arXiv subjects

Basabdatta Palit

Publications and source records attributed to Basabdatta Palit.

10 recordsLinked to original sources

arXiv2025

FedNET: Federated Learning for Proactive Traffic Management and Network Capacity Planning

We propose FedNET, a proactive and privacy-preserving framework for early identification of high-risk links in large-scale communication networks, that leverages a distributed multi-step traffic forecasting method. FedNET employs Federated Learning (FL) to model the temporal evolution of node-level traffic in a distributed manner, enabling accurate multi-step-ahead predictions (e.g., several hours to days) without exposing sensitive network data. Using these node-level forecasts and known routing information, FedNET estimates the future link-level utilization by aggregating traffic contributions across all source-destination pairs. The links are then ranked according to the predicted load intensity and temporal variability, providing an early warning signal for potential high-risk links. We compare the federated traffic prediction of FedNET against a centralized multi-step learning baseline and then systematically analyze the impact of history and prediction window sizes on forecast accuracy using the $R^2$ score. Results indicate that FL achieves accuracy close to centralized training, with shorter prediction horizons consistently yielding the highest accuracy ($R^2 >0.92$), while longer horizons providing meaningful forecasts ($R^2 \approx 0.45\text{--}0.55$). We further validate the efficacy of the FedNET framework in predicting network utilization on a realistic network topology and demonstrate that it consistently identifies high-risk links well in advance (i.e., three days ahead) of the critical stress states emerging, making it a practical tool for anticipatory traffic engineering and capacity planning.

cs.LG↗

arXiv2025

Federated Learning for Deforestation Detection: A Distributed Approach with Satellite Imagery

Accurate identification of deforestation from satellite images is essential in order to understand the geographical situation of an area. This paper introduces a new distributed approach to identify as well as locate deforestation across different clients using Federated Learning (FL). Federated Learning enables distributed network clients to collaboratively train a model while maintaining data privacy and security of the active users. In our framework, a client corresponds to an edge satellite center responsible for local data processing. Moreover, FL provides an advantage over centralized training method which requires combining data, thereby compromising with data security of the clients. Our framework leverages the FLOWER framework with RAY framework to execute the distributed learning workload. Furthermore, efficient client spawning is ensured by RAY as it can select definite amount of users to create an emulation environment. Our FL framework uses YOLOS-small (a Vision Transformer variant), Faster R-CNN with a ResNet50 backbone, and Faster R-CNN with a MobileNetV3 backbone models trained and tested on publicly available datasets. Our approach provides us a different view for image segmentation-based tasks on satellite imagery.

cs.CV↗

arXiv2025

Trusted Repeater Placement in QKD-enabled Optical Networks

Quantum Key Distribution (QKD) provides information-theoretic security, but is limited by distance in optical networks, thereby requiring repeater nodes to extend coverage. Existing works usually assume all repeater nodes and associated Key Management Servers (KMSs) to be Trusted Repeater Nodes (TRNs), while ignoring risks from software exploits and insider threats. In this paper, we propose a reliability-aware TRN placement framework for metro optical networks, which assigns each node a trust score and integrates it into the Dijkstra algorithm via weighted links. We then rank the nodes using a composite score, which is a weighted combination of betweenness centrality and eigenvector centrality to enable a secure and scalable TRN deployment. Simulation results on a reference topology show that our method covers 10.77% more shortest paths compared to traditional metrics like degree centrality, using the same number (around eight) of TRNs, making it suitable for TRN selection to maximize secure connectivity.

cs.NI↗

arXiv2025

Benchmarking Federated Learning for Throughput Prediction in 5G Live Streaming Applications

Accurate and adaptive network throughput prediction is essential for latency-sensitive and bandwidth-intensive applications in 5G and emerging 6G networks. However, most existing methods rely on centralized training with uniformly collected data, limiting their applicability in heterogeneous mobile environments with non-IID data distributions. This paper presents the first comprehensive benchmarking of federated learning (FL) strategies for throughput prediction in realistic 5G edge scenarios. We evaluate three aggregation algorithms - FedAvg, FedProx, and FedBN - across four time-series architectures: LSTM, CNN, CNN+LSTM, and Transformer, using five diverse real-world datasets. We systematically analyze the effects of client heterogeneity, cohort size, and history window length on prediction performance. Our results reveal key trade-offs among model complexities, convergence rates, and generalization. It is found that FedBN consistently delivers robust performance under non-IID conditions. On the other hand, LSTM and Transformer models outperform CNN-based baselines by up to 80% in R2 scores. Moreover, although Transformers converge in half the rounds of LSTM, they require longer history windows to achieve a high R2, indicating higher context dependence. LSTM is, therefore, found to achieve a favorable balance between accuracy, rounds, and temporal footprint. To validate the end-to-end applicability of the framework, we have integrated our FL-based predictors into a live adaptive streaming pipeline. It is seen that FedBN-based LSTM and Transformer models improve mean QoE scores by 11.7% and 11.4%, respectively, over FedAvg, while also reducing the variance. These findings offer actionable insights for building scalable, privacy-preserving, and edge-aware throughput prediction systems in next-generation wireless networks.

cs.DC↗

arXiv2024

A Lightweight QoS-Aware Resource Allocation Method for NR-V2X Networks

Vehicle-to-Everything (V2X) communication, which includes Vehicle-to-Infrastructure (V2I), Vehicle-to-Vehicle (V2V), and Vehicle-to-Pedestrian (V2P) networks, is gaining significant attention due to the rise of connected and autonomous vehicles. V2X systems require diverse Quality of Service (QoS) provisions, with V2V communication demanding stricter latency and reliability compared to V2I. The 5G New Radio-V2X (NR-V2X) standard addresses these needs using multi-numerology Orthogonal Frequency Division Multiple Access (OFDMA), which allows for flexible allocation of radio resources. However, V2I and V2V users sharing the same radio resources leads to interference, necessitating efficient power and resource allocation. In this work, we propose a novel resource allocation and sharing algorithm for 5G-based V2X systems. Our approach first groups Resource Blocks (RBs) into Resource Chunks (RCs) and allocates them to V2I users using the Gale-Shapley stable matching algorithm. Power is then allocated to RCs to facilitate efficient resource sharing between V2I and V2V users through a bisection search method. Finally, the Gale-Shapley algorithm is used to pair V2I and V2V users, maintaining low computational complexity while ensuring high performance. Simulation results demonstrate that our proposed Gale-Shapley Resource Allocation with Gale-Shapley Sharing (GSRAGS) achieves competitive performance with lower complexity compared to existing works while effectively meeting the QoS demands of V2X communication systems.

cs.NI↗

arXiv2024

Performance Analysis of Resource Allocation Algorithms for Vehicle Platoons over 5G eV2X Communication

Vehicle platooning is a cooperative driving technology that can be supported by 5G enhanced Vehicle-to-Everything (eV2X) communication to improve road safety, traffic efficiency, and reduce fuel consumption. eV2X communication among the platoon vehicles involves the periodic exchange of Cooperative Awareness Messages (CAMs) containing vehicle information under strict latency and reliability requirements. These requirements can be maintained by administering the assignment of resources, in terms of time slots and frequency bands, for CAM exchanges in a platoon, with the help of a resource allocation mechanism. State-of-the-art on control and communication design for vehicle platoons either consider a simplified platoon model with a detailed communication architecture or consider a simplified communication delay model with a detailed platoon control system. Departing from existing works, we have developed a comprehensive vehicle platoon communication and control framework using OMNET++, the benchmarking network simulation tool. We have carried out an inclusive and comparative study of three different platoon Information Flow Topologies (IFTs), namely Car-to-Server, Multi-Hop, and One-Hop over 5G using the Predecessor-leader following platoon control law to arrive at the best-suited IFT for platooning. Secondly, for the best-suited 5G eV2X platooning IFT selected, we have analyzed the performance of three different resource allocation algorithms, namely Maximum of Carrier to Interference Ratio (MaxC/I), Proportional Fair (PF), and Deficit Round Robin (DRR). Exhaustive system-level simulations show that the One-Hop information flow strategy along with the MaxC/I resource allocation yields the best Quality of Service (QoS) performance, in terms of latency, reliability, Age of Information (AoI), and throughput.

cs.NI↗

arXiv2023

A Kalman Filter based Low Complexity Throughput Prediction Algorithm for 5G Cellular Networks

Throughput Prediction is one of the primary preconditions for the uninterrupted operation of several network-aware mobile applications, namely video streaming. Recent works have advocated using Machine Learning (ML) and Deep Learning (DL) for cellular network throughput prediction. In contrast, this work has proposed a low computationally complex simple solution which models the future throughput as a multiple linear regression of several present network parameters and present throughput. It then feeds the variance of prediction error and measurement error, which is inherent in any measurement setup but unaccounted for in existing works, to a Kalman filter-based prediction-correction approach to obtain the optimal estimates of the future throughput. Extensive experiments across seven publicly available 5G throughput datasets for different prediction window lengths have shown that the proposed method outperforms the baseline ML and DL algorithms by delivering more accurate results within a shorter timeframe for inferencing and retraining. Furthermore, in comparison to its ML and DL counterparts, the proposed throughput prediction method is also found to deliver higher QoE to both streaming and live video users when used in conjunction with popular Model Predictive Control (MPC) based adaptive bitrate streaming algorithms.

cs.NI↗

arXiv2023

A QoS-Aware Uplink Spectrum and Power Allocation with Link Adaptation for Vehicular Communications in 5G networks

In this work, we have proposed link adaptation-based joint spectrum and power allocation algorithms for the uplink communication in 5G Cellular Vehicle-to-Everything (C-V2X) systems. In C-V2X, vehicle-to-vehicle (V2V) users share radio resources with vehicle-to-infrastructure (V2I) users. Existing works primarily focus on the optimal pairing of V2V and V2I users, assuming that each V2I user needs a single resource block (RB) while minimizing interference through power allocation. In contrast, in this work, we have considered that the number of RBs needed by the users is a function of their channel condition and Quality of Service (QoS) - a method called link adaptation. It effectively compensates for the frequent channel quality fluctuations at the high frequencies of 5G communication.5G uses a multi-numerology frame structure to support diverse QoS requirements, which has also been considered in this work. The first algorithm proposed in this article greedily allocates RBs to V2I users using link adaptation. It then uses the Hungarian algorithm to pair V2V with V2I users while minimizing interference through power allocation. The second proposed method groups RBs into resource chunks (RCs) and uses the Hungarian algorithm twice - first to allocate RCs to V2I users and then to pair V2I users with V2V users. Extensive simulations reveal that link adaptation increases the number of satisfied V2I users and their sum rate while also improving the QoS of V2I and V2V users, making it indispensable for 5G C-V2X systems.

cs.NI↗

arXiv2023

Improving UE Energy Efficiency through Network-aware Video Streaming over 5G

Adaptive Bitrate (ABR) Streaming over the cellular networks has been well studied in the literature; however, existing ABR algorithms primarily focus on improving the end-users' Quality of Experience (QoE) while ignoring the resource consumption aspect of the underlying device. Consequently, proactive attempts to download video data to maintain the user's QoE often impact the battery life of the underlying device unless the download attempts are synchronized with the network's channel condition. In this work, we develop EnDASH-5G -- a wrapper over the popular DASH-based ABR streaming algorithm, which establishes this synchronization by utilizing a network-aware video data download mechanism. EnDASH-5G utilizes a novel throughput prediction mechanism for 5G mmWave networks by upgrading the existing throughput prediction models with a transfer learning-based approach leveraging publicly available 5G datasets. It then exploits deep reinforcement learning to dynamically decide the playback buffer length and the video bitrate using the predicted throughput. This ensures that the data download attempts get synchronized with the underlying network condition, thus saving the device's battery power. From a thorough evaluation of EnDASH-5G, we observe that it achieves a near $30.5\%$ decrease in the maximum energy consumption than the state-of-the-art Pensieve ABR algorithm while performing almost at par in QoE.

cs.NI↗

arXiv2023

Revisiting Cellular Throughput Prediction over the Edge: Collaborative Multi-device, Multi-network in-situ Learning

Pervasive applications over large-scale, distributed embedded devices and the Internet of Things (IoT) demand precise coordination with the network; for example, several such applications, like collaborative video streaming and live analysis, augmented reality, etc., need continuous monitoring of network throughput and adapt the application behavior accordingly. Although the idea of network throughput prediction is not new and quite dated, in this paper, we show that the existing approaches fail to correctly infer the throughput when the network operator or the device change, and thus, not generic enough for Internet-scale applications. We propose \ourmethod, a novel approach that allows collaborative training across different client hardware by capturing throughput variations based on devices' sensitivity towards the corresponding network configurations. Rigorous evaluations show that \ourmethod{} outperforms various standard baseline algorithms with more than $80\%$ R2-score over different datasets. We also analyze the performance of \ourmethod{} over a network-aware streaming media application and demonstrate its efficacy for various application scenarios.

cs.NI↗