Lyapunov Optimization with Virtual Queues (LOVQ) is proposed, a task offloading framework based on the Lyapunov Drift Plus Penalty method that jointly optimizes energy consumption and delay while ensuring long-term system stability.
V. Verma, Pushkar, Bablu Kumar et al.· Discover Computing· 0 citations
The proposed work presents a convolutional neural network, hereafter referred to as CNN4WFD, based on transfer learning and built on an improved version of an Xception architecture, which is used to detect wildfires, outperforming traditional CNN baselines both in accuracy and computational efficiency.
MobileNetV3 provides the most balanced trade-off among the evaluated models between classification accuracy, robustness, and computational efficiency, and these evaluated performances indicate the potential of the HMSLD framework.
Kanak Kumar, Anshul Verma, Pradeepika Verma· Proceedings of the National...· 0 citations
A double deep Q-Network-based proactive autoscaling approach (DDQN-Proactive) along with Resource Removal Strategy (RRS) that enhances decision-making by decoupling action selection from value evaluation, enabling more stable and adaptive scaling.
An integrated framework that combines LLM fine-tuning using federated adaptive local low-rank adaptation (FedALoRA) with forecasting-driven autoscaling policies is proposed, making it well-suited for federated-LLM Autoscaling in dynamic edge environments.