications. Ablation studies validate the synergistic contribution of each component, with the complete hybrid model consistently outperforming ablated versions across all performance metrics.

Authors

Institutions

Publication Details

Journal
Cureus Journal of Computer Science.
Published
2026-11-16
DOI
https://doi.org/10.7759/s44389-026-00370-x
Primary Topic
Cloud Computing and Resource Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Hybrid Deep Learning and Metaheuristic Model for Dynamic Load Balancing in Cloud Data Centers

Michael Adeniyi Ibiyomi
6 links
Cureus Journal of Computer Science.
Cloud Computing and Resource Management
article

A Hybrid Deep Learning and Metaheuristic Model for Dynamic Load Balancing in Cloud Data Centers

Michael Adeniyi Ibiyomi
article en

Abstract

Cloud computing environments face significant challenges in maintaining optimal performance due to dynamic workloads and heterogeneous resource configurations. Traditional load balancing algorithms often fail to adapt to real-time fluctuations, leading to suboptimal resource utilization, increased latency, and degraded performance. This paper presents a novel hybrid load balancing model that integrates Long Short-Term Memory (LSTM) networks with Ant Colony Optimization (ACO) and Throttle algorithms. The proposed approach leverages LSTM's predictive capabilities to forecast workload patterns, ACO's metaheuristic optimization for intelligent task scheduling, and Throttle mechanisms for dynamic resource allocation. Experimental evaluation using CloudSim-based simulation demonstrates that the hybrid model achieves a response time of 120 ms, throughput of 150 tasks/second, and resource utilization of 85%, significantly outperforming configurations lacking individual components. The LSTM model achieved a Mean Absolute Percentage Error of 2.17% and inference time of 0.7249 seconds, confirming its suitability for real-time applications. Ablation studies validate the synergistic contribution of each component, with the complete hybrid model consistently outperforming ablated versions across all performance metrics.

Cureus Journal of Computer Science.
The Federal Polytechnic, Ado-Ekiti (NG)
Industry, innovation and infrastructure
Cloud Computing and Resource Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon