Visalakshi Annepu

Bio: Visalakshi Annepu is an academic researcher from VIT University. The author has contributed to research in topics: Node (networking) & Wireless sensor network. The author has an hindex of 5, co-authored 11 publications receiving 63 citations. Previous affiliations of Visalakshi Annepu include Andhra University.

Implementation of an Efficient Artificial Bee Colony Algorithm for Node Localization in Unmanned Aerial Vehicle Assisted Wireless Sensor Networks

Abstract: Node localization is a fundamental task in wireless sensor networks as it is useful for several localization based protocols and applications. Node localization using Global Poisoning System (GPS) employed fixed terrestrial anchor nodes suffers from high deployment cost and poor localization accuracy in GPS denied locations. These issues can be easily handled by deploying movable Unmanned Aerial Vehicles (UAVs). A movable UAV equipped with a single GPS module virtually increases number of anchor nodes and localizes a node at different locations. Hence, UAVs are cost effective and also provides high localization accuracy. As the flying altitude of UAV greatly influence localization accuracy, the present work firstly optimizes the flying height and then the node localization is defined as least square optimization problem using this optimal height. Since the classical received signal strength indicator based multilateration results high localization error, the least square localization using optimization techniques is found to be better alternative. The recently proposed Artificial Bee Colony (ABC) algorithm is a powerful optimization technique that can be applied for this optimization problem to achieve high accuracy. Thus, this paper aims at designing an ABC localization technique using UAV anchors to achieve minimum localization error. Further, we provide detailed simulation analysis to support the proposed ABC localization scheme.

Implementation of self adaptive mutation factor and cross-over probability based differential evolution algorithm for node localization in wireless sensor networks

Abstract: Node localization or positioning is essential for many position aware protocols in a wireless sensor network. The classical global poisoning system used for node localization is limited because of its high cost and its unavailability in the indoor environments. So, several localization algorithms have been proposed in the recent past to improve localization accuracy and to reduce implementation cost. One of the popular approaches of localization is to define localization as a least square localization (LSL) problem. During optimization of LSL problem, the performance of the classical Gauss–Newton method is limited because it can be trapped by local minima. By contrast, differential evolution (DE) algorithm has high localization accuracy because it has an ability to determine global optimal solution to the LSL problem. However, the convergence speed of the conventional DE algorithm is low as it uses fixed values of mutation factor and cross-over probability. Thus, in this paper, a self-adaptive mutation factor cross-over probability based differential evolution (SA-MCDE) algorithm is proposed for LSL problem to improve convergence speed. The SA-MCDE algorithm adaptively adjusts the mutation factor and cross-over probability in each generation to better explore and exploit the global optimal solution. Thus, improved localization accuracy with high convergence speed is expected from the SA-MCDE algorithm. The rigorous simulation results conducted for several localization algorithms declare that the propose SA-MCDE based localization has about (40–90) % more localization accuracy over the classical techniques.

An unmanned aerial vehicle-aided node localization using an efficient multilayer perceptron neural network in wireless sensor networks

Abstract: Localization of sensor node is decisive for many localization-based scenarios of wireless sensor networks (WSNs). Node localization using fixed terrestrial anchor nodes (ANs) equipped with global positioning system (GPS) modules suffers from high deployment cost and poor localization accuracy, because the terrestrial AN propagates signals to the unknown nodes (UNs) through unreliable ground-to-ground channel. However, the ANs deployed in unmanned aerial vehicles (UAVs) with a single GPS module communicate over reliable air-to-ground channel, where almost clear line-of-sight path exists. Thus, the localization accuracy and deployment cost are better with aerial anchors than terrestrial anchors. However, still the nonlinear distortions imposed in propagation channel limit the performance of classical RSSI and least square localization schemes. So, the neural network (NN) models can become good alternative for node localization under such nonlinear conditions as they can do complex nonlinear mapping between input and output. Since the multilayer perceptron (MLP) is a robust tool in the assembly of NNs, MLP-based localization scheme is proposed for UN localization in UAV-aided WSNs. The detailed simulation analysis provided in this paper prefers the MLP localization scheme as they exhibit improved localization accuracy and deployment cost.

Performance Analysis of HSRP in Provisioning Layer-3 Gateway Redundancy for Corporate Networks

Abstract: The network functionaries incorporate and core networks aim to provide 99.999% reliability to their networks. The most preferred way to achieve this is to provide dynamic routing to the network. If the router gateway is disrupted by port failure, network administrator should manually configure the route in which packets are being forwarded. By using Hot Stand Routing Protocol (HSRP), it simultaneously adapts new route, which provides redundancy to the network with reduced packet loss. In this paper, our aim is to calculate the difference in number of packets lost when router with gateway is disrupted in the network by combining HSRP with Open Shortest Path First (OSPF) protocol. By using this combined technique, we can reduce the packet loss to maximum extent thereby increasing the reliability. The simulation results provide best route when HSRP is combined with OSPF than the existing technique without HSRP.

Energy and Spectrum Optimization for 5G Massive MIMO Cognitive Femtocell Based Mobile Network Using Auction Game Theory

Abstract: Energy and spectrum optimization for massive multiple input multiple output (MIMO) cognitive femtocell based fifth generation (5G) mobile network is developed using auction game. In 5G massive MIMO, multiple numbers of antennas are used to transmit the signal with same time frequency to maximize the number of users, who can communicate with less number of channels. Cognitive radio network (CRN) also increases spectrum efficiency by sharing primary users channel to transmit data for secondary users. In this article, cognitive femtocell base stations are treated as secondary base stations to win a channel by using auction game with utility function. Femtocell base stations bid for a channel with pricing value to the MIMO base station spectrum manager and the spectrum manager allocates spectrum to the femtocell base station based on maximum pricing value. Opportunistic spectrum access by femtocell using cognitive approach decreases number of active antennas in massive MIMO based network which reduces energy consumption. Simulation results show that the proposed network reduces ~ 70% power consumptions than the existing CRN and only MIMO CRN based strategies. Simulation results also presents that the massive MIMO cognitive femtocell network increases signal to interference plus noise ratio and spectral efficiency ~ 13% and ~ 20% respectively than the existing CRN and only MIMO CRN based approaches.

MC–CDMA receiver design using recurrent neural networks for eliminating multiple access interference and nonlinear distortion

Abstract: Summary Multicarrier code division multiple access (MC–CDMA) is a promising wireless communication technology with high spectral efficiency and system performance. However, all multiple access techniques including MC–CDMA were most likely to have multiple access interference (MAI). So this paper mainly aims at designing a suitable receiver for MC–CDMA system to mitigate such MAI. The classical receivers like maximal ratio combining, minimum mean square error, and iterative block–decision feedback equalization fail to cancel MAI when the MC–CDMA is subjected to severe nonlinear distortions, which may occur due to saturated power amplifiers or arbitrary channel conditions. Being highly nonlinear structures, the neural network receivers such as multilayer perceptron and recurrent neural network could be better alternative for such a case. The feasibility, efficiency, and effectiveness of the proposed neural network receiver are studied thoroughly for MC–CDMA system under different nonlinear conditions.

Development of a Multilayer Perception Neural Network for Optimal Predictive Modeling in Urban Microcellular Radio Environments

Abstract: Modern cellular communication networks are already being perturbed by large and steadily increasing mobile subscribers in high demand for better service quality. To constantly and reliably deploy and optimally manage such mobile cellular networks, the radio signal attenuation loss between the path lengths of a base transmitter and the mobile station receiver must be appropriately estimated. Although many log-distance-based linear models for path loss prediction in wireless cellular networks exist, radio frequency planning requires advanced non-linear models for more accurate predictive path loss estimation, particularly for complex microcellular environments. The precision of the conventional models on path loss prediction has been reported in several works, generally ranging from 8–12 dB in terms of Root Mean Square Error (RMSE), which is too high compared to the acceptable error limit between 0 and 6 dB. Toward this end, the need for near-precise machine learning-based path loss prediction models becomes imperative. This work develops a distinctive multi-layer perception (MLP) neural network-based path loss model with well-structured implementation network architecture, empowered with the grid search-based hyperparameter tuning method. The proposed model is designed for optimal path loss approximation between mobile station and base station. The hyperparameters examined include the neuron number, learning rate and hidden layers number. In detail, the developed MLP model prediction accuracy level using different learning and training algorithms with the tuned best values of the hyperparameters have been applied for extensive path loss experimental datasets. The experimental path loss data is acquired via a field drive test conducted over an operational 4G LTE network in an urban microcellular environment. The results were assessed using several first-order statistical performance indicators. The results show that prediction errors of the proposed MLP model compared favourably with measured data and were better than those obtained using conventional log-distance-based path loss models.