Department of Computer Science and Information Systems
Permanent URI for this collectionhttp://localhost:4000/handle/123456789/1928
Browse
15 results
Search Results
Item An efficient federated transfer learning approach for Multi-UAV systems(IEEE, 2025-05) Joshi, Sandeep; Rajya Lakshmi, L.Recent advances in multi-unmanned aerial vehicle (UAV) based federated learning do not take into consideration the massive computational requirements of modern deep learning models on mobile UAV s. Additionally, there has been significant progress that shows that the information transmitted between the federated agent and the central hub can be attacked to undermine the privacy of the data. We propose a novel multi-UAV-based federated transfer learning system that drastically reduces the computational burden overall, shifts it from UAV s to the ground fusion center, and reduces the bandwidth requirements while enhancing its secure nature. The proposed system makes multi-UAV learning significantly fast, reliable, power efficient, and practically feasible. Furthermore, we provide simulation and experimental results to demonstrate the effectiveness of the proposed systemItem Load-aware resource scheduling in fog computing based delay-sensitive IOT networks(IEEE, 2023-08) Rajya Lakshmi, L.Internet of Things (IoT), with its capability to connect anything, anywhere, anytime, bringing in revolutionary changes in data collection, processing and utilization. IoT networks generate a huge amount of data, which is difficult to process and store on IoT devices. Cloud computing with its huge availability of resources, can process and store these huge volumes of data. However, owing to the long distance between the cloud and IoT devices, the cloud computing suffers the issues like high latency, network congestion and unreliability. To address these issues, fog computing, which is a decentralized computing paradigm has been proposed as an extension to cloud computing. To utilize the fog resources efficiently and to avoid over-utilization and under-utilization of resources, this paper proposes a resource scheduling algorithm which is capable of balancing the load on fog nodes while satisfying the delay requirements of IoT applications. Extensive simulations are conducted to evaluate the performance of the proposed method. The simulation results establish that the load is almost equally distributed among the fog nodes in the network in most of the traffic arrival scenarios.Item Link Quality Based Path Selection Methods for IEEE 802.16j Mobile Multihop Relay Networks(Springer, 2013-08) Rajya Lakshmi, L.IEEE 802.16j mobile multihop relay (MMR) networks are developed to enhance the coverage area and the throughput of IEEE 802.16 networks. Path selection is an important research problem related to these networks. In the networks where the link qualities are highly varying, to provide consistent quality of service to the users, it is very important to select paths consisting of links with consistent link qualities. To address this issue, in this paper, two path consistency based path selection methods are proposed for IEEE 802.16j MMR networks. Through simulations, the performance of the method proposed for the mobile nodes is compared with the performance of two path selection methods proposed in the literature. It is observed that the proposed method provides better performance than the methods selected from the literature.Item Cooperative data transmission framework for IEEE 802.16j mobile multihop relay networks(Springer, 2014-05) Rajya Lakshmi, L.IEEE 802.16j Mobile Multihop Relay specification is an amendment of the IEEE 802.16 standard and it is developed to extend IEEE 802.16e. Quality of Service (QoS) constrained service flow management is an important issue related to these networks. In the situation where the link quality between a superordinate station and one of its subordinate Non-Transparent Relay Stations (NTRSs) is poor then it is difficult to fulfill the QoS requirements of the flows that are passing through that NTRS. To handle such situations, in this paper, a novel Cooperative Data Transmission (CDT) framework is proposed. It uses the Transparent Relay Stations (TRSs) which are the common neighbors of the NTRSs and their superordinate stations to fulfill the QoS requirements of the flows that are passing through the NTRSs. The changes required to the network entry, path establishment, bandwidth allocation and data transmission processes of the IEEE 802.16j standard for the CDT framework are proposed in this paper. Also, the performance gains achievable with the proposed CDT framework in terms of the throughput are analyzed numerically. The upper and lower bounds on the throughput gain are obtained. Through simulations, the performance of the proposed CDT framework is studied and compared with the performance of the normal data transmission where no cooperation from TRSs is involved in the data transmission. The CDT framework showed significant performance advantages when compared with the normal data transmission methodItem PRIME: A partial path establishment based handover management technique for QoS support in WiMAX based wireless mesh networks(Elsevier, 2015-06) Rajya Lakshmi, L.In this paper, we propose a novel handover management technique called PaRtIal path establishment based handover Management tEchnique (PRIME) for WiMAX based wireless mesh networks (WMNs). Different from the currently existing methods for WiMAX networks, PRIME addresses handover management in WiMAX WMNs deployed with distributed scheduling. In these networks, to continue the quality of service (QoS) constrained flows to a mobile node (MN) after its handover, a new path with the required bandwidth and which passes through its new base station (BS) needs to be established as quickly as possible. To address that issue, PRIME handles re-routing and scheduling issues of a handing over MN together. To provide lossless and seamless service, PRIME tries to establish new path(s) in the wireless mesh with the required bandwidth to the MN before it enters into the coverage area of the new BS. The present paper proposes a novel crossover node based partial path establishment algorithm to establish new path(s) which support QoS requirements of handoff calls. To analyze the performance of PRIME, the present paper proposes a multi-dimensional Markov model. Unlike previous models which analyze the performance of wireless networks, our proposed model represents nodes in terms of the number of transmission and reception available slots. The theoretical upper and lower bounds on the call dropping probabilities of handoff calls are obtained. To study the performance advantages of PRIME, we devise another handover management method called RFPHMT which does not use the concept of crossover base station in the new path establishment of a handing over node. The performance of PRIME and RFPHMT are compared in terms of call dropping probabilities and call setup delays. PRIME shows superior performance than RFPHMT. For a random topology, at a high call arrival rate of 1/2000 (calls/milliseconds), the handover call dropping probability of PRIME is 40% less than that of RFPHMT. The call dropping probabilities of PRIME with the simulations are always within the theoretical bounds which proves that the obtained bounds are close to the real call dropping probabilities.Item A Dynamic Backup Path Management Method for TDMA Based WiMAX Client WMNs(Springer, 2016-02) Rajya Lakshmi, L.This paper proposes a backup path management method for time division multiple access (TDMA) based client wireless mesh networks (WMNs). In a TDMA based client WMN, as links/nodes fail or as nodes perform handover and as flows enter and leave the network, the paths between various nodes change as well as the bandwidth available along these paths. In these networks, to support the quality of service requirements of flows, backup paths with the required bandwidth need to be established dynamically. Some methods are proposed in the literature to establish backup paths which handle link/node failures and node handover in ad hoc networks, but none of these methods can provide backup paths with the required bandwidth dynamically. To address that issue, the present paper proposes a backup path management method which is adaptive to both topological changes and traffic changes in a network. Each node along the current path between a source and a destination finds backup paths with the required bandwidth in order to handle failure of the link to its downstream node and its own failure or handover. Nodes use two-hop neighborhood information and slots status information of two-hop neighbors to establish backup paths. We prove that the number of backup paths available when a node N searches for backup paths to handle its own failure are more than the number of backup paths available when some other node searches for the backup paths for the failure of node N. Performance of the proposed method is compared with the performance of a naive path management (NPM) method in which always the source establishes backup paths whenever a link/node fails or a node performs handover, and also with the performance of a backup path management method proposed in the literature. The proposed method significantly outperforms the NPM method and the method selected from the literature. For example, when the speed of the mobile nodes is 50 m/s, the packet delivery ratio with the proposed method is 63 % more than the NPM method and 35 % more than the method selected from the literature.Item Handover management framework for WiMAX Point-to-Multi-Point networks(Elsevier, 2016-11) Rajya Lakshmi, L.In this paper, a distributed base station cooperation-based handover management method is proposed for WiMAX Point-to-Multi-Point networks to provide quality of service to handover nodes. Moreover, a delay reduction method is proposed to reduce the packet delivery delays during handover. A Call Admission Control (CAC) algorithm is proposed to handle handover calls of various service classes fairly, according to their priorities. A bandwidth borrowing scheme is proposed to reduce the handover call dropping probabilities of various service classes while not starving the ongoing calls of lower priority service classes. A Markov model is developed to analyze the proposed CAC method and to obtain the approximate handover call dropping probabilities of various service classes. Simulation experiments are conducted to establish the performance advantages of the proposed handover management and CAC methods.Item Adaptive Zone Size Selection Method for IEEE 802.16j Mobile Multihop Relay Networks(Springer, 2017-08) Rajya Lakshmi, L.IEEE 802.16j relay networks are capable of extending the coverage areas of IEEE 802.16 networks and can support the data rate requirements of users at cell edges. In these networks, each frame is divided into various zones to facilitate data transmission between various types of nodes. As the link qualities in the network change, accordingly the zone sizes should also change to support the Quality of Service (QoS) requirements of flows and to avoid bandwidth wastage. To address this issue, in this paper, we propose an adaptive zone size selection method for IEEE 802.16j networks. With this method, zone sizes of scheduling nodes are adaptively changed in accordance with their changing link qualities. As the link qualities degrade, the scheduling nodes may not be able to support the QoS requirements of flows due to the lack of free bandwidth availability in the corresponding zones. To handle this issue with less control overhead, we propose a cross-zone bandwidth allocation method. A zone size reselection method is also proposed to handle the situations where the cross-zone bandwidth allocation is not possible. Performance of the proposed method is compared with the performance of a fixed zone size selection method and a zone size selection method proposed in the literature. The proposed method shows significantly better performance than the other two methods in terms of traffic admittance, bandwidth utilization, and satisfaction ratios of flows.Item Fair Scheduling of Concurrent Transmissions in Directional Antenna Based WPANs/WLANs(IEEE, 2018-07) Rajya Lakshmi, L.With their capability to support high data rates, millimeter-Wave (mmWave) communications are evolving as a promising and potential technology to support high data rate applications in short range networks. This paper addresses the problem of fair scheduling in mmWave wireless personal and local area networks (WPANs/WLANs) to support applications with varying quality of service (QoS) requirements. To ensure fairness while exploiting the spatial reuse facilitated by directional antennas, concurrent transmission scheduling in mmWave WPANs/WLANs is formulated as a multi-objective optimization problem. Two heuristic schedulers are developed to obtain a schedule in real-time. These schedulers first satisfy the minimum QoS requirements of as many flows as possible, and then, allocate the remaining bandwidth to various flows while ensuring long-term and short-term fairness among the flows. Results from extensive simulations conducted in a dense mmWave WPAN show that the proposed fair schedulers provide better fairness and throughput, compared to existing methods.Item Achieving Fairness in IEEE 802.11ah Networks for IoT Applications with Different Requirements(IEEE, 2019-07) Rajya Lakshmi, L.The IEEE 802.11ah standard can provide cost-effective Internet access to a large number of devices in newly evolving Internet-of-Things (IoT) and machine-to-machine (M2M) networks. To handle high collision probability caused by a large number of devices, it adopts a group-based protocol at the MAC layer and divides nodes (or sensors) into a number of groups. The formed groups may not be uniform in terms of data rate requirements, since each group is a combination of sensors with different traffic characteristics. To achieve fair resource utilization across the groups which in turn maximizes the channel utilization, this paper formulates fair grouping in IEEE 802.11ah networks as an optimization problem, and we develop a heuristic method to solve the problem in real-time. In addition, to ensure fair channel utilization by the nodes in each group, a contention window selection and adjustment method is proposed. Results from extensive simulations conducted in a dense IoT network show that the proposed fairness model achieves a superior performance than the existing methods in terms of throughput, packet delay, energy efficiency, and fairness.