arXiv subjects

Jyotsna Bapat

Publications and source records attributed to Jyotsna Bapat.

At least 19 recordsLinked to original sources

arXiv2026

Load Balanced ISAC Systems for URLLC Users

This paper presents an energy-efficient downlink cell-free massive multiple-input multiple-output (CF-mMIMO) integrated sensing and communication (ISAC) network that serves ultra-reliable low-latency communication (URLLC) users while simultaneously detecting a target. We propose a load-balancing algorithm that minimizes the total network power consumption; including transmit power, fixed static power, and traffic-dependent fronthaul power at the access points (APs) without degrading system performance. To this end, we formulate a mixed-integer non-convex optimization problem and introduce an iterative joint power allocation and AP load balancing (JPALB) algorithm. The algorithm aims to reduce total power usage while meeting both the communication quality-of-service (QoS) requirements of URLLC users and the sensing QoS needed for target detection. Proposed JPALB algorithm for ISAC systems was simulated with maximum-ratio transmission (MRT) and regularized zero-forcing (RZF) precoders. Simulation results show approximately 33% reduction in power consumption, using JPALB algorithm compared to a baseline with no load balancing, without compromising communication and sensing QoS requirements.

cs.IT↗

arXiv2025

A Novel Integrated Architecture for Intent Based Approach and Zero Touch Networks

The transition to Sixth Generation (6G) networks presents challenges in managing quality of service (QoS) of diverse applications and achieving Service Level Agreements (SLAs) under varying network conditions. Hence, network management must be automated with the help of Machine Learning (ML) and Artificial Intelligence (AI) to achieve real-time requirements. Zero touch network (ZTN) is one of the frameworks to automate network management with mechanisms such as closed loop control to ensure that the goals are met perpetually. Intent- Based Networking (IBN) specifies the user intents with diverse network requirements or goals which are then translated into specific network configurations and actions. This paper presents a novel architecture for integrating IBN and ZTN to serve the intent goals. Users provides the intent in the form of natural language, e.g., English, which is then translated using natural language processing (NLP) techniques (e.g., retrieval augmented generation (RAG)) into Network Intent LanguagE (Nile). The Nile intent is then passed on to the BiLSTM and Q-learning based ZTN closed loop framework as a goal which maintains the intent under varying network conditions. Thus, the proposed architecture can work autonomously to ensure the network performance goal is met by just specifying the user intent in English. The integrated architecture is also implemented on a testbed using OpenAirInterface (OAI). Additionally, to evaluate the architecture, an optimization problem is formulated which evaluated with Monte Carlo simulations. Results demonstrate how ZTN can help achieve the bandwidth goals autonomously set by user intent. The simulation and the testbed results are compared and they show similar trend. Mean Opinion Score (MOS) for Quality of Experience (QoE) is also measured to indicate the user satisfaction of the intent.

cs.NI↗

arXiv2025

Digital Twin Assisted Proactive Management in Zero Touch Networks

The rapid expansion of cellular networks and rising demand for high-quality services require efficient and autonomous network management solutions. Zero Touch Network (ZTN) management has emerged as a key approach to automating network operations, minimizing manual intervention, and improving service reliability. Digital Twin (DT) creates a virtual representation of the physical network in realtime, allowing continuous monitoring, predictive analytics, and intelligent decision-making by simulating what-if scenarios. This paper integrates DT with ZTN proactive bandwidth management in end-to-end (E2E) next-generation networks. The integrated architecture applies Few-Shot Learning (FSL) to a memoryaugmented Bidirectional Long Short Term Memory (BiLSTM) model to predict a new network state to augment the known and trained states. Using Q-learning, it determines the optimal action (e.g. traffic shaping) under varying network conditions such that user Quality of Service (QoS) requirements are met. Three scenarios have been considered: 1) normal ZTN operation with closed-loop control, 2) a what-if scenario of DT, and 3) network state unknown to DT. The simulation results show that the network can adapt to underlying changing conditions. In addition, DT-assisted ZTN achieves better performance than the other techniques.

cs.NI↗

arXiv2025

Connecting the Unconnected -- Sentiment Analysis of Field Survey of Internet Connectivity in Emerging Economies

Internet has significantly improved the quality of citizens across the world. Though the internet coverage is quite high, 40% of global population do not have access to broadband internet. This paper presents an analysis of a field survey of population in some areas of Kathmandu, Nepal, an emerging economy. This survey was triggered by intermittent severe congestion of internet in certain areas of the city. People from three different areas were asked about their present experience of internet usage, its impact on their lives and their aspirations for the future. Survey pointed to high speed, low cost, reliable and secure internet as a major aspiration of the respondents. Based on their inputs, this paper presents a sentiment analysis as well as demographic information. Keys insights from this analysis shows that overall sentiment to most queries are positive. The variances of positive sentiments are high whereas those for negative ones are low. Also, some correlations and clusters are observed among the attributes though no dominant component exists in the data.

cs.CY↗

arXiv2025

Novel Closed Loop Control Mechanism for Zero Touch Networks using BiLSTM and Q-Learning

As networks advance toward the Sixth Generation (6G), management of high-speed and ubiquitous connectivity poses major challenges in meeting diverse Service Level Agreements (SLAs). The Zero Touch Network (ZTN) framework has been proposed to automate and optimize network management tasks. It ensures SLAs are met effectively even during dynamic network conditions. Though, ZTN literature proposes closed-loop control, methods for implementing such a mechanism remain largely unexplored. This paper proposes a novel two-stage closedloop control for ZTN to optimize the network continuously. First, an XGBoosted Bidirectional Long Short Term Memory (BiLSTM) model is trained to predict the network state (in terms of bandwidth). In the second stage, the Q-learning algorithm selects actions based on the predicted network state to optimize Quality of Service (QoS) parameters. By selecting appropriate actions, it serves the applications perpetually within the available resource limits in a closed loop. Considering the scenario of network congestion, with available bandwidth as state and traffic shaping options as an action for mitigation, results show that the proposed closed-loop mechanism can adjust to changing network conditions. Simulation results show that the proposed mechanism achieves 95% accuracy in matching the actual network state by selecting the appropriate action based on the predicted state.

cs.NI↗

arXiv2025

Connectivity for AI enabled cities -- A field survey based study of emerging economies

The impact of Artificial Intelligence (AI) is transforming various aspects of urban life, including, governance, policy and planning, healthcare, sustainability, economics, entrepreneurship, etc. Although AI immense potential for positively impacting urban living, its success depends on overcoming significant challenges, particularly in telecommunications infrastructure. Smart city applications, such as, federated learning, Internet of Things (IoT), and online financial services, require reliable Quality of Service (QoS) from telecommunications networks to ensure effective information transfer. However, with over three billion people underserved or lacking access to internet, many of these AI-driven applications are at risk of either remaining underutilized or failing altogether. Furthermore, many IoT and video-based applications in densely populated urban areas require high-quality connectivity. This paper explores these issues, focusing on the challenges that need to be mitigated to make AI succeed in emerging countries, where more than 80% of the world population resides and urban migration grows. In this context, an overview of a case study conducted in Kathmandu, Nepal, highlights citizens' aspirations for affordable, high-quality internet-based services. The findings underscore the pressing need for advanced telecommunication networks to meet diverse user requirements while addressing investment and infrastructure gaps. This discussion provides insights into bridging the digital divide and enabling AI's transformative potential in urban areas.

cs.CY↗

arXiv2024

Target Detection for OTFS-Aided Cell-Free MIMO ISAC System

This letter focuses on enhancing target detection performance for a multi-user integrated sensing and communication (ISAC) system using orthogonal time frequency space (OTFS)-aided cell-free multiple-input multiple-output (MIMO) technology in high-speed vehicular environments. We propose a sensing-centric (SC) approach for target detection using communication signals with or without sensing signals. Power allocation is optimized to maximize the sensing signal-to-noise ratio (SNR) of the proposed SC scheme while ensuring a required quality-of-service (QoS) for the communication user equipment (UEs), and adhering to each access points (APs) power budget. Numerical results show that the proposed SC scheme vastly outperforms a communication-centric method that minimizes the total power consumed at the APs subject to the same constraints.

cs.IT↗

arXiv2024

Improved Q-learning based Multi-hop Routing for UAV-Assisted Communication

Designing effective Unmanned Aerial Vehicle(UAV)-assisted routing protocols is challenging due to changing topology, limited battery capacity, and the dynamic nature of communication environments. Current protocols prioritize optimizing individual network parameters, overlooking the necessity for a nuanced approach in scenarios with intermittent connectivity, fluctuating signal strength, and varying network densities, ultimately failing to address aerial network requirements comprehensively. This paper proposes a novel, Improved Q-learning-based Multi-hop Routing (IQMR) algorithm for optimal UAV-assisted communication systems. Using Q(\lambda) learning for routing decisions, IQMR substantially enhances energy efficiency and network data throughput. IQMR improves system resilience by prioritizing reliable connectivity and inter-UAV collision avoidance while integrating real-time network status information, all in the absence of predefined UAV path planning, thus ensuring dynamic adaptability to evolving network conditions. The results validate IQMR's adaptability to changing system conditions and superiority over the current techniques. IQMR showcases 36.35\% and 32.05\% improvements in energy efficiency and data throughput over the existing methods.

cs.NI↗

arXiv2023

Energy Efficient UAV-Assisted Emergency Communication with Reliable Connectivity and Collision Avoidance

Emergency communication is vital for search and rescue operations following natural disasters. Unmanned Aerial Vehicles (UAVs) can significantly assist emergency communication by agile positioning, maintaining connectivity during rapid motion, and relaying critical disaster-related information to Ground Control Stations (GCS). Designing effective routing protocols for relaying crucial data in UAV networks is challenging due to dynamic topology, rapid mobility, and limited UAV resources. This paper presents a novel energy-constrained routing mechanism that ensures connectivity, inter-UAV collision avoidance, and network restoration post-UAV fragmentation while adapting without a predefined UAV path. The proposed method employs improved Q learning to optimize the next-hop node selection. Considering these factors, the paper proposes a novel, Improved Q-learning-based Multi-hop Routing (IQMR) protocol. Simulation results validate IQMRs adaptability to changing system conditions and superiority over QMR, QTAR, and QFANET in energy efficiency and data throughput. IQMR achieves energy consumption efficiency improvements of 32.27%, 36.35%, and 36.35% over QMR, Q-FANET, and QTAR, along with significantly higher data throughput enhancements of 53.3%, 80.35%, and 93.36% over Q-FANET, QMR, and QTAR.

cs.NI↗

arXiv2023

Network Centralities in Quantum Entanglement Distribution due to User Preferences

Quantum networks are of great interest of late which apply quantum mechanics to transfer information securely. One of the key properties which are exploited is entanglement to transfer information from one network node to another. Applications like quantum teleportation rely on the entanglement between the concerned nodes. Thus, efficient entanglement distribution among network nodes is of utmost importance. Several entanglement distribution methods have been proposed in the literature which primarily rely on attributes, such as, fidelities, link layer network topologies, proactive distribution, etc. This paper studies the centralities of the network when the link layer topology of entanglements (referred to as entangled graph) is driven by usage patterns of peer-to-peer connections between remote nodes (referred to as connection graph) with different characteristics. Three different distributions (uniform, gaussian, and power law) are considered for the connection graph where the two nodes are selected from the same distribution. For the entangled graph, both reactive and proactive entanglements are employed to form a random graph. Results show that the edge centralities (measured as usage frequencies of individual edges during entanglement distribution) of the entangled graph follow power law distributions whereas the growth in entanglements with connections and node centralities (degrees of nodes) are monomolecularly distributed for most of the scenarios. These findings will help in quantum resource management, e.g., quantum technology with high reliability and lower decoherence time may be allocated to edges with high centralities.

quant-ph↗

arXiv2022

Node and Edge Centrality based Failures in Multi-layer Complex Networks

Multi-layer complex networks (MLCN) appears in various domains, such as, transportation, supply chains, etc. Failures in MLCN can lead to major disruptions in systems. Several research have focussed on different kinds of failures, such as, cascades, their reasons and ways to avoid them. This paper considers failures in a specific type of MLCN where the lower layer provides services to the higher layer without cross layer interaction, typical of a computer network. A three layer MLCN is constructed with the same set of nodes where each layer has different characteristics, the bottom most layer is Erdos-Renyi (ER) random graph with shortest path hop count among the nodes as gaussian, the middle layer is ER graph with higher number of edges from the previous, and the top most layer is scale free graph with even higher number of edges. Both edge and node failures are considered. Failures happen with decreasing order of centralities of edges and nodes in static batch mode and when the centralities change dynamically with progressive failures. Emergent pattern of three key parameters, namely, average shortest path length (ASPL), total shortest path count (TSPC) and total number of edges (TNE) for all the three layers after node or edge failures are studied. Extensive simulations show that all but one parameters show definite degrading patterns. Surprising, ASPL for the middle layer starts showing a chaotic behavior beyond a certain point for all types of failures.

cs.SI↗

arXiv2022

Multi-class Classifier based Failure Prediction with Artificial and Anonymous Training for Data Privacy

This paper proposes a novel non-intrusive system failure prediction technique using available information from developers and minimal information from raw logs (rather than mining entire logs) but keeping the data entirely private with the data owners. A neural network based multi-class classifier is developed for failure prediction, using artificially generated anonymous data set, applying a combination of techniques, viz., genetic algorithm (steps), pattern repetition, etc., to train and test the network. The proposed mechanism completely decouples the data set used for training process from the actual data which is kept private. Moreover, multi-criteria decision making (MCDM) schemes are used to prioritize failures meeting business requirements. Results show high accuracy in failure prediction under different parameter configurations. On a broader context, any classification problem, beyond failure prediction, can be performed using the proposed mechanism with artificially generated data set without looking into the actual data as long as the input features can be translated to binary values (e.g. output from private binary classifiers) and can provide classification-as-a-service.

cs.AI↗

arXiv2022

Generalised Mathematical Formulations for Non-Linear Optimized Scheduling

In practice, most of the optimization problems are non-linear requiring certain interactive solutions and approaches to model. In 5G Advanced and Beyond network slicing, mathematically modeling the users, type of service distributions and its adaptive SLAs are complex due to several dependencies. To facilitate the above, in this paper, we present novel Non-linear mathematical formulations and results that will form the base to achieve Optimized Scheduling.

cs.NI↗

arXiv2021

Predictive Dynamic Scaling Multi-Slice-in-Slice-Connected Users for 5G System Resource Scheduling

Network slicing is an effective 5G concept for improved resource utilization and service scalability tailored to users (UEs) requirements. According to the standardization, 5G system should support UEs through specification of its heterogenous requirements such as, high data rates, traffic density, latency, reliability, UE density, system efficiency and service availability. These requirements are specified as Service Level Agreements (SLAs) between UEs and network operators resulting in increased interest to develop novel challenging mechanisms for improved interference-free resource efficient performances. An emerging concept that enables such demanding SLA assurances is Open-Radio Access Network (O-RAN). In this paper, we study a novel resource scheduling problem for UE services conditioned on other services in network slicing. To improve system performance, we propose that UEs are connected across network slices to serve several applications. UEs of similar service classes (defined by SLAs) are grouped to form optimized slice-in-slice category(s) within network slice(s).We propose novel Predictive Dynamic Scaling Multi-UE service specific System Resource Optimized Scheduling (DMUSO) algorithm(s). Multiobjective multi-constraint optimization problems (MOP) are formed to learn the dynamic system resource allocation and throughput for UE services conditioned on new services entering the network slice. An epsilon-constraint line search algorithm is presented to estimate UE service bandwidth. Using the theoretical models, DMUSO forms optimal slice-in-slice categories and estimates the maximum dynamic additional slice-in-slice categories, throughput served across network slices. Finally, compared to state-of-the-art literatures, DMUSO guarantees UEs SLAs with 4.4 and 7.5 times performance gains

cs.NI↗

arXiv2021

Optimization Results for 5G Slice-in-Slice Scheduling

Open Radio Access Network (ORAN) Slicing for 5G and Beyond is an emerging architecture and feature that will facilitate challenging RAN Service Level Agreement (SLA) assurance targets. This could pave the way for operators to realize the benefits of network slicing efficiently. In this paper, we provide novel and detailed optimization results to achieve Slice-in-Slice Scheduling for 5G User Services in ORAN slicing.

cs.NI↗

arXiv2021

Connectivity and Collision Constrained Opportunistic Routing for Emergency Communication using UAV

Emergency communication is extremely important to aid rescue and search operation in the aftermath of any disaster. In such scenario, Unmanned Aerial Vehicle (UAV) networks may be used to complement the damaged cellular networks over large areas. However, in such UAV networks, routing is a challenge, owing to high UAV mobility, intermittent link quality between UAVs, dynamic three dimensional (3D) UAV topology and resource constraints. Though several UAV routing approaches have been proposed, none of them so far have addressed inter UAV coverage, collision and routing in an integrated manner. In this paper, we consider a scenario where network of UAVs, operating at different heights from ground, with inter UAV coverage and collision constraints, are sent on a mission to collect disaster surveillance data and route it to Terrestrial Base Station via multi-hop UAV path. Analytical expressions for coverage probability (Pcov) and collision probability (Pcoll) are derived and minimum (Rmin) and maximum (Rmax) distance between UAVs are empirically calculated. We then propose a novel Multi-hop Opportunistic 3D Routing (MO3DR) algorithm with inter UAV coverage and collision constraints such that at every hop expected progress of data packet is maximized. The numerical results obtained from closed form mathematical modelling are validated through extensive simulation and their trade-off with variation in network parameters such as path loss component, trajectory divergence etc. are demonstrated. Finally, we obtain empirical optimality condition for inter UAV distance for the given application requirement.

cs.NI↗

arXiv2021

A Data Augmented Bayesian Network for Node Failure Prediction in Optical Networks

Failures in optical network backbone can cause significant interruption in internet data traffic. Hence, it is very important to reduce such network outages. Prediction of such failures would be a step forward to avoid such disruption of internet services for users as well as operators. Several research proposals are available in the literature which are applications of data science and machine learning techniques. Most of the techniques rely on significant amount of real time data collection. Network devices are assumed to be equipped to collect data and these are then analysed by different algorithms to predict failures. Every network element which is already deployed in the field may not have these data gathering or analysis techniques designed into them initially. However, such mechanisms become necessary later when they are already deployed in the field. This paper proposes a Bayesian network based failure prediction of network nodes, e.g., routers etc., using very basic information from the log files of the devices and applying power law based data augmentation to complement for scarce real time information. Numerical results show that network node failure prediction can be performed with high accuracy using the proposed mechanism.

cs.NI↗

arXiv2021

A Non-intrusive Failure Prediction Mechanism for Deployed Optical Networks

Failures in optical network backbone can lead to major disruption of internet data traffic. Hence, minimizing such failures is of paramount importance for the network operators. Even better, if the network failures can be predicted and preventive steps can be taken in advance to avoid any disruption in traffic. Various data driven and machine learning techniques have been proposed in literature for failure prediction. Most of these techniques need real time data from the networks and also need different monitors to measure key optical parameters. This means provision for failure prediction has to be available in network nodes, e.g., routers and network management systems. However, sometimes deployed networks do not have failure prediction built into their initial design but subsequently need arises for such mechanisms. For such systems, there are two key challenges. Firstly, statistics of failure distribution, data, etc., are not readily available. Secondly, major changes cannot be made to the network nodes which are already commercially deployed. This paper proposes a novel implementable non-intrusive failure prediction mechanism for deployed network nodes using information from log files of those devices. Numerical results show that the mechanism has near perfect accuracy in predicting failures of individual network nodes.

cs.NI↗