Energy-Aware VM Consolidation Using Similarity-Driven Intelligence in Green Cloud Environments Nirmal Kr Biswas, Debashis Das, Sourav Banerjee, Utpal Biswas IEEE Transactions on Sustainable Computing, 2026 Cloud computing is currently playing an essential role in supporting emerging sectors such as smart energy, intelligent transportation, and large-scale distributed systems. The scalability and adaptability features of cloud computing are efficiently enable resource utilization and continuous data exchange in dynamic and heterogeneous environments. However, the increasing demand for cloud services has raised the energy consumption of cloud data centers, which has a critical environmental impact. Therefore, sustainable resource management tactics have become crucial in today's world. Dynamic Virtual Machine (VM) consolidation is one of the major tactics for sustainable resource management in the green cloud computing environment. Herein, a novel dynamic Energy-Aware Cosine Similarity Learning Network (ECSLN) is proposed to predict the overutilized host. Further, an Impact Factor-Based VM Selection (IFBVMS) method is proposed to select VMs for migration, and an ECSLN-Packed Placement method for VM placement into hosts. The main aim of the proposed VM consolidation is to maximize energy efficiency while preserving compliance with Service Level Agreements (SLAs) for sustainable environments. The experimental evaluation using real-world traces like PlanetLab, Bitbrains, and Alibaba Cluster 2020 workload validates that the proposed VM consolidation methods significantly reduce energy consumption and SLA violation compared to the existing methods for sustainable environments. The evaluation shows that the proposed ECSLN-based consolidation framework enables green cloud infrastructure by intelligently balancing energy consumption, SLA violation, and performance of cloud data centers.
Multi-Chain NFTs: A Secure and Sustainable Approach to Interoperability in Blockchain Suseta Datta, Rajdeep Roy, Sourav Banerjee, Utpal Biswas Research Advances in Network Technologies Volume 3, 2026 In the zestful domain of blockchain technology, non-fungible tokens (NFTs) have embellished a seminal procedure for setting up digital asset holding. This paper proposes a novel framework for multi-chain NFTs, wherein a single smart contract is deployed across multiple blockchain networks, prolonging the alike contract address to clinch congruous and lone NFT adjuncts. The launching burn-and-mint contraption eases coherent NFT conducts beyond divergent chains, magnifying user trail while conserving safety, solidity, and derivation. By examining the effects of this scheme, the challenges of achieving interoperability among blockchain systems are identified, and potential solutions are proposed to facilitate ethical digital asset management. This work presents prospects of multi-chain NFTs to augment liquidity in the digital asset mart, presenting the latest opportunities for creators, collations, and capitalists. Furthermore, the approach of these NFTs in aiding upheld initiatives, like endowing climate projects and tokenizing actual assets, is inspected. The discovery grant to the proceeding discourse on blockchain upheaval, providing perceptions into the evolution of NFT technology and its pivotal role in elevating economic insertion and overseeing expedient usage.
Generative AI-enabled energy-efficient CRSNs for Consumer electronics applications in smart healthcare: An IoT Approach Amrit Mukherjee, Pavan Paikrao, Pratik Goswami, Sourav Banerjee IEEE Transactions on Consumer Electronics, 2026 The work presents a generative AI-driven framework for enhancing energy efficiency in spectrum sensing within Cognitive Radio Sensor Networks (CRSNs) for consumer electronics. Using Generative Adversarial Networks (GANs), the approach generates synthetic training data to compensate for limited real-world spectrum observations and dynamically adapts to changing radio environments. This reduces dependence on resource-intensive data collection while optimizing key parameters, such as sensor sleeping rates and detection thresholds, through a neural network model. This proposed work explores the integration of Generative Artificial Intelligence (AI) into spectrum sensing for CRSNs, by proposing a novel framework to improve energy efficiency while maintaining high detection accuracy. The work has included generative models, such as Variational Autoencoders (VAEs) and GANs, which synthesize the realistic spectrum data to train lightweight sensing models by reducing the dependency on extensive real-world data collection along with minimizing computational overhead. The study evaluates the effectiveness of the framework using mathematical modeling, which shows a significant reduction in energy consumption compared to conventional methods, without compromising the sensing reliability. In addition, the paper discusses practical implications for consumer electronics applications by highlighting scalability and adaptability to dynamic spectrum conditions and potential deployment challenges.
Lightweight Cryptographic Authentication for UAV Networks: A Hyperelliptic Curve Approach Bodhisattwa Baidya, Atanu Mondal, Sourav Banerjee, Gourab Das Proceedings of the International Conference on Research in Computational Intelligence and Communication Networks Icrcicn, 2025 Unmanned aerial vehicle (UAV) networks heavily rely upon very lightweight and highly efficient authentication mechanism to provide safe communication in resource-limited environments. In this paper, we present a high-performance authentication mechanism utilizing hyperelliptic curve cryptography (HECC), optimized by grey wolf optimization (GWO). Demonstration shows HECC method generates keys 1.12 times as quickly as ECC and remarkable 1649 times speedup relative to RSA for medium-security level, while also being able to perform a complete four-way handshake authentication in 67 bytes. Statistical analyses confirm all measured performance advantages were statistically significant ($\mathbf{p}\lt 0.05$) with large effect sizes. GWObased method achieves $1.92 \%$ percent performance increase and has $100 \%$ security against replay attacks, man-in-the-middle attacks, and impersonation attacks. The scalability evaluation showed the method to be effective with varying numbers of UAV swarms, producing a maximum of 12.92 UAVs per second of peak throughput and demonstrating its feasibility for real-time deployment into UAV networks.
Enhancing Acute Lymphoblastic Leukemia Image Segmentation: Unveiling the Impact of Color Spaces and Clustering Techniques International Journal of Computers and their Applications, 2024
Design of a Secure Blockchain-Based Smart IoV Architecture Debashis Das, Sourav Banerjee, Wathiq Mansoor, Utpal Biswas, Pushpita Chatterjee, Uttam Ghosh 2020 3rd International Conference on Signal Processing and Information Security Icspis 2020, 2020
Challenges and approach for SHM technology transition Structural Health Monitoring 2011 Condition Based Maintenance and Intelligent Structures Proceedings of the 8th International Workshop on Structural Health Monitoring, 2011
On the performance quantification of active sensing SHM systems using model-assisted POD methods Structural Health Monitoring 2011 Condition Based Maintenance and Intelligent Structures Proceedings of the 8th International Workshop on Structural Health Monitoring, 2011
RAPID system for hot spot corrosion monitoring of Gas pipelines Structural Health Monitoring 2011 Condition Based Maintenance and Intelligent Structures Proceedings of the 8th International Workshop on Structural Health Monitoring, 2011
Large sensor network architectures for monitoring large-scale structures Structural Health Monitoring 2011 Condition Based Maintenance and Intelligent Structures Proceedings of the 8th International Workshop on Structural Health Monitoring, 2011
Health monitoring of composite structures using carbon nanotube and acoustic sensors Structural Health Monitoring 2011 Condition Based Maintenance and Intelligent Structures Proceedings of the 8th International Workshop on Structural Health Monitoring, 2011
Hot-spot fatigue and impact damage detection on a helicopter tailboom Structural Health Monitoring 2011 Condition Based Maintenance and Intelligent Structures Proceedings of the 8th International Workshop on Structural Health Monitoring, 2011
Statistical damage estimation at Hot Spots using Gaussian Mixture Model Structural Health Monitoring 2009 from System Integration to Autonomous Systems Proceedings of the 7th International Workshop on Structural Health Monitoring Iwshm 2009, 2009
Smartcomposite system for impact damage detection on composite structure Proceedings of SPIE the International Society for Optical Engineering, 2009
Real time active pipeline integrity detection system for direct assessment of corrosion Structural Health Monitoring 2009 from System Integration to Autonomous Systems Proceedings of the 7th International Workshop on Structural Health Monitoring Iwshm 2009, 2009
