arXiv subjects

Samiran Chattopadhyay

Publications and source records attributed to Samiran Chattopadhyay.

25 records · Page 2Linked to original sources

arXiv2022

Mobility Management in 5G and Beyond: A Novel Smart Handover with Adaptive Time-to-Trigger and Hysteresis Margin

The 5th Generation (5G) New Radio (NR) and beyond technologies will support enhanced mobile broadband, very low latency communications, and huge numbers of mobile devices. Therefore, for very high speed users, seamless mobility needs to be maintained during the migration from one cell to another in the handover. Due to the presence of a massive number of mobile devices, the management of the high mobility of a dense network becomes crucial. Moreover, a dynamic adaptation is required for the Time-to-Trigger (TTT) and hysteresis margin, which significantly impact the handover latency and overall throughput. Therefore, in this paper, we propose an online learning-based mechanism, known as Learning-based Intelligent Mobility Management (LIM2), for mobility management in 5G and beyond, with an intelligent adaptation of the TTT and hysteresis values. LIM2 uses a Kalman filter to predict the future signal quality of the serving and neighbor cells, selects the target cell for the handover using state-action-reward-state-action (SARSA)-based reinforcement learning, and adapts the TTT and hysteresis using the epsilon-greedy policy. We implement a prototype of the LIM2 in NS-3 and extensively analyze its performance, where it is observed that the LIM2 algorithm can significantly improve the handover operation in very high speed mobility scenarios.

cs.NI↗

arXiv2021

SmartCon: Deep Probabilistic Learning Based Intelligent Link-Configuration in Narrowband-IoT Towards 5G and B5G

To enhance the coverage and transmission reliability, repetitions adopted by Narrowband Internet of Things (NB-IoT) allow repeating transmissions several times. However, this results in a waste of radio resources when the signal strength is high. In addition, in low signal quality, the selection of a higher modulation and coding scheme (MCS) level leads to a huge packet loss in the network. Moreover, the number of physical resource blocks (PRBs) per-user needs to be chosen dynamically, such that the utilization of radio resources can be improved on per-user basis. Therefore, in NB-IoT systems, dynamic adaptation of repetitions, MCS, and radio resources, known as auto link-configuration, is crucial. Accordingly, in this paper, we propose SmartCon which is a Generative Adversarial Network (GAN)-based deep learning approach for auto link-configuration during uplink or downlink scheduling, such that the packet loss rate is significantly reduced in NB-IoT networks. For the training purpose of the GAN, we use a Multi-Armed Bandit (MAB)-based reinforcement learning mechanism that intelligently tunes its output depending on the present network condition. The performance of SmartCon is thoroughly evaluated through simulations where it is shown to significantly improve the performance of NB-IoT systems compared to baseline schemes.

cs.NI↗

arXiv2020

Segmenting Scientific Abstracts into Discourse Categories: A Deep Learning-Based Approach for Sparse Labeled Data

The abstract of a scientific paper distills the contents of the paper into a short paragraph. In the biomedical literature, it is customary to structure an abstract into discourse categories like BACKGROUND, OBJECTIVE, METHOD, RESULT, and CONCLUSION, but this segmentation is uncommon in other fields like computer science. Explicit categories could be helpful for more granular, that is, discourse-level search and recommendation. The sparsity of labeled data makes it challenging to construct supervised machine learning solutions for automatic discourse-level segmentation of abstracts in non-bio domains. In this paper, we address this problem using transfer learning. In particular, we define three discourse categories BACKGROUND, TECHNIQUE, OBSERVATION-for an abstract because these three categories are the most common. We train a deep neural network on structured abstracts from PubMed, then fine-tune it on a small hand-labeled corpus of computer science papers. We observe an accuracy of 75% on the test corpus. We perform an ablation study to highlight the roles of the different parts of the model. Our method appears to be a promising solution to the automatic segmentation of abstracts, where the labeled data is sparse.

cs.CL↗

arXiv2017

Impact of IEEE 802.11n/ac PHY/MAC High Throughput Enhancements over Transport/Application Layer Protocols - A Survey

Since the inception of Wireless Local Area Networks (WLANs) in the year 1997, it has tremendously grown in the last few years. IEEE 802.11 is popularly known as WLAN. To provide the last mile wireless broadband connectivity to users, IEEE 802.11 is enriched with IEEE 802.11a, IEEE 802.11b and IEEE 802.11g. More recently, IEEE 802.11n, IEEE 802.11ac and IEEE 802.11ad are introduced with enhancements to the physical (PHY) layer and medium access control (MAC) sublayer to provide much higher data rates and thus these amendments are called High Throughput WLANs (HT-WLANs). For both standards, PHY is enhanced with multiple-input multiple-output (MIMO) antenna technologies, channel bonding, short guard intervals (SGI), enhanced modulation and coding schemes (MCS). At the same time, MAC layer overhead is reduced by introducing frame aggregation and block acknowledgement technologies. However, existing studies reveal that although PHY and MAC enhancements promise to improve physical data rate significantly, they yield negative impact over upper layer protocols -- mainly for reliable end-to-end transport/application layer protocols. As a consequence, a large number of schools have focused researches on HT-WLANs to improve the coordination among PHY/MAC and upper layer protocols and thus, boost up the performance benefit. In this survey, we discuss the impact of enhancements of PHY/MAC layer in HT-WLANs over transport/application layer protocols. list down different open challenges that can be explored for the development of next generation HT-WLAN technologies.

cs.NI↗

arXiv2014

Understanding the Mechanics of Some Localized Protocols by Theory of Complex Networks

In the study of ad hoc sensor networks, clustering plays an important role in energy conservation therefore analyzing the mechanics of such topology can be helpful to make logistic decisions .Using the theory of complex network the topological model is extended, where we account for the probability of preferential attachment and anti preferential attachment policy of sensor nodes to analyze the formation of clusters and calculate the probability of clustering. The theoretical analysis is conducted to determine nature of topology and quantify some of the observed facts during the execution of topology control protocols. The quantification of the observed facts leads to the alternative understanding of the energy efficiency of the routing protocols.

cs.NI↗

arXiv2013

Designing an Efficient Delay Sensitive Routing Metric for IEEE 802.16 Mesh Networks

Quality of Service provisioning is one of the major design goals of IEEE 802.16 mesh networks. In order to provide quality delivery of delay sensitive services such as voice, video etc., it is required to route such traffic over a minimum delay path. In this paper we propose a routing metric for delay sensitive services in IEEE 802.16 mesh networks. We design a new cross layer routing metric, namely Expected Scheduler Delay (ESD), based on HoldOff exponent and the current load at each node of the network. This proposed metric takes into account the expected theoretical end-to-end delay of routing paths as well as network congestion to find the best suited path. We propose an efficient distributed scheme to calculate ESD and route the packets using source routing mechanism based on ESD. The simulation results demonstrate that our metric achieves reduced delay compared to a standard scheme used in IEEE 802.16 mesh, that takes hop count to find the path.

cs.NI↗

arXiv2010

Constructing Path Efficient and Energy Aware Virtual Multicast Backbones in Static Ad Hoc Wireless Networks

For stationary wireless ad hoc networks, one of the key challenging issues in routing and multicasting is to conserve as much energy as possible without compromising path efficiency measured as end-to-end delay. In this paper, we address the problem of path efficient and energy aware multicasting in static wireless ad hoc networks. We propose a novel distributed scalable algorithm for finding a virtual multicast backbone (VMB). Based on this VMB, we have further developed a multicasting scheme that jointly improves path efficiency and energy conservation. By exploiting inherent broadcast advantage of wireless communication and employing a more realistic energy consumption model for wireless communication which not only depends on radio propagation losses but also on energy losses in transceiver circuitry, our simulation results show that the proposed VMB-based multicasting scheme outperforms existing prominent tree based energy conserving, path efficient multicasting schemes.

cs.NI↗