Route prediction using enhanced deep belief network-based optimization for maximizing network lifetime in MANET

Frequent topology changes in Mobile Ad Hoc Networks (MANETs) often result in unstable routing paths, increased energy consumption, and reduced network lifetime. To address these challenges, this study proposes a Route Prediction (RP) framework based on an Enhanced Deep Belief Network (EDBN) and the Red-billed Blue Magpie Optimizer (RBMO). Initially, residual node energy, mobility pattern, link quality, and hop count are extracted and normalized as routing features. The EDBN predicts the expected lifespan of candidate routes, whereas the RBMO algorithm selects the optimal routing path using a multi-objective fitness function that maximizes route stability and network lifetime while minimizing routing overhead and energy consumption. The framework was implemented in MATLAB and evaluated under MANET simulation settings comprising network sizes ranging from 10 to 100 mobile nodes deployed over a 1000 × 1000 m² area using the Random Waypoint mobility model, node speeds of 1–20 m/s, IEEE 802.11 DCF, CBR traffic, a 250 m transmission range, and 30 independent simulation runs. Route prediction accuracy is measured as the percentage of candidate routes whose predicted lifetime correctly matches the observed stable route lifetime during simulation. Experimental comparisons with CChOA-DQN, QSA-TPSN, SCGC-DONN, and HO-FHOS demonstrate that the proposed EDBN–RBMO framework achieves the highest route prediction accuracy together with improved packet delivery ratio, network lifetime, throughput, lower end-to-end delay, and reduced energy consumption. These results demonstrate the effectiveness of integrating predictive route lifetime estimation with metaheuristic optimization for reliable and energy-efficient routing in dynamic MANET environments.

Authors

Institutions

Publication Details

Journal
Discover Computing
Published
2026-11-18
DOI
https://doi.org/10.1007/s10791-026-10732-7
Primary Topic
Mobile Ad Hoc Networks
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Route prediction using enhanced deep belief network-based optimization for maximizing network lifetime in MANET

K. C. Rajheshwari, T. Ganesan, K. Sivakumar, B. Yuvaraj
2 links
Discover Computing
Mobile Ad Hoc Networks
article

Route prediction using enhanced deep belief network-based optimization for maximizing network lifetime in MANET

K. C. Rajheshwari, T. Ganesan, K. Sivakumar, B. Yuvaraj
article en

Abstract

Frequent topology changes in Mobile Ad Hoc Networks (MANETs) often result in unstable routing paths, increased energy consumption, and reduced network lifetime. To address these challenges, this study proposes a Route Prediction (RP) framework based on an Enhanced Deep Belief Network (EDBN) and the Red-billed Blue Magpie Optimizer (RBMO). Initially, residual node energy, mobility pattern, link quality, and hop count are extracted and normalized as routing features. The EDBN predicts the expected lifespan of candidate routes, whereas the RBMO algorithm selects the optimal routing path using a multi-objective fitness function that maximizes route stability and network lifetime while minimizing routing overhead and energy consumption. The framework was implemented in MATLAB and evaluated under MANET simulation settings comprising network sizes ranging from 10 to 100 mobile nodes deployed over a 1000 × 1000 m² area using the Random Waypoint mobility model, node speeds of 1–20 m/s, IEEE 802.11 DCF, CBR traffic, a 250 m transmission range, and 30 independent simulation runs. Route prediction accuracy is measured as the percentage of candidate routes whose predicted lifetime correctly matches the observed stable route lifetime during simulation. Experimental comparisons with CChOA-DQN, QSA-TPSN, SCGC-DONN, and HO-FHOS demonstrate that the proposed EDBN–RBMO framework achieves the highest route prediction accuracy together with improved packet delivery ratio, network lifetime, throughput, lower end-to-end delay, and reduced energy consumption. These results demonstrate the effectiveness of integrating predictive route lifetime estimation with metaheuristic optimization for reliable and energy-efficient routing in dynamic MANET environments.

Discover ComputingVol. 29(1)
GS Engineering (United States) (US), KPR Institute of Engineering and Technology (IN), Sona College of Technology (IN)
Industry, innovation and infrastructure
Mobile Ad Hoc Networks
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