arXiv subjects

Poonam Lohan

Publications and source records attributed to Poonam Lohan.

17 recordsLinked to original sources

arXiv2026

HALO: Hierarchical Auction-assisted Learning for Offloading in SAGIN

In this paper, we investigate delay-aware task offloading and resource scheduling in a three-tier space-air-ground integrated network (SAGIN) consisting of IoT devices, UAV edge nodes, and a high-altitude platform station (HAPS). We formulate joint task association and continuous resource control (including bandwidth, transmit power, and CPU frequency allocation) as a non-convex mixed-integer nonlinear programming (MINLP) problem, which is inherently NP-hard. To capture fine-grained system dynamics, we introduce a macro-micro slot model that tracks cumulative transmission and computation progress over time. Based on this model, we propose HALO, a hierarchical auction-assisted learning framework that combines auction-based task association with hierarchical Proximal Policy Optimization (HPPO) for resource allocation. Simulation results under different traffic loads show that HALO consistently outperforms representative deep reinforcement learning (DRL) baselines. In particular, HALO achieves an average improvement of 3.06 percentage points in task success rate over PPO (corresponding to a 3.4% relative gain) and shows consistently greater robustness than DDPG and SAC, with relative improvements of 10.6% and 4.8%, respectively. These results highlight HALO's ability to maintain stable and efficient performance under varying traffic conditions, making it well-suited for delay-sensitive SAGIN environments.

cs.NI↗

arXiv2026

A Lightweight Digital-Twin-Based Framework for Edge-Assisted Vehicle Tracking and Collision Prediction

Vehicle tracking, motion estimation, and collision prediction are fundamental components of traffic safety and management in Intelligent Transportation Systems (ITS). Many recent approaches rely on computationally intensive prediction models, which limits their practical deployment on resource-constrained edge devices. This paper presents a lightweight digital-twin-based framework for vehicle tracking and spatiotemporal collision prediction that relies solely on object detection, without requiring complex trajectory prediction networks. The framework is implemented and evaluated in Quanser Interactive Labs (QLabs), a high-fidelity digital twin of an urban traffic environment that enables controlled and repeatable scenario generation. A YOLO-based detector is deployed on simulated edge cameras to localize vehicles and extract frame-level centroid trajectories. Offline path maps are constructed from multiple traversals and indexed using K-D trees to support efficient online association between detected vehicles and road segments. During runtime, consistent vehicle identifiers are maintained, vehicle speed and direction are estimated from the temporal evolution of path indices, and future positions are predicted accordingly. Potential collisions are identified by analyzing both spatial proximity and temporal overlap of predicted future trajectories. Our experimental results across diverse simulated urban scenarios show that the proposed framework predicts approximately 88% of collision events prior to occurrence while maintaining low computational overhead suitable for edge deployment. Rather than introducing a computationally intensive prediction model, this work introduces a lightweight digital-twin-based solution for vehicle tracking and collision prediction, tailored for real-time edge deployment in ITS.

cs.CV↗

arXiv2026

Proactive SFC Provisioning with Forecast-Driven DRL in Data Centers

Service Function Chaining (SFC) requires efficient placement of Virtual Network Functions (VNFs) to satisfy diverse service requirements while maintaining high resource utilization in Data Centers (DCs). Conventional static resource allocation often leads to overprovisioning or underprovisioning due to the dynamic nature of traffic loads and application demands. To address this challenge, we propose a hybrid forecast-driven Deep reinforcement learning (DRL) framework that combines predictive intelligence with SFC provisioning. Specifically, we leverage DRL to generate datasets capturing DC resource utilization and service demands, which are then used to train deep learning forecasting models. Using Optuna-based hyperparameter optimization, the best-performing models, Spatio-Temporal Graph Neural Network, Temporal Graph Neural Network, and Long Short-Term Memory, are combined into an ensemble to enhance stability and accuracy. The ensemble predictions are integrated into the DC selection process, enabling proactive placement decisions that consider both current and future resource availability. Experimental results demonstrate that the proposed method not only sustains high acceptance ratios for resource-intensive services such as Cloud Gaming and VoIP but also significantly improves acceptance ratios for latency-critical categories such as Augmented Reality increases from 30% to 50%, while Industry 4.0 improves from 30% to 45%. Consequently, the prediction-based model achieves significantly lower E2E latencies of 20.5%, 23.8%, and 34.8% reductions for VoIP, Video Streaming, and Cloud Gaming, respectively. This strategy ensures more balanced resource allocation, and reduces contention.

cs.NI↗

arXiv2026

Structure-Aware NL-to-SQL for SFC Provisioning via AST-Masking Empowered Language Models

Effective Service Function Chain (SFC) provisioning requires precise orchestration in dynamic and latency-sensitive networks. Reinforcement Learning (RL) improves adaptability but often ignores structured domain knowledge, which limits generalization and interpretability. Large Language Models (LLMs) address this gap by translating natural language (NL) specifications into executable Structured Query Language (SQL) commands for specification-driven SFC management. Conventional fine-tuning, however, can cause syntactic inconsistencies and produce inefficient queries. To overcome this, we introduce Abstract Syntax Tree (AST)-Masking, a structure-aware fine-tuning method that uses SQL ASTs to assign weights to key components and enforce syntax-aware learning without adding inference overhead. Experiments show that AST-Masking significantly improves SQL generation accuracy across multiple language models. FLAN-T5 reaches an Execution Accuracy (EA) of 99.6%, while Gemma achieves the largest absolute gain from 7.5% to 72.0%. These results confirm the effectiveness of structure-aware fine-tuning in ensuring syntactically correct and efficient SQL generation for interpretable SFC orchestration.

cs.NI↗

arXiv2026

Spatiotemporal Semantic V2X Framework for Cooperative Collision Prediction

Intelligent Transportation Systems (ITS) demand real-time collision prediction to ensure road safety and reduce accident severity. Conventional approaches rely on transmitting raw video or high-dimensional sensory data from roadside units (RSUs) to vehicles, which is impractical under vehicular communication bandwidth and latency constraints. In this work, we propose a semantic V2X framework in which RSU-mounted cameras generate spatiotemporal semantic embeddings of future frames using the Video Joint Embedding Predictive Architecture (V-JEPA). To evaluate the system, we construct a digital twin of an urban traffic environment enabling the generation of d verse traffic scenarios with both safe and collision events. These embeddings of the future frame, extracted from V-JEPA, capture task-relevant traffic dynamics and are transmitted via V2X links to vehicles, where a lightweight attentive probe and classifier decode them to predict imminent collisions. By transmitting only semantic embeddings instead of raw frames, the proposed system significantly reduces communication overhead while maintaining predictive accuracy. Experimental results demonstrate that the framework with an appropriate processing method achieves a 10% F1-score improvement for collision prediction while reducing transmission requirements by four orders of magnitude compared to raw video. This validates the potential of semantic V2X communication to enable cooperative, real-time collision prediction in ITS.

cs.CV↗

arXiv2025

Semantic Edge-Cloud Communication for Real-Time Urban Traffic Surveillance with ViT and LLMs over Mobile Networks

Real-time urban traffic surveillance is vital for Intelligent Transportation Systems (ITS) to ensure road safety, optimize traffic flow, track vehicle trajectories, and prevent collisions in smart cities. Deploying edge cameras across urban environments is a standard practice for monitoring road conditions. However, integrating these with intelligent models requires a robust understanding of dynamic traffic scenarios and a responsive interface for user interaction. Although multimodal Large Language Models (LLMs) can interpret traffic images and generate informative responses, their deployment on edge devices is infeasible due to high computational demands. Therefore, LLM inference must occur on the cloud, necessitating visual data transmission from edge to cloud, a process hindered by limited bandwidth, leading to potential delays that compromise real-time performance. To address this challenge, we propose a semantic communication framework that significantly reduces transmission overhead. Our method involves detecting Regions of Interest (RoIs) using YOLOv11, cropping relevant image segments, and converting them into compact embedding vectors using a Vision Transformer (ViT). These embeddings are then transmitted to the cloud, where an image decoder reconstructs the cropped images. The reconstructed images are processed by a multimodal LLM to generate traffic condition descriptions. This approach achieves a 99.9% reduction in data transmission size while maintaining an LLM response accuracy of 89% for reconstructed cropped images, compared to 93% accuracy with original cropped images. Our results demonstrate the efficiency and practicality of ViT and LLM-assisted edge-cloud semantic communication for real-time traffic surveillance.

cs.NI↗

arXiv2025

FLARE: Flying Learning Agents for Resource Efficiency in Next-Gen UAV Networks

This letter addresses a critical challenge in the context of 6G and beyond wireless networks, the joint optimization of power and bandwidth resource allocation for aerial intelligent platforms, specifically uncrewed aerial vehicles (UAVs), operating in highly dynamic environments with mobile ground user equipment (UEs). We introduce FLARE (Flying Learning Agents for Resource Efficiency), a learning-enabled aerial intelligence framework that jointly optimizes UAV positioning, altitude, transmit power, and bandwidth allocation in real-time. To adapt to UE mobility, we employ Silhouette-based K-Means clustering, enabling dynamic grouping of users and UAVs' deployment at cluster centroids for efficient service delivery. The problem is modeled as a multi-agent control task, with bandwidth discretized into resource blocks and power treated as a continuous variable. To solve this, our proposed framework, FLARE, employs a hybrid reinforcement learning strategy that combines Multi-Agent Deep Deterministic Policy Gradient (MADDPG) and Deep Q-Network (DQN) to enhance learning efficiency. Simulation results demonstrate that our method significantly enhances user coverage, achieving a 73.45% improvement in the number of served users under a 5 Mbps data rate constraint, outperforming MADDPG baseline.

cs.NI↗

arXiv2025

LiLM-RDB-SFC: Lightweight Language Model with Relational Database-Guided DRL for Optimized SFC Provisioning

Effective management of Service Function Chains (SFCs) and optimal Virtual Network Function (VNF) placement are critical challenges in modern Software-Defined Networking (SDN) and Network Function Virtualization (NFV) environments. Although Deep Reinforcement Learning (DRL) is widely adopted for dynamic network decision-making, its inherent dependency on structured data and fixed action rules often limits adaptability and responsiveness, particularly under unpredictable network conditions. This paper introduces LiLM-RDB-SFC, a novel approach combining Lightweight Language Model (LiLM) with Relational Database (RDB) to answer network state queries to guide DRL model for efficient SFC provisioning. Our proposed approach leverages two LiLMs, Bidirectional and Auto-Regressive Transformers (BART) and the Fine-tuned Language Net T5 (FLAN-T5), to interpret network data and support diverse query types related to SFC demands, data center resources, and VNF availability. Results demonstrate that FLAN-T5 outperforms BART with a lower test loss (0.00161 compared to 0.00734), higher accuracy (94.79% compared to 80.2%), and less processing time (2h 2min compared to 2h 38min). Moreover, when compared to the large language model SQLCoder, FLAN-T5 matches the accuracy of SQLCoder while cutting processing time by 96% (SQLCoder: 54 h 43 min; FLAN-T5: 2 h 2 min).

cs.NI↗

arXiv2025

Multi-Agent Deep Reinforcement Learning for Optimized Multi-UAV Coverage and Power-Efficient UE Connectivity

In critical situations such as natural disasters, network outages, battlefield communication, or large-scale public events, Unmanned Aerial Vehicles (UAVs) offer a promising approach to maximize wireless coverage for affected users in the shortest possible time. In this paper, we propose a novel framework where multiple UAVs are deployed with the objective to maximize the number of served user equipment (UEs) while ensuring a predefined data rate threshold. UEs are initially clustered using a K-means algorithm, and UAVs are optimally positioned based on the UEs' spatial distribution. To optimize power allocation and mitigate inter-cluster interference, we employ the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm, considering both LOS and NLOS fading. Simulation results demonstrate that our method significantly enhances UEs coverage and outperforms Deep Q-Network (DQN) and equal power distribution methods, improving their UE coverage by up to 2.07 times and 8.84 times, respectively.

cs.NI↗

arXiv2025

Integrating Language Models for Enhanced Network State Monitoring in DRL-Based SFC Provisioning

Efficient Service Function Chain (SFC) provisioning and Virtual Network Function (VNF) placement are critical for enhancing network performance in modern architectures such as Software-Defined Networking (SDN) and Network Function Virtualization (NFV). While Deep Reinforcement Learning (DRL) aids decision-making in dynamic network environments, its reliance on structured inputs and predefined rules limits adaptability in unforeseen scenarios. Additionally, incorrect actions by a DRL agent may require numerous training iterations to correct, potentially reinforcing suboptimal policies and degrading performance. This paper integrates DRL with Language Models (LMs), specifically Bidirectional Encoder Representations from Transformers (BERT) and DistilBERT, to enhance network management. By feeding final VNF allocations from DRL into the LM, the system can process and respond to queries related to SFCs, DCs, and VNFs, enabling real-time insights into resource utilization, bottleneck detection, and future demand planning. The LMs are fine-tuned to our domain-specific dataset using Low-Rank Adaptation (LoRA). Results show that BERT outperforms DistilBERT with a lower test loss (0.28 compared to 0.36) and higher confidence (0.83 compared to 0.74), though BERT requires approximately 46% more processing time.

cs.NI↗

arXiv2025

Leveraging Multimodal-LLMs Assisted by Instance Segmentation for Intelligent Traffic Monitoring

A robust and efficient traffic monitoring system is essential for smart cities and Intelligent Transportation Systems (ITS), using sensors and cameras to track vehicle movements, optimize traffic flow, reduce congestion, enhance road safety, and enable real-time adaptive traffic control. Traffic monitoring models must comprehensively understand dynamic urban conditions and provide an intuitive user interface for effective management. This research leverages the LLaVA visual grounding multimodal large language model (LLM) for traffic monitoring tasks on the real-time Quanser Interactive Lab simulation platform, covering scenarios like intersections, congestion, and collisions. Cameras placed at multiple urban locations collect real-time images from the simulation, which are fed into the LLaVA model with queries for analysis. An instance segmentation model integrated into the cameras highlights key elements such as vehicles and pedestrians, enhancing training and throughput. The system achieves 84.3% accuracy in recognizing vehicle locations and 76.4% in determining steering direction, outperforming traditional models.

cs.AI↗

arXiv2024

Scalability Assurance in SFC provisioning via Distributed Design for Deep Reinforcement Learning

High-quality Service Function Chaining (SFC) provisioning is provided by the timely execution of Virtual Network Functions (VNFs) in a defined sequence. Advanced Deep Reinforcement Learning (DRL) solutions are utilized in many studies to contribute to fast and reliable autonomous SFC provisioning. However, under a large-scale network environment, centralized solutions might struggle to provide efficient outcomes when handling massive demands with stringent End-to-End (E2E) delay constraints. Therefore, in this paper, a novel distributed SFC provisioning framework is proposed, where the network is divided into several clusters. Each cluster has a dedicated local agent with a DRL module to handle the SFC provisioning of demands in that cluster. Also, there is a general agent that can communicate with local agents to handle the requests beyond their capacity. The DRL module of local agents can be applied under different configurations of clusters independent of different numbers of data centers and logical links in each cluster. Simulation results demonstrate that utilizing the proposed distributed framework offers up to 60% improvements in the acceptance ratio of service requests in comparison to the centralized approach while minimizing the E2E delay of accepted requests.

cs.NI↗

arXiv2024

Leveraging Edge Intelligence and LLMs to Advance 6G-Enabled Internet of Automated Defense Vehicles

The evolution of Artificial Intelligence (AI) and its subset Deep Learning (DL), has profoundly impacted numerous domains, including autonomous driving. The integration of autonomous driving in military settings reduces human casualties and enables precise and safe execution of missions in hazardous environments while allowing for reliable logistics support without the risks associated with fatigue-related errors. However, relying on autonomous driving solely requires an advanced decision-making model that is adaptable and optimum in any situation. Considering the presence of numerous interconnected autonomous vehicles in mission-critical scenarios, Ultra-Reliable Low Latency Communication (URLLC) is vital for ensuring seamless coordination, real-time data exchange, and instantaneous response to dynamic driving environments. The advent of 6G strengthens the Internet of Automated Defense Vehicles (IoADV) concept within the realm of Internet of Military Defense Things (IoMDT) by enabling robust connectivity, crucial for real-time data exchange, advanced navigation, and enhanced safety features through IoADV interactions. On the other hand, a critical advancement in this space is using pre-trained Generative Large Language Models (LLMs) for decision-making and communication optimization for autonomous driving. Hence, this work presents opportunities and challenges with a vision of realizing the full potential of these technologies in critical defense applications, especially through the advancement of IoADV and its role in enhancing autonomous military operations.

cs.NI↗

arXiv2024

GenAI Assistance for Deep Reinforcement Learning-based VNF Placement and SFC Provisioning in 5G Cores

Virtualization technology, Network Function Virtualization (NFV), gives flexibility to communication and 5G core network technologies for dynamic and efficient resource allocation while reducing the cost and dependability of the physical infrastructure. In the NFV context, Service Function Chain (SFC) refers to the ordered arrangement of various Virtual Network Functions (VNFs). To provide an automated SFC provisioning algorithm that satisfies high demands of SFC requests having ultra-reliable and low latency communication (URLLC) requirements, in the literature, Artificial Intelligence (AI) modules and Deep Reinforcement Learning (DRL) algorithms are investigated in detail. This research proposes a generative Variational Autoencoder (VAE) assisted advanced-DRL module for handling SFC requests in a dynamic environment where network configurations and request amounts can be changed. Using the hybrid approach, including generative VAE and DRL, the algorithm leverages several advantages, such as dimensionality reduction, better generalization on the VAE side, exploration, and trial-error learning from the DRL model. Results show that GenAI-assisted DRL surpasses the state-of-the-art model of DRL in SFC provisioning in terms of SFC acceptance ratio, E2E delay, and throughput maximization.

cs.NI↗

arXiv2024

A Novel Joint DRL-Based Utility Optimization for UAV Data Services

In this paper, we propose a novel joint deep reinforcement learning (DRL)-based solution to optimize the utility of an uncrewed aerial vehicle (UAV)-assisted communication network. To maximize the number of users served within the constraints of the UAV's limited bandwidth and power resources, we employ deep Q-Networks (DQN) and deep deterministic policy gradient (DDPG) algorithms for optimal resource allocation to ground users with heterogeneous data rate demands. The DQN algorithm dynamically allocates multiple bandwidth resource blocks to different users based on current demand and available resource states. Simultaneously, the DDPG algorithm manages power allocation, continuously adjusting power levels to adapt to varying distances and fading conditions, including Rayleigh fading for non-line-of-sight (NLoS) links and Rician fading for line-of-sight (LoS) links. Our joint DRL-based solution demonstrates an increase of up to 41% in the number of users served compared to scenarios with equal bandwidth and power allocation.

cs.NI↗

arXiv2024

A New Realistic Platform for Benchmarking and Performance Evaluation of DRL-Driven and Reconfigurable SFC Provisioning Solutions

Service Function Chain (SFC) provisioning stands as a pivotal technology in the realm of 5G and future networks. Its essence lies in orchestrating VNFs (Virtual Network Functions) in a specified sequence for different types of SFC requests. Efficient SFC provisioning requires fast, reliable, and automatic VNFs' placements, especially in a network where massive amounts of SFC requests are generated having ultra-reliable and low latency communication (URLLC) requirements. Although much research has been done in this area, including Artificial Intelligence (AI) and Machine Learning (ML)-based solutions, this work presents an advanced Deep Reinforcement Learning (DRL)-based simulation model for SFC provisioning that illustrates a realistic environment. The proposed simulation platform can handle massive heterogeneous SFC requests having different characteristics in terms of VNFs chain, bandwidth, and latency constraints. Also, the model is flexible to apply to networks having different configurations in terms of the number of data centers (DCs), logical connections among DCs, and service demands. The simulation model components and the workflow of processing VNFs in the SFC requests are described in detail. Numerical results demonstrate that using this simulation setup and proposed algorithm, a realistic SFC provisioning can be achieved with an optimal SFC acceptance ratio while minimizing the E2E latency and resource consumption.

cs.NI↗

arXiv2019

Utility-Aware Optimal Resource Allocation Protocol for UAV-Assisted Small Cells with Heterogeneous Coverage Demands

In this paper, we consider a UAV-assisted small-cell having heterogeneous users with different data rates and coverage demands. Specifically, we propose a novel utility-aware resource-allocation protocol to maximize the utility of UAV by allowing it to simultaneously serve the highest possible number of heterogeneous users with available energy resources. In this regard, first, we derive a closed-form expression for the rate-coverage probability of a user considering Rician fading to incorporate the strong line of sight (LoS) component in UAV communication. Next, since this UAV utility maximization problem is non-convex and combinatorial, to obtain the global optimal resource allocation policy we propose an iterative feasibility checking method for fixed integers ranging from lower to upper bound on the number of users that can be served by UAV. To further reduce the complexity, we formulate an equivalent problem aimed at minimizing per user energy consumption, where tight analytical relaxation on rate-coverage probability constraint is used along with semi-closed expressions for joint-optimal power and time allocation. Lastly, via detailed numerical investigation, we validate our analytical claims, present insights on the impact of key system parameters, and demonstrate that 60% more users can be served using the proposed scheme, as compared to relevant benchmarks.

cs.IT↗