Weighted delay prediction in mobile ad hoc network using fuzzy time series

Abstract

Several parameters like routing protocol, mobility pattern, average speed of mobile nodes, path length from source to destination, previous delay, etc., affect the end-to-end packet delay in mobile ad hoc network. But the nature of relationship between end-to-end delay and those parameters is still unclear. In this article, we have tried to establish a relationship among end-to-end delay, path length and previous delay. A regression equation is established between path length and end-to-end delay. The end-to-end delay is also represented as a fuzzy time series. The current end-to-end delay is then obtained by combining delay predicted by path length regression equation and fuzzy time series. The suitable weights of these two predicted delays are also experimentally determined. To the best of our knowledge, comprehensive analysis for packet delay estimation using various network parameters along with fuzzy time series has not been explored earlier. Based on various performance evaluation criterion, we found that by combining the predicted values of delay using path length regression and fuzzy time series gives satisfactory packet delay prediction in ad hoc network.

Keywords

• Network delay
• Mobile ad hoc network
• Trapezoidal fuzzy numbers
• Path length