Gowrishankar

Bio: Gowrishankar is an academic researcher from B.M.S. College of Engineering. The author has contributed to research in topics: Wireless network & Quality of service. The author has an hindex of 7, co-authored 19 publications receiving 119 citations.

Neural Network Based Traffic Prediction for Wireless Data Networks

Abstract: In a wireless network environment accurate and timely estimation or prediction of network traffic has gained much importance in the recent past The network applications use traffic prediction results to maintain its performance by adopting its behaviors Network Service provider will use the prediction values in ensuring the better Quality of Service(QoS) to the network users by admission control and load balancing by inter or intra network handovers This paper presents modeling and prediction of wireless network traffic Here traffic is modeled as nonlinear and non-stationary time series The nonlinear and non-stationary time series traffic is predicted using neural network and statistical methods The results of both the methods are compared on different time scales or time granularity The Neural Network (NN) architectures used in this study are Recurrent Radial Basis Function Network (RRBFN) and Echo state network (ESN)The statistical model used here in this work is Fractional Auto Regressive Integ

Analytic Performability Model of Vertical Handoff in Wireless Networks

Abstract: Problem statement: The next generation wireless systems should be designed to support heterogeneous traffic with seamless mobility. A single network alone cannot cope up with such heterogeneous requirements. Hence it is desirable to interoperate between diverse and complementary Radio Access Technologies (RATs). In such system, user will switch between different Radio Access Technologies (RATs) to satisfy the User/application requirement and this process is known as Vertical Handoff (VHO). The process of network switching had three phases, network discovery, handoff decision and execution. The decision phase played a crucial role in resource utilization and user/application Quality of Service (QoS) requirement. Hence it was essential to model and evaluate the handoff decision system along with VHO system model. Approach: The traditional performance models were optimistic models and would evaluate the system performance under ideal condition by ignoring failures and recovery in the system. The availability models were conservative models and would assess the availability/reliability of the system. The performabality models were combined models of performance and reliability. The performablity models were more realistic models of the system due to the simultaneous consideration of performance and reliability. Here the VHO process of a next generation wireless system was modeled and evaluated by an analytic performablity model and performance of decision system is evaluated through the sensitivity analysis of VHO decision parameter. Results: In VHO performance evaluation, the metrics of performance evaluation are handoff dropping probability and new call blocking probability. The dynamics of these metrics are depends on set of wireless network parameter such as Available Bandwidth (ABW), users, Bit Error Rate (BER) and network traffic. The ABW, BER and network traffic is also parameter for VHO decisions. The results of performance evaluation are used to develop a novel intelligent vertical handoff decision technique to achieve optimum tradeoff between set of handoff decision criteria. Finally, sensitivity analysis of system parameters on four traffic classes and two vertical handoff decision algorithms along with intelligent vertical handoff decision method were presented. Conclusion: The results of sensitivity analysis depicted that the VHO process in next generation wireless system needs intelligent criteria based technique at the decision making phase of VHO process.

Performability Model of Vertical Handoff in Wireless Data Network

Abstract: The integration of different wireless technologies is the emerging trend in providing ubiquitous access to the high data rate wireless network. In such system user will be roaming among different radio access technologies (RATs) and this is known as vertical handover/handoff. In order to understand the practical behavior of the system, the Performability model is found to be essential. In wireless network the available bandwidth (ABW) of network is divided into set of logical channels[1] and these set of channels are shared among a set of network users. The network users are divided into new users and handoff users. The handoff users are further classified into vertical handoff users and horizontal handoff users. In a wireless network, the priority is given to handoff users. In order to provide better service to the wireless users the quality of service (QoS) parameters were defined[2]. One of the QoS parameter for the wireless network is handoff dropping probability. For better QoS it is desirable to reduce the handoff dropping probability hence separate set of guard channels were reserved for handoff[3][4]. In this prevailing scenario it is highly desirable to obtain analytic performability model. The stochastic Petri net (SPN) based performability model has been developed to verify the efficiency and accuracy of analytic performability model. The results obtained from both the performability models are promising.

Survey of soft computing techniques for joint radio resource management

Abstract: Ever changing requirements of the mobile devices has posed significant challenges on existing cellular network systems. The Next Generation Wireless Networks (NGWN) will be heterogeneous which will have different Radio Access Technologies (RATs) operating together. Radio Resource Management (RRM) is one of the key challenges in NGWN. Joint Radio Resource Management (JRRM) is one of the RRM technique plays instrumental role in ensuring the desired Quality of Service (QoS) to the users working on different applications which are having the diversified nature of QoS requirements to be fulfilled by the wireless networks. Soft computing is one promising field which is strongly believed to enhance the capability of the existing methods for JRRM. The objective of this paper is to bring out the best features of soft computing techniques for JRRM in NGWN to enhance capability of existing methods, which integrates the different RRM strategies using soft computing techniques for NGWN and observe how JRRM would properly work together with soft computing techniques in heterogeneous scenario to perform better than the existing techniques.

Performance comparison between MADM algorithms for vertical handoff in 4G networks

Abstract: In a fourth generation (4G) wireless environment, the need for an user to be always best connected (ABC) anywhere at anytime leads to execute a vertical handoff decision for guaranteeing service continuity and quality of service (QoS). Several strategies have been proposed in the literature for addressing this problem, being multiple attribute decision making (MADM) one of the most promising methods. A comparative analysis of these methods including SAW, MEW, TOPSIS, ELECTRE, VIKOR, GRA, and WMC is illustrated with a numerical simulation, showing their performance for different applications such as: voice and data connections, in a 4G wireless system.

Energy Aware Cluster Based Multi-hop Energy Efficient Routing Protocol using Multiple Mobile Nodes (MEACBM) in Wireless Sensor Networks

Abstract: Routing in Wireless Sensor Networks (WSNs) is the most significant and the challenging issue for the researchers in terms of enhancing its performance in terms of network lifetime, energy efficiency, scalability, connectivity, throughput, etc. They have the incredible capability to interact and gather data from any physical environment with help of routing protocols. Many routing protocols based solutions have been proposed in the recent years for accomplishing the preferred level of performance in WSNs for these issues. The hierarchical heterogeneous cluster based energy efficient routing protocols are more efficient as compared to flat and location based routing protocols due to the presence of nodes heterogeneity in terms of energy level of sensor nodes which enhances the lifetime of the network. The most recent trend that extensively enhances the functionality and the performance of WSNs is the use of mobile sensor nodes. In this paper, the authors proposed a novel concept regarding mobile sensor nodes is proposed called Mobile Energy Aware Cluster Based Multi-hop (MEACBM) routing protocol for hierarchical heterogeneous WSNs which selects CHs on the basis of newly proposed probability equation which selects only that sensor node as Cluster Head (CH) which has the highest energy among other sensor nodes by introducing a new term S(i).E in the equation. It considers hierarchical heterogeneous clustering considering three levels of sensor nodes; multi-hoping for inter-cluster communication and connectivity of sensor nodes within the whole network area. In MEACBM, after the deployment of sensor nodes and formation of clusters, the whole network area is divided into sectors and inside each sector a mobile sensor node is placed which act as Mobile Data Collector (MDC) for collecting data from CHs. This technique helps in significantly reducing the energy consumption of sensor nodes for transferring information to the Base Station (BS). Simulation performance based results indicates the effectiveness of MEACBM routing protocols by comparing it with other contemporary cluster based routing protocols in terms of network lifetime, stability, throughput, number of CHs and number of dead nodes.

A hybrid neural network model and encoding technique for enhanced classification of energy consumption data

Abstract: Total losses in transmission and distribution (T&D) of electrical energy including nontechnical losses (NTL) are huge and are affecting the good interest of utility company and its customers. In this context, importance of customer load profile evaluation for detection of illegal consumers is explained in this paper. Classification of the customers based on load profile evaluation using SVMLIB requires us to choose training function and related parameters. Selecting these parameters would consume a lot of time and is not suggestible evaluation of real time electricity consumption patterns, as, the suspicious profiles are to be predicted instantly. In light of this issue, this paper implements a neural network (NN) model and suggests a hierarchical model for enhanced estimation of the classification efficiency, if that data was classified using support vector machines (SVM). In addition, this paper proposes an encoding technique that can identify illegal consumers with better efficiency and faster classification of data.

A Neural Network Model for Driver’s Lane-Changing Trajectory Prediction in Urban Traffic Flow

Abstract: The neural network may learn and incorporate the uncertainties to predict the driver’s lane-changing behavior more accurately. In this paper, we will discuss in detail the effectiveness of Back-Propagation (BP) neural network for prediction of lane-changing trajectory based on the past vehicle data and compare the results between BP neural network model and Elman Network model in terms of the training time and accuracy. Driving simulator data and NGSIM data were processed by a smooth method and then used to validate the availability of the model. The test results indicate that BP neural network might be an accurate prediction of driver’s lane-changing behavior in urban traffic flow. The objective of this paper is to show the usefulness of BP neural network in prediction of lane-changing process and confirm that the vehicle trajectory is influenced previously by the collected data.