PROJECT TITLE :
Networks of learning automata for the vehicular environment: a performance analysis study
Due to the stringent constraints of constant topological changes and low finish-to-finish delay, knowledge forwarding within the vehicular enviornment is usually a challenging task. In this article, we tend to have analyzed the performance of networks of learning automata (LA) using the ideas of the Bayesian coalition game in the vehicular atmosphere. LA are assumed to be the players in the game, which kind a coalition primarily based on some predefined strategy from the strategy space. Each action taken by the players in the game may be rewarded or penalized by the surroundings in which they operate. The setting provides a feedback for every action taken by the LA. The probability of choice of an action is estimated using the Bayesian conditional likelihood on the payoff corresponding to every player. When fetching input from the atmosphere, the LA update their action likelihood vector. The performance of the proposed scheme is evaluated in different network conditions in a real setting by varying the learning rates of the automaton. A 20-thirty % enhancement of the successful packet delivery ratio has been observed using the proposed scheme within the vehicular atmosphere.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here