A Comparative Study of Multi-Agent Reinforcement Learning Approaches for Resource Optimization in Wireless Networks Madhavi. S, Karthikeyan A 2025 International Conference on Data Science and Business Systems Icdsbs 2025, 2025 Integrated into wireless networks, Multi-Agent Reinforcement Learning (MARL) has shown considerable potential in addressing resource optimization problems including power control, spectrum allocation, and effective communication. When MARL is applied in dynamic wireless environments, including limited resource blocks, energy constraints, communication errors, and convergence delays, there are further challenges as well. By means of a comprehensive review of MARL approaches applied in wireless networks, this paper classifies current methods based on network characteristics, learning processes, and optimization objectives. We review important developments, alternative strategies, and flag up remaining problems like energy-efficient communication, scalability, and real-time convergence. One of the suggested future possibilities is the use of modern wireless technologies including Terahertz communication and Intelligent Reflecting Surfaces (IRS) to enhance MARL performance. This survey offers a basis for academics trying to design ideal MARL solutions for next-generation wireless networks.
An Overview of Adaptive Network Control in the Internet of Things: Machine Learning Methods for Optimizing Traffic and Dynamic Resource Management A Karthikeyan, J Joel 2025 International Conference on Data Science and Business Systems Icdsbs 2025, 2025 The Internet of Things (IoT) ecosystem has witnessed exponential growth, making network settings complex and dynamic. These challenges in energy efficiency, traffic, and resource allocation have already made adaptive network control an indispensable instrument for Internet of Things (IoT) systems. The survey provides a comprehensive overview of adaptive network control techniques, particularly those based on ML algorithms to maximize traffic handling and dynamic resource allocation. Focusing on Internet of Things (IoT) use cases such as edge computing, sensor networks, and heterogeneous device management, the research examines a wide variety of ML algorithms, including supervised, unsupervised, and reinforcement learning. The study shows that network scaling using ML-based methods will be stable and load-balanced and reduce latency continuously. Here adaptive resource management is explored with reinforcement learning (RL) methods that can alter on-demand storage, processing and bandwidth to match the dynamic requirements. It says federated learning provides a way to optimize decentralized systems without compromising user data while making full use of distributed resources. Recent studies from the wide spectrum of ML applications provide case studies and experimental findings for increasing fault tolerance, reducing energy consumption, and improving Quality of Service (QoS) in IoT networks. Enabling flexible, efficient, and sustainable IoT networks, this study presents the transformative potential of machine learning. Other important research issues identified include scalable algorithms, real-time decision-making abilities, and high security. Suggestions for future work reveals the area of hybrid ML models, 6G AI convergence and development of light weight algorithms that can be run in low power Internet of Things devices. This work aims to provide a foundation for researchers and practitioners to use machine learning for advanced network control in the context of IoT ecosystems.
Proactive flow control using adaptive beam forming for smart intra-layer data communication in wireless network on chip Dinesh Kumar T.R., Karthikeyan A. Automatika, 2023 Systems-on-chips need numerous predesigned cores to advance. NoC enables Multi-Core SoCs (MC_SoCs). Conventional NoC cores use power and latency on multi-hop wired connections. An effective Wireless Network-on-Chip (WiNoC) architecture can overcome NoC difficulties. On-chip antennas, transceivers, and routers replace multi-hop cable connections with high-bandwidth single-hop wireless networks using WiNoC. Nanotechnology development demands fast data transfer to overcome performance bottlenecks from sharing memory modules and connecting fabrics. This research offers a new Proactive Flow control using Adaptive Beam formation for Smart Intra-layer Data Communication technique(PF_SDC) to optimally use network resources and assure QoS in Wireless Network-on-Chip for next-generation nano-domain technology. Hybrid NoC architecture optimises application admission for data transfer over wired and wireless interconnects. Data traffic is managed by a fuzzy inference-based Intelligent Head Agent (IHA). Queue load predicts router status for the fittest path selection. IHA initiates beams at angles to admit data flow towards the target while utilising the least amount of network power and resources. A simulation model shows that the proposed system may be applied in real-world applications and consumes little power with good throughput.
Dynamic low power management technique for decision directed inter-layer communication in three dimensional wireless network on chip T. R. Dinesh Kumar, A. Karthikeyan Automatika, 2023 3D ICs, a novel technology, might significantly impact multicore NoCs with hundreds or thousands of processing components on a single chip.Multiple 2D chips can be stacked vertically to create multiple active processing elements at various levels.Adding active device layers to 3D ICs can enhance system performance, increase functionality, and increase packing density.New architectural and IC technology advancements hinder energy-efficient design research.Achieving a balance between chip power and performance is crucial.This paper describes the "Dynamic Low Power Management Method in 3DWiNoC" (DLPM 3DWiNoC) architecture, which enables self-organized, centrally managed service management using Smart Master Agents.The approach utilizes SMA's ODA DD module for self-organized, centrally managed service management.To improve power regulation, data flow across vertical interconnects (TSVs) is reconfigured based on a dynamic evaluation of channel link use.SMA aims to reduce congestion by increasing connection utilization through high-frequency, bi-directional vertical channels via TSVs.The suggested system is modeled in MATLAB Simulink.Compared to 3D stacking, TSV stacking of vertical interconnects with the SMA method ensures low parasitic (latency and power) and higher bandwidth with higher vertical wire densities.Experimental results show that the proposed architecture decreases area overhead by 5%-7%, network latency by 12%-15%, and NoC power consumption by 15%-20% compared to the present multi-NoC design.
Energy efficient optimal hop transmission using minimum power least cost algorithm in cooperative routing for wireless sensor network Immanuvel Arokia James K., Manjula P., Guga Priya G., Karthikeyan A. Automatika, 2023 Cooperative communication has gained a lot of popularity recently. Through a variety of shortest path methods, this article's paradigm may efficiently reduce the amount of power consumed and hop transmission. In this research, we construct the Minimum Power Least Cost Routing (MPLCR) algorithm and evaluate its performance. The design of the proposed algorithm took into account link computation, sequential scanning algorithm approach, and balance (residual) energy. To prevent connection failures and lessen network traffic, the link calculation is used to choose the best route (relay node). In order to reduce network power consumption, a sequential scanning technique was used to find the shortest path with the fewest hops. And also discuss relay nodes and their characteristics in order to improve the transmission stream's quality of service. An ideal path is one that ensures end-to-end transmission while using the least amount of transmitted power. The minimum power least cost routing algorithm uses cooperative communications to help build the smallest power route. When compared to the current algorithms, the proposed approach uses less energy by more than 30%.
Analysis of image quality enhancement by dissimilarity reconditioning under haze conditions for driving reinforcement International Journal of Control Theory and Applications, 2016
An optimal energy management system for electric vehicles using firefly optimization algorithm based dynamic EDF scheduling International Journal of Engineering and Technology, 2015
A new power gating scheme using multi-mode power switches for static power reduction International Journal of Applied Engineering Research, 2015
Implementation of reconfigurable fault tolerant network on chip for aerospace applications Life Science Journal, 2013
RECENT SCHOLAR PUBLICATIONS
An Overview of Adaptive Network Control in the Internet of Things: Machine Learning Methods for Optimizing Traffic and Dynamic Resource Management A Karthikeyan, J Joel 2025 International Conference on Data Science and Business Systems (ICDSBS), 1-6 , 2025 2025
A Comparative Study of Multi-Agent Reinforcement Learning Approaches for Resource Optimization in Wireless Networks A Karthikeyan 2025 International Conference on Data Science and Business Systems (ICDSBS), 1-8 , 2025 2025
Design and implementation in power-efficient and thermal conductivity of vedic processor for embedded applications A Prema, A Karthikeyan Thermal Science and Engineering Progress 55, 102895 , 2024 2024
Energy saving using transformation algorithm in vertical farming A Karthikeyan, C Anand, N Manoj Kumar, K Seenuvasan, B Gowtham, ... AIP Conference Proceedings 2965 (1), 020022 , 2024 2024 Citations: 1
Proactive flow control using adaptive beam forming for smart intra-layer data communication in wireless network on chip TR Dinesh Kumar, A Karthikeyan Automatika: časopis za automatiku, mjerenje, elektroniku, računarstvo i … , 2023 2023 Citations: 6
Energy efficient optimal hop transmission using minimum power least cost algorithm in cooperative routing for wireless sensor network K Immanuvel Arokia James, P Manjula, G Guga Priya, A Karthikeyan Automatika: časopis za automatiku, mjerenje, elektroniku, računarstvo i … , 2023 2023 Citations: 2
Dynamic low power management technique for decision directed inter-layer communication in three dimensional wireless network on chip TR Dinesh Kumar, A Karthikeyan Automatika: časopis za automatiku, mjerenje, elektroniku, računarstvo i … , 2023 2023 Citations: 4
Co-operative beam forming selection with energy balanced operation for wireless sensor network KIA James, R Prabakaran, A Karthikeyan, RR Prianka Wireless Networks 28 (8), 3653-3663 , 2022 2022 Citations: 3
Understanding of controllable optical memory using 1D InP based photonic structures at three communication windows MR Khanna, A Karthikeyan, PG Kuppusamy, RR Prianka Optical and Quantum Electronics 54 (6), 326 , 2022 2022 Citations: 1
Investigations on hybrid wavelength-mode-orthogonal frequency-division multiplexing scheme based free space optical transmission system under varying atmospheric conditions D Joseph, A Karthikeyan, PG Kuppusamy, V Prabhu Optical and Quantum Electronics 54 (1), 64 , 2022 2022 Citations: 12
An energy-aware buffer management (EABM) routing protocol for WSN: P. Jayarajan et al. P Jayarajan, GR Kanagachidambaresan, TVP Sundararajan, ... The Journal of Supercomputing 76 (6), 4543-4555 , 2020 2020 Citations: 66
Detection and classification of 2D and 3D hyper spectral image using enhanced Harris corner detector A Karthikeyan, S Pavithra, PM Anu Scalable Computing: Practice and Experience 21 (1), 93-100 , 2020 2020 Citations: 6
Secured identity based cryptosystem approach for intelligent routing protocol in VANET A Karthikeyan, PG Kuppusamy, IS Amiri Scalable Computing: Practice and Experience 21 (1), 41-46 , 2020 2020 Citations: 3
Texture classification using optimized local ternary patterns with nonlinear diffusion as pre-processing G Madasamy Raja, M Thaha, R Latha, A Karthikeyan Multimedia Tools and Applications 79 (5), 3831-3846 , 2020 2020 Citations: 10
A novel approach for non-invasive measurement of mean arterial pressure using pulse transit time V Prabhu, PG Kuppusamy, A Karthikeyan, M Sucharitha Multimedia Tools and Applications 79 (5), 3775-3789 , 2020 2020 Citations: 10
Reduction of return loss in microstrip patch antenna using EBG structure for vehicular wireless communication A Prianka, R.R., Kavida, A.C., Karthikeyan Journal of Green Engineering 10 (12), 12917–12932 , 2020 2020
Investigation of turbo decoding techniques based on lottery arbiter in 3D network on chip M Suganthy, A Karthikeyan, PG Kuppusamy Microprocessors and Microsystems 71, 102885 , 2019 2019 Citations: 4
IOT-Interoperability and dynamic workflow composition–challenges and perspectives [articol] V Suresh Kumar, PG Kuppusamy, A Karthikeyan Timișoara: Editura Politehnica , 2019 2019
IOT INTEROPERABILITY AND DYNAMIC WORKFLOW COMPOSITION CHALLENGES AND PERSPECTIVES VS KUMAR, PG KUPPUSAMY, A KARTHIKEYAN Journal of electrical engineering 19 (1), 5-5 , 2019 2019 Citations: 1
Evaluation and analysis of data driven in expectation maximization segmentation through various initialization techniques in medical images V Prabhu, PG Kuppusamy, A Karthikeyan, R Varatharajan Multimedia Tools and Applications 77 (8), 10375-10390 , 2018 2018 Citations: 14
MOST CITED SCHOLAR PUBLICATIONS
An energy-aware buffer management (EABM) routing protocol for WSN: P. Jayarajan et al. P Jayarajan, GR Kanagachidambaresan, TVP Sundararajan, ... The Journal of Supercomputing 76 (6), 4543-4555 , 2020 2020 Citations: 66
Randomly prioritized buffer-less routing architecture for 3D network on chip A Karthikeyan, PS Kumar Computers & Electrical Engineering 59, 39-50 , 2017 2017 Citations: 28
GALS implementation of randomly prioritized buffer-less routing architecture for 3D NoC A Karthikeyan, PS Kumar Cluster Computing 21 (1), 177-187 , 2018 2018 Citations: 24
Evaluation and analysis of data driven in expectation maximization segmentation through various initialization techniques in medical images V Prabhu, PG Kuppusamy, A Karthikeyan, R Varatharajan Multimedia Tools and Applications 77 (8), 10375-10390 , 2018 2018 Citations: 14
Investigations on hybrid wavelength-mode-orthogonal frequency-division multiplexing scheme based free space optical transmission system under varying atmospheric conditions D Joseph, A Karthikeyan, PG Kuppusamy, V Prabhu Optical and Quantum Electronics 54 (1), 64 , 2022 2022 Citations: 12
Texture classification using optimized local ternary patterns with nonlinear diffusion as pre-processing G Madasamy Raja, M Thaha, R Latha, A Karthikeyan Multimedia Tools and Applications 79 (5), 3831-3846 , 2020 2020 Citations: 10
A novel approach for non-invasive measurement of mean arterial pressure using pulse transit time V Prabhu, PG Kuppusamy, A Karthikeyan, M Sucharitha Multimedia Tools and Applications 79 (5), 3775-3789 , 2020 2020 Citations: 10
An optimal energy management system for electric vehicles using firefly optimization algorithm based dynamic EDF scheduling E Kayalvizhi, A Karthikeyan, J Arunarasi International Journal of Engineering and Technology 7 (4), 1385-1393 , 2015 2015 Citations: 9
A maximum powerpoint tracking using perturb and observation algorithm by LABVIEW and arduino D Divya, A Karthikeyan, G Panneerselvam, D Priya 2014 International Conference on Science Engineering and Management Research … , 2014 2014 Citations: 7
Proactive flow control using adaptive beam forming for smart intra-layer data communication in wireless network on chip TR Dinesh Kumar, A Karthikeyan Automatika: časopis za automatiku, mjerenje, elektroniku, računarstvo i … , 2023 2023 Citations: 6
Detection and classification of 2D and 3D hyper spectral image using enhanced Harris corner detector A Karthikeyan, S Pavithra, PM Anu Scalable Computing: Practice and Experience 21 (1), 93-100 , 2020 2020 Citations: 6
Analysis and performance comparison of 3-D NoC routing algorithms A Sweety, A Karthikeyan, SJ Kirubakaran Int J Appl Eng Res 10 (5), 13415-13429 , 2015 2015 Citations: 5
Dynamic low power management technique for decision directed inter-layer communication in three dimensional wireless network on chip TR Dinesh Kumar, A Karthikeyan Automatika: časopis za automatiku, mjerenje, elektroniku, računarstvo i … , 2023 2023 Citations: 4
Investigation of turbo decoding techniques based on lottery arbiter in 3D network on chip M Suganthy, A Karthikeyan, PG Kuppusamy Microprocessors and Microsystems 71, 102885 , 2019 2019 Citations: 4
A neoteric FPGA architecture with Memristor based interconnects for efficient power consumption A Karthikeyan, J Arunarasi, A Mary Indian J. of Sci. Technol 9 (5), 1-9 , 2016 2016 Citations: 4
Co-operative beam forming selection with energy balanced operation for wireless sensor network KIA James, R Prabakaran, A Karthikeyan, RR Prianka Wireless Networks 28 (8), 3653-3663 , 2022 2022 Citations: 3
Secured identity based cryptosystem approach for intelligent routing protocol in VANET A Karthikeyan, PG Kuppusamy, IS Amiri Scalable Computing: Practice and Experience 21 (1), 41-46 , 2020 2020 Citations: 3
Energy efficient optimal hop transmission using minimum power least cost algorithm in cooperative routing for wireless sensor network K Immanuvel Arokia James, P Manjula, G Guga Priya, A Karthikeyan Automatika: časopis za automatiku, mjerenje, elektroniku, računarstvo i … , 2023 2023 Citations: 2
Energy saving using transformation algorithm in vertical farming A Karthikeyan, C Anand, N Manoj Kumar, K Seenuvasan, B Gowtham, ... AIP Conference Proceedings 2965 (1), 020022 , 2024 2024 Citations: 1
Understanding of controllable optical memory using 1D InP based photonic structures at three communication windows MR Khanna, A Karthikeyan, PG Kuppusamy, RR Prianka Optical and Quantum Electronics 54 (6), 326 , 2022 2022 Citations: 1