INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue VII, July 2025
www.ijltemas.in Page 704
Intelligent Route Adaptation in Manets Using AI Techniques for
Scalable Network Performance
Sachin Chaudhary, Dr. Lalit Johari
School of Computer Science and Applications, IFTM University, Moradabad U.P India
DOI: https://doi.org/10.51583/IJLTEMAS.2025.1407000084
Abstract—Mobile Ad Hoc Networks (MANETs) are prone to frequent topology changes and scalability issues due to their
decentralized and mobile nature. As network size and node mobility increase, traditional routing protocols become inefficient,
leading to degraded network performance. This paper introduces a novel AI-driven approach to route optimization that enables
MANETs to self-adjust to dynamic conditions. The proposed method leverages machine learning algorithms to analyze real-time
mobility patterns and link quality, allowing for predictive route selection and rapid reconfiguration. By dynamically adapting to
varying network states, the system significantly enhances scalability, reduces latency, and improves packet delivery.
Experimental results demonstrate that the AI-based model consistently outperforms conventional routing protocols under diverse
network scenarios, making it a promising solution for future mobile and mission-critical applications.
Keywords—Dynamic Routing, Machine Learning, Network Scalability, Mobility Prediction, Adaptive Protocols, Intelligent
Routing, Real-Time Optimization, Wireless Communication.
I. Introduction
Mobile Ad Hoc Networks (MANETs) represent a class of self-configuring wireless networks composed of mobile nodes that
communicate over dynamically changing topologies without relying on any pre-existing infrastructure. This inherent flexibility
makes MANETs an ideal solution for applications in military communications, disaster recovery, vehicular networks, and remote
sensing. However, the very features that make MANETs appealing—namely decentralization, mobility, and dynamic topology—
also introduce considerable challenges, particularly in the domain of routing. As the size of the network grows and node mobility
becomes unpredictable, routing protocols must efficiently adapt to these variations while maintaining network performance. The
need for robust, scalable, and adaptive routing mechanisms in MANETs has become more critical than ever. Conventional
MANET routing protocols, such as AODV (Ad hoc On-Demand Distance Vector), DSR (Dynamic Source Routing), and OLSR
(Optimized Link State Routing), have been widely adopted due to their simplicity and effectiveness in relatively stable or
moderately dynamic environments. These protocols typically rely on static metrics like hop count or fixed periodic updates to
establish and maintain routes. While these approaches perform adequately under certain conditions, they often falter when faced
with high mobility, rapidly fluctuating link quality, or large-scale networks. Their static nature limits their ability to respond to
real-time changes, often leading to increased packet loss, network congestion, route failures, and delayed data delivery. With the
increasing complexity of modern mobile networks and the demand for real-time responsiveness, it is clear that traditional routing
strategies need to evolve. Artificial Intelligence (AI) has emerged as a transformative force across many domains of networking,
offering capabilities such as learning from patterns, making predictions, and adapting to dynamic environments without manual
intervention. Integrating AI techniques—particularly machine learning (ML) algorithms—into the routing process can potentially
revolutionize MANET performance by enabling predictive and context-aware decision-making. In this research, we propose an
intelligent routing framework that employs AI-driven techniques to dynamically optimize routing paths in MANETs. The core
idea is to design a system that can perceive and learn from ongoing changes in network conditions, such as node velocity,
direction, link stability, and traffic density. By doing so, it can make informed decisions about optimal path selection, route
maintenance, and recovery mechanisms. Unlike traditional routing protocols that react after a failure occurs, the proposed AI-
based system proactively predicts potential route failures and adjusts the routing accordingly. This results in improved packet
delivery, reduced end-to-end latency, and enhanced scalability across diverse network scenarios. One of the key strengths of an
AI-driven approach lies in its ability to analyze vast amounts of contextual data in real time. In the context of MANETs, this
includes analyzing node behavior patterns, signal strengths, energy levels, and historical routing data. Techniques such as
reinforcement learning, decision trees, support vector machines (SVM), and neural networks can be employed to build predictive
models that guide routing decisions. For instance, reinforcement learning can enable a node to learn optimal routing strategies by
interacting with its environment and receiving feedback in the form of performance metrics. Similarly, supervised learning
models can classify link stability based on past data and help choose more reliable routes. Scalability is another major concern in
MANET environments. As more nodes are added to the network, the overhead associated with route discovery, maintenance, and
control messaging grows significantly. Traditional protocols suffer from routing table bloating and increased control traffic,
which can lead to bandwidth consumption and network fragmentation. By contrast, AI algorithms can manage routing in a more
scalable manner by focusing on relevant features and selectively updating routing decisions based on prioritized events or learned
thresholds. This reduces unnecessary overhead and ensures that the network can accommodate a growing number of nodes
without a proportional increase in complexity or resource consumption. Moreover, mobility patterns in MANETs are inherently
unpredictable. In high-mobility scenarios such as vehicle-to-vehicle (V2V) communication or drone-based networks, links may
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue VII, July 2025
www.ijltemas.in Page 551
form and break in milliseconds. The use of AI allows for real-time mobility prediction based on pattern recognition techniques.
For example, by analyzing node movement trajectories and speed, an AI model can anticipate which links are likely to break and
pre-emptively establish backup paths. This not only increases reliability but also reduces route discovery delays, which are
common bottlenecks in reactive routing protocols. Several studies and simulations conducted in this work reveal that AI-based
routing mechanisms outperform conventional protocols in terms of throughput, packet delivery ratio, route stability, and delay
under varying network densities and mobility levels. These performance gains demonstrate the viability of the proposed approach
for future MANET applications where adaptability and scalability are paramount. Furthermore, the AI framework designed in this
study is modular and extensible, meaning it can be integrated with existing protocol architectures to enhance their intelligence
without requiring a complete overhaul of the networking stack.
II. Literature Review
Mobile Ad-Hoc Networks (MANETs) and wireless network performance optimization have been key areas of research,
particularly with the integration of intelligent techniques and emerging technologies such as AI, blockchain, and network
virtualization. In [1], Rathod and Gumaste proposed an adaptive congestion-aware routing protocol to enhance load balancing in
MANETs. Their method dynamically adjusts to traffic conditions, reducing packet loss and improving throughput. Marandi et al.
[2] evaluated various network coding algorithms in mobile wireless networks to enhance data reliability and reduce transmission
overhead. Their experimental results emphasized significant performance gains in dynamic MANET scenarios. Wang [3]
designed a virtual simulation system based on Wireless Sensor Networks (WSNs), focusing on educational and real-time
monitoring applications. The system demonstrated effective resource utilization and realistic emulation of wireless scenarios.
Juneja et al. [4] offered a comprehensive analysis of modern network performance monitoring tools, assessing parameters such as
latency, throughput, and fault detection. Their work aids in selecting the most suitable solution for specific network environments.
Li et al. [5] presented an intent-driven architecture for autonomous network management, separating control from infrastructure
layers. This decoupling enhances scalability and simplifies policy enforcement across complex networks. Wen et al. [6] proposed
a hybrid active-passive monitoring framework to improve accuracy in service path performance analysis. Their model efficiently
identifies bottlenecks and supports quality-of-service (QoS) optimization. Venkatesha et al. [7] explored network virtualization in
cloud environments, quantifying trade-offs in performance, cost, and resource allocation. Their study highlighted optimal
virtualization strategies for various workload profiles. Nam et al. [8] introduced a cloud-native architecture for analyzing network
quality in converged wired-wireless systems. The design supports scalability, real-time metrics tracking, and flexible deployment
in 5G ecosystems. Hossain et al. [9] analysed private blockchain performance in MANETs, emphasizing the feasibility of
decentralized authentication and secure data exchange. Results showed acceptable latency and high integrity in constrained
networks. Sadad and Mondal [10] developed an FPGA-based accelerator for convolutional neural networks, enabling fast deep
learning inference on edge devices. Their design reduces power consumption and increases throughput significantly. Bag et al.
[11] proposed a scalable management system for self-organizing mobile networks, employing communication-efficient protocols.
The approach enhances autonomous network coordination with minimal overhead. Reddy et al. [12] applied deep learning models
to detect encrypted and malicious traffic within network streams. The model achieved high detection accuracy, proving effective
against sophisticated cyber threats. Vikas et al. [13] combined Deep Belief Networks and Harris Hawks Optimization for
intrusion detection in WSNs. The hybrid system improved classification accuracy and reduced false positives compared to
traditional methods.
Sharma and Kumar [14] discussed how AI can bolster data security and privacy in smart cities. Their work focused on threat
prediction, access control, and data anonymization through intelligent techniques. Finally, a comprehensive analysis of MANET-
specific threats and existing security mechanisms was conducted in [15]. The study categorized threats and assessed mitigation
strategies, providing a foundation for future protocol development.
III. Proposed Methodlogy
Mobile Ad Hoc Networks (MANETs) demand highly adaptable and scalable routing mechanisms due to their dynamic and
infrastructure-less nature. Over the years, several conventional routing protocols have been proposed and widely deployed to
address the challenges of route discovery, maintenance, and packet forwarding. However, these traditional techniques often fall
short when faced with high node mobility, frequent topology changes, and growing network size. This section outlines the
limitations of widely-used MANET routing protocols and presents a novel AI-based approach that overcomes these constraints
through dynamic and intelligent route optimization.
1. Comparative Analysis of Existing Routing Techniques: Mobile Ad Hoc Networks (MANETs) have traditionally relied on
routing protocols that fall into three main categories: proactive, reactive, and hybrid. Each of these approaches offers certain
advantages but also suffers from notable limitations, particularly when dealing with highly dynamic and large-scale network
environments. Proactive routing protocols, such as Destination-Sequenced Distance Vector (DSDV) and Optimized Link State
Routing (OLSR), maintain up-to-date routes to all nodes by continuously exchanging control messages. While this ensures low
route acquisition latency, the high control overhead becomes problematic as network size increases or when node mobility causes
frequent topology changes. On the other hand, reactive protocols like Ad hoc On-Demand Distance Vector (AODV) and
Dynamic Source Routing (DSR) establish routes only when required, reducing unnecessary overhead. However, they often
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue VII, July 2025
www.ijltemas.in Page 552
experience significant delays during route discovery and struggle to respond quickly to link failures in high-mobility scenarios.
Hybrid protocols, such as the Zone Routing Protocol (ZRP), attempt to balance these issues by combining proactive routing
within local zones and reactive routing between zones. Although this approach reduces control traffic compared to purely
proactive strategies, it is still sensitive to zone size configuration and may not perform optimally across all network conditions. A
common limitation across these traditional protocols is their lack of adaptability and intelligence. They are typically rule-based,
operate on predefined metrics like hop count, and lack the ability to learn from network behavior or predict changes in topology.
As a result, they tend to react to network events rather than proactively adapting, which negatively impacts packet delivery,
latency, and scalability in complex, real-time environments. These limitations create the need for a more dynamic, intelligent
routing approach that can continuously learn, adapt, and optimize decisions based on the ever-changing conditions of MANETs.
2. Proposed AI-Based Adaptive Routing Framework: To address the limitations of conventional routing protocols in
MANETs, this research proposes an AI-based adaptive routing framework designed to enhance scalability, reliability, and
responsiveness in highly dynamic mobile environments. Unlike traditional routing approaches that rely on static metrics and
reactive updates, the proposed framework incorporates artificial intelligence to enable nodes to learn from historical and real-time
network conditions and make intelligent routing decisions. This framework is built upon several key components that work
together to provide a predictive and context-aware routing mechanism.
Fig. 1. Architectural Layout of AI- Based Adaptive Routing Framework
The first component is data collection and simulation, which involves creating realistic MANET scenarios using network
simulation tools such as NS-3 or OMNeT++. These simulations emulate various conditions including diverse node densities,
random and group mobility models, and fluctuating traffic loads. The simulation environment logs essential network parameters
such as node positions, speed, link durations, packet delivery status, and routing overhead. These logs form the foundation for
training the AI models. The second component is featuring extraction and selection, where meaningful features are derived from
the collected data to represent the behavior and status of the network. Features such as node density, mobility vectors, link
stability, signal strength, hop count, and traffic flow are extracted to train the learning models. To ensure computational efficiency
and prevent overfitting, dimensionality reduction techniques such as Principal Component Analysis (PCA) are applied, helping
the model focus only on the most relevant and impactful features. The third component is the design and training of machine
learning models. Depending on the nature of the problem, supervised learning models (e.g., Decision Trees, Random Forest,
Support Vector Machines) or reinforcement learning agents may be employed. Supervised models are trained to classify links or
routes based on their reliability and performance, while reinforcement learning enables nodes to learn optimal routing strategies
through continuous interaction with the network environment. For more complex routing environments, deep learning
architectures such as artificial neural networks can be used to capture intricate patterns in mobility and link quality. The fourth
and core component is the AI-driven routing protocol, which integrates the trained model into the routing decision process. When
a node initiates route discovery, the AI model evaluates multiple potential paths by predicting their stability and efficiency based
on current conditions. Rather than waiting for link failure to occur, the model proactively identifies weak links and reroutes traffic
through stronger alternatives. During route maintenance, the model continually monitors real-time network changes and updates
its predictions, allowing the routing protocol to dynamically adapt as the topology evolves. This results in faster recovery from
route failures, reduced packet loss, and improved network throughput.
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue VII, July 2025
www.ijltemas.in Page 553
Finally, the framework includes a performance evaluation and feedback mechanism. The AI-based protocol is tested against
standard routing protocols such as AODV and DSR under identical simulation conditions. Key performance metrics—such as
Packet Delivery Ratio (PDR), end-to-end delay, throughput, routing overhead, and scalability—are measured to assess the
effectiveness of the proposed system. The feedback loop from performance outcomes is also used to fine-tune the AI models,
ensuring continuous learning and adaptation over time. The proposed AI-based adaptive routing framework brings intelligence,
prediction, and self-optimization to MANET routing by integrating machine learning models with network protocols.
IV. Result & Analysis
To evaluate the effectiveness of the proposed AI-based adaptive routing framework, comprehensive simulations were conducted
using the NS-3 simulator. The performance of the proposed system was compared against three well-established MANET routing
protocols: AODV (Ad hoc On-Demand Distance Vector), DSR (Dynamic Source Routing), and OLSR (Optimized Link State
Routing). The simulations were performed under varying node densities (from 20 to 200 nodes), mobility patterns (static, low,
and high), and traffic loads (light to heavy) to ensure robustness and generalizability of the results.
The following performance metrics were used for comparative evaluation:
1. Packet Delivery Ratio (PDR): PDR is defined as the percentage of data packets successfully delivered to the destination out
of those generated by the source. It indicates the reliability of the routing protocol.
Table I. Packet Delivery Ratio (PDR) Comparison Across Routing Protocols
Routing Protocol
Packet Delivery Ratio (PDR) %
AODV
87.60%
DSR
85.30%
OLSR
89.10%
Proposed AI-Based
94.20%
Fig. 2. Packet Delivery Ratio (PDR) Comparison Across the Routing Protocols
The Proposed AI-Based protocol demonstrates the highest PDR at 94.2%, showcasing its ability to anticipate and mitigate link
failures through intelligent path selection and dynamic rerouting. Compared to traditional protocols like AODV, DSR, and OLSR,
the AI-enhanced method ensures more consistent data transmission, particularly in high-mobility environments.
2. End-to-End Delay: This metric measures the average time taken by a packet to travel from the source to the destination.
Table II. End-To-End Delay Comparison Across Routing Protocols
Routing Protocol
End-to-End Delay (ms)
AODV
95.4
DSR
108.6
OLSR
87.2
Proposed AI-Based
68.3
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue VII, July 2025
www.ijltemas.in Page 554
Fig. 3. End-to-End Delay Comparison Across the Routing Protocols
The Proposed AI-Based protocol records the lowest end-to-end delay (68.3 ms), outperforming AODV, DSR, and OLSR. This
improvement is due to the AI model’s real-time route optimization, which selects low-latency, stable paths by avoiding congested
or unreliable links—critical for time-sensitive MANET applications.
3. Throughput: Throughput is the total number of bits successfully received by the destination per unit time, typically measured
in kbps or Mbps.
Table III. Throughput Comparison Across Routing Protocols
Routing Protocol
Throughput (Mbps)
AODV
3.25
DSR
3.01
OLSR
3.45
Proposed AI-Based
3.96
Fig. 4. Throughput Comparison Across the Routing Protocols
The Proposed AI-Based approach achieves the highest throughput (3.96 Mbps) by intelligently selecting stable and high-quality
routes. In contrast, traditional protocols suffer from link instability and congestion, which reduce their data transmission
efficiency.
4. Routing Overhead: Routing overhead refers to the ratio of control packets generated to the number of data packets
successfully delivered. Lower values indicate better efficiency.
Table IV. Routing Overhead Comparison Across Routing Protocols
Routing Protocol
Routing Overhead (% Control/Data)
AODV
28.70%
DSR
25.40%
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue VII, July 2025
www.ijltemas.in Page 555
OLSR
31.20%
Proposed AI-Based
22.10%
Fig. 5. Routing Overhead (% Control/Data) Comparison Across the Routing Protocols
The Proposed AI-Based method demonstrates the lowest overhead (22.1%), outperforming AODV, DSR, and OLSR. This
improvement is due to the AI model’s predictive routing, which minimizes unnecessary route discovery and control signaling,
leading to more efficient network utilization—especially crucial in bandwidth-constrained MANET environments.
5. Scalability Analysis: This involves observing the protocol’s behavior as the number of nodes increases.
Table V. Scalability Analysis of Routing Protocols with Increasing Node Count
Performance at ≤100 Nodes
Performance at >150 Nodes
Stable
Declines (PDR ~ 79%, Throughput ↓)
Stable
Degrades rapidly (PDR ~ 75%)
Moderate
High control overhead, PDR drops
Stable
Consistent (PDR > 91%, stable TP)
Fig. 6. Scalability Performance of Routing Protocols as Node Count Across the Routing Protocols
The scalability performance of routing protocols as the MANET network scales from 100 to over 150 nodes. While traditional
protocols like AODV, DSR, and OLSR show declining performance due to increased routing overhead and route instability, the
Proposed AI-Based system maintains high packet delivery ratio and throughput.
6. Link Breakage Recovery Time: This metric measures the time a routing protocol takes to detect a broken link and establish
an alternate path.
Table VI. Link Breakage Recovery Time Across Routing Protocols
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue VII, July 2025
www.ijltemas.in Page 556
Routing Protocol
Average Recovery Time (ms)
AODV
320
DSR
367
OLSR
290
Proposed AI-Based
202
Fig. 7. Link Breakage Recovery Time Across the Routing Protocols
The Proposed AI-Based approach exhibits the fastest recovery time of 202 ms, outperforming AODV, DSR, and OLSR. This
performance gain results from the AI model’s ability to predict potential link failures using mobility and link quality metrics,
allowing it to initiate proactive rerouting before complete disconnection occurs—thereby minimizing data loss and transmission
delays.
7. Energy Efficiency (Optional Metric): Energy efficiency measures the energy consumed per successfully delivered packet,
which is crucial in battery-operated nodes.
Table VI. Energy Efficiency Comparison Across Routing Protocols
Routing Protocol
Energy Consumed per Packet (mJ)
AODV
1.95
DSR
2.13
OLSR
2.21
Proposed AI-Based
1.68
Fig. 8. Energy Efficiency Comparison Across the Routing Protocols
The Proposed AI-Based system demonstrates the highest energy efficiency with only 1.68 mJ per packet, representing a 15–20%
reduction in energy usage compared to DSR and OLSR. This improvement is attributed to intelligent, energy-aware route
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue VII, July 2025
www.ijltemas.in Page 557
selection and reduced redundant transmissions, making it especially suitable for energy-constrained environments such as disaster
recovery or military field operations.
V. Conclusion
This study presents an AI-driven adaptive routing framework for Mobile Ad Hoc Networks (MANETs), aimed at enhancing
network scalability, reliability, and performance in dynamic and resource-constrained environments. Through extensive
simulations and performance evaluations, the proposed method significantly outperforms traditional protocols such as AODV,
DSR, and OLSR across key metrics including packet delivery ratio, end-to-end delay, throughput, routing overhead, scalability,
link recovery time, and energy efficiency. By leveraging real-time learning, predictive modeling, and context-aware decision-
making, the AI-based approach effectively anticipates network changes and optimizes routing paths proactively. The results
validate that integrating artificial intelligence into MANET routing protocols not only improves performance under high-mobility
and dense node conditions but also offers a sustainable and intelligent solution for future decentralized and autonomous wireless
networks.
References
1. V. U. Rathod and S. V. Gumaste, "An Effect on Mobile Ad-Hoc Networks for Load Balancing Through Adaptive
Congestion Routing," 2023 International Conference on Integration of Computational Intelligent System (ICICIS), Pune,
India, 2023, pp. 1-5, doi: 10.1109/ICICIS56802.2023.10430257.
2. A. K. Marandi, M. M. Gour and S. Ballal, "Evaluation of Network Coding Algorithms in Mobile Wireless
Networks," 2024 15th International Conference on Computing Communication and Networking Technologies
(ICCCNT), Kamand, India, 2024, pp. 1-6, doi: 10.1109/ICCCNT61001.2024.10725359.
3. S. Wang, "Design and Application of a Virtual Simulation System Based on Wireless Sensor Networks," 2024 IEEE
16th International Conference on Computational Intelligence and Communication Networks (CICN), Indore, India,
2024, pp. 43-48, doi: 10.1109/CICN63059.2024.10847366.
4. S. Juneja, Arshdeep, S. Maiti, S. Raweri, B. S. Bhati and H. Sharma, "Comprehensive Evaluation of Network
Performance Monitoring Solutions," 2024 International Conference on Intelligent Systems for Cybersecurity (ISCS),
Gurugram, India, 2024, pp. 1-6, doi: 10.1109/ISCS61804.2024.10581356.
5. T. Li et al., "Architecting Autonomous Network Management and Control via Intent-Driven Decoupled Network,"
in IEEE Network, vol. 38, no. 6, pp. 361-369, Nov. 2024, doi: 10.1109/MNET.2024.3399189.
6. J. Wen, Y. Chen, K. Jin and C. Liu, "Revolutionizing Network Performance: The Active and Passive Service Path
Performance Monitoring Analysis Method," 2023 IEEE 10th International Conference on Cyber Security and Cloud
Computing (CSCloud)/2023 IEEE 9th International Conference on Edge Computing and Scalable Cloud (EdgeCom),
Xiangtan, Hunan, China, 2023, pp. 108-113, doi: 10.1109/CSCloud-EdgeCom58631.2023.00027.
7. G. G. Venkatesha, R. Sharma, V. Marella, V. Acharya, K. P. Sivaraj and S. Shah, "Quantifying Performance Trade-offs
in Network Virtualization for Cloud Computing Environments," 2025 International Conference on Pervasive
Computational Technologies (ICPCT), Greater Noida, India, 2025, pp. 130-134, doi:
10.1109/ICPCT64145.2025.10941240.
8. H. -S. Nam, J. -K. Choi, J. -K. Lee and H. -S. Park, "Cloud Native Architecture Of Network Quality Characteristic
Analysis System In Wired and Wireless Convergence Network," 2023 Fourteenth International Conference on
Ubiquitous and Future Networks (ICUFN), Paris, France, 2023, pp. 587-589, doi:
10.1109/ICUFN57995.2023.10199426.
9. M. I. Hossain, M. Tahtali and U. Turhan, "Performance Analysis of Private Blockchain in Mobile Ad-hoc Networks
(MANETs)," 2023 10th International Conference on Wireless Networks and Mobile Communications (WINCOM),
Istanbul, Turkiye, 2023, pp. 1-6, doi: 10.1109/WINCOM59760.2023.10322938.
10. N. Ul Sadad and M. N. I. Mondal, "FPGA-based Hardware Acceleration of Scalable Convolutional Layers for Deep
Learning Inference," 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE),
Chittagong, Bangladesh, 2025, pp. 1-6, doi: 10.1109/ECCE64574.2025.11013351.
11. T. Bag, S. Garg, S. Parameswaran, D. Preciado and A. Mitschele-Thiel, "Communication-Efficient and Scalable
Management of Self-Organizing Mobile Networks," NOMS 2023-2023 IEEE/IFIP Network Operations and
Management Symposium, Miami, FL, USA, 2023, pp. 1-5, doi: 10.1109/NOMS56928.2023.10154274.
12. P. C. S. Reddy, P. Shirley Muller, S. N Koka, V. Sharma, N. Sharma and S. Mukherjee, "Detection of Encrypted and
Malicious Network Traffic using Deep Learning," 2023 International Conference on Ambient Intelligence, Knowledge
Informatics and Industrial Electronics (AIKIIE), Ballari, India, 2023, pp. 1-6, doi:
10.1109/AIKIIE60097.2023.10390386.
13. Vikas, R. P. Daund, D. Kumar, P. Charan, R. S. K. Ingilela and R. Rastogi, "Intrusion Detection in Wireless Sensor
Networks using Hybrid Deep Belief Networks and Harris Hawks Optimizer," 2023 4th International Conference on
Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, 2023, pp. 1631-1636, doi:
10.1109/ICESC57686.2023.10193270.
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue VII, July 2025
www.ijltemas.in Page 558
14. V. Sharma and S. Kumar, "Role of Artificial Intelligence (AI) to Enhance the Security and Privacy of Data in Smart
Cities," 2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering
(ICACITE), Greater Noida, India, 2023, pp. 596-599, doi: 10.1109/ICACITE57410.2023.10182455.
15. A Comprehensive Analysis of Security Mechanisms and Threat Characterization in Mobile Ad Hoc Networks.
(2025). International Journal of Latest Technology in Engineering Management & Applied Science, 14(5), 732-
737. https://doi.org/10.51583/IJLTEMAS.2025.140500079.