Multi objective genetic algorithm based adaptive QoS routing in MANET

Areas in which Genetic Algorithm (GA) excel is their ability to manipulate many parameters simultaneously, their use of parallelism enables them to produce multiple equally good solutions to the same problem. So GAs are most appropriate for multi objective optimization problems, in which there is no single value to be minimized or maximized, but having multiple objectives, usually with tradeoffs involved: one can only be improved at the expense of another. By looking at this strength of GA we have applied MultiObjective GA to support QoS Routing in Mobile Ad-hoc Network (MANET). A MANET is dynamic multi-hop wireless network established by a group of mobile nodes on a shared wireless channel by virtue of their proximity to each other. To support mobility to user generally low configured nodes are in use, so limited resources, dynamic network topology and link variations are the issues with MANET. So, Routing in such a dynamic environment is a challenging issue, lots of work has been done for routing in MANET but QoS (Quality of Service) requirements are not yet supported that way, and in this scenario to find optimal path is a problem of NP class. We have applied MultiObjective Genetic algorithm: to optimize four QoS parameters bandwidth constraints, delay, traffic from adjacent nodes, and number of hops, and to provide adaptive route in MANET. Our experiment is based on Network Simulator NS-2.28 and results show that GA based approach is better than traditional method.