Networking and Communication Engineering

S. Mahalakshmi ¹, R. Pradipa ¹

Affiliations
1 KLN College of Information Technology, Madurai, IN

Abstract

Infrastructure-less and Self-organized networks among vehicles are known as Vehicular ad hoc networks (VANETs). Designing efficient routing protocols for rapid topology changing environment is a major concern. Optimized Link State Routing protocol (OLSR) - link state, table driven proactive protocol uses control messages to identify the link state information everywhere in the network. Being a Proactive protocol routes to all destinations within the networks are known and maintained before use, which leads to uncertainty for the Data transmission. Due to this limitation in OLSR it is necessary to optimize the routing. In this study, to minimize the Uncertainty in OLSR routing due to the frequent change in the topology, Rough Set Theory (RST) is used. Our proposal is further validated by simulation.

Keywords

Connectivity Time, Dynamic Source Routing Protocol (DSR), Optimized Link State Routing Protocol, Rough Set Theory, Vehicular Ad hoc Networks.

Full Text

     

S. Sabeetha Saraswathi ¹, S. Mohana ², N. Vijayaraj ³, S. Imavathy ⁴, S. Mahalakshmi ⁴

Affiliations
1 Department of Computer Science and Engineering, Shri Angalamman College of Engineering & Technology, Siruganoor, Trichy, Tamilnadu, IN
2 Department of Computer Science and Engineering, M.I.E.T. College of Engineering, Trichy, Tamilnadu, IN
3 Department of Information Technology, Shri Angalamman college of Engineering & Technology, Siruganoor, Trichy, Tamilnadu, IN
4 Department of IT, E.G.S. Pillay Engineering College, Nagapattinam, IN

Abstract

The core functions of grid computing are Resource allocation and job scheduling. These functions are based on adequate information of available resources. Timely acquiring resource status information is of great importance in ensuring overall performance of grid computing. This work aims at building a distributed system for grid resource monitoring and prediction. The system architecture for grid resource monitoring and prediction has been design. The key issues for system implementation, including machine learning-based methodologies for modeling and optimization of resource prediction models are discussed. Evaluations are performed on a prototype system. The experimental results indicate that the efficiency and accuracy of the system meet the demand of online system for grid resource monitoring and prediction.

Keywords

Grid Resource, Monitoring and Prediction, Neural Network, Support Vector Machine, Genetic Algorithm, Particle Swarm Optimization.

Full Text