Using Neural-Networks to Reduce Entity State Updates in Distributed Interactive Applications

Dead reckoning is the most commonly used predictive contract mechanism for the reduction of network traffic in Distributed Interactive Applications (DIAs). However, this technique often ignores available contextual information that may be influential to the state of an entity, sacrificing remote predictive accuracy in favour of low computational complexity. In this paper, we present a novel extension of dead reckoning by employing neural- networks to take into account expected future entity behaviour during the transmission of entity state updates (ESUs) for remote entity modeling in DIAs. This proposed method succeeds in reducing network traffic through a decrease in the frequency of ESU transmission required to maintain consistency. Validation is achieved through simulation in a highly interactive DIA, and results indicate significant potential for improved scalability when compared to the use of the IEEE DIS Standard dead reckoning technique. The new method exhibits relatively low computational overhead and seamless integration with current dead reckoning schemes.