Thillai Rani Munichamy

Thillai Rani Munichamy


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 January 2023 in Energies
Verified
Journal Article
Open access
PDF file
VKVINOTH KUMAR K
VINOTH KUMAR K
Ivan IzoninIvan Izonin
Ivan Izonin
SSSugumaran Subramanian
Sugumaran Subramanian
SSShishir Kumar Shandilya
Shishir Kumar Shandilya
SVSivasankaran Velayutham
Sivasankaran Velayutham
MHMyroslav Havryliuk
Myroslav Havryliuk
The Mobile Ad-hoc Network is a self-configuring decentralized network, where the network topology is dynamically modifiable. The IoT (Internet of Things) based Wireless Sensor Network contains more sensors and shares information over the Internet to a cloud server. However, the IoT-based wireless sensor network channel has moderate security is poor compared to MANET and packet loss is increased due to attackers. In IoT, all the sensors forward the detected data frequently to the internet gateway, so the energy saving in the network is low compared to MANET. In this work, the smart environment of IoT, Wireless Sensor Networks (WSN) and MANET make a great heterogeneous network in IT Technology; the combination of this heterogeneous network has new challenging issues. In this heterogeneous network, MANET provides a trusted route between the sensor to gateway nodes into the IoT environment using Energy Saving Optimization Techniques [MANET-ESO in IoT]. It saves energy for each node and reduces the economic level. The results of the ns-3 simulation show that the proposed method provides better results in Alive node counts, residual Energy, throughput, packet delivery ratio and routing overhead.

1 June 2025 in International Journal of Computational and Experimental Science and Engineering
Verified
Journal Article
Open access
PDF file
SJS. Jagan
S. Jagan
BGB. Girirajan
B. Girirajan
MMManisha Bhimrao Mane
Manisha Bhimrao Mane
HBHussana Johar R B
Hussana Johar R B
MAMariam Anil
Mariam Anil
TMThillai Rani Munichamy
Thillai Rani Munichamy
The convergence of quantum computing and artificial intelligence (AI) has introduced innovative opportunities to accelerate deep learning, particularly within decentralized cloud architectures. This study develops an adaptive quantum AI model leveraging hybrid quantum-classical algorithms to optimize deep learning processes such as training, inference, and resource allocation. The proposed model integrates Variational Quantum Circuits (VQCs) and Quantum Approximate Optimization Algorithms (QAOAs), which enable efficient handling of high-dimensional data and complex optimization tasks inherent in distributed environments. By addressing challenges like latency, energy efficiency, and computational overhead, the quantum AI model demonstrates significant performance gains in decentralized cloud systems.Experimental evaluations on benchmark datasets reveal a 40% reduction in training time, a 30% improvement in resource efficiency, and a 20% increase in prediction accuracy compared to classical deep learning frameworks. This study highlights the transformative potential of quantum computing in AI-driven decentralized cloud architectures, offering insights into its application for computationally intensive tasks across industries such as healthcare, finance, and logistics. Future work will focus on refining quantum hardware compatibility, developing quantum error correction methods, and exploring federated learning applications to expand the scope of quantum AI in privacy-preserving and distributed systems.

17 March 2025 in International Journal of Computational and Experimental Science and Engineering
Verified
Journal Article
Open access
PDF file
ASAnwar Ahamed Shaikh
Anwar Ahamed Shaikh
ICI. Carol
I. Carol
MEMeenakshi
Meenakshi
HSHelina Rajini Suresh
Helina Rajini Suresh
TMThillai Rani Munichamy
Thillai Rani Munichamy
JPJ. Rejina Parvin
J. Rejina Parvin
Edge computing has emerged as a pivotal technology for managing computational workloads in latency-sensitive applications by offloading tasks from resource-constrained Internet of Things (IoT) devices to nearby edge servers. However, optimizing task offloading while ensuring energy efficiency remains a significant challenge. This paper proposes a Hybrid AI-Based Task Offloading (HATO) model, integrating Reinforcement Learning (RL) with Deep Neural Networks (DNNs) to dynamically allocate computational resources while minimizing energy consumption. The HATO framework formulates task offloading as a multi-objective optimization problem, considering factors such as device workload, network latency, edge server availability, and energy constraints. Experimental evaluations demonstrate that the proposed model achieves a 27.3% reduction in energy consumption, a 19.6% improvement in task completion time, and a 31.2% enhancement in overall edge server utilization compared to conventional heuristic-based methods. The reinforcement learning module adapts task offloading strategies in real-time, ensuring optimal computational load balancing while minimizing latency. The proposed Hybrid AI-Based Approach outperforms baseline models in diverse edge computing scenarios, making it a scalable and efficient solution for next-generation IoT applications.

12 October 2022
Verified
Book Chapter
Closed access
PDF file
TMThillai Rani Munichamy
Thillai Rani Munichamy
RRRajkumar Ramasamy
Rajkumar Ramasamy
KPK. P. Sai Pradeep
K. P. Sai Pradeep
MJM. Jaishree
M. Jaishree
STS. TamilSelvan
S. TamilSelvan

2 January 2026
Verified
Book Chapter
Closed access
PDF file
TMThillai Rani Munichamy
Thillai Rani Munichamy
MKM. Navin Kumar
M. Navin Kumar
MJM. Jaishree
M. Jaishree
SPSAI PRADEEP K P
SAI PRADEEP K P