Just-in-Time Adaptive Algorithm for Optimal Parameter Setting in 802.15.4 WSNs

摘要

Recent studies have shown that the IEEE 802.15.4 MAC protocol suffers from severe limitations, in termsudof reliability and energy efficiency, when the CSMA/CA parameter setting is not appropriate. However,udselecting the optimal setting that guarantees the application reliability requirements, with minimumudenergy consumption, is not a trivial task in wireless sensor networks, especially when the operatingudconditions change over time. In this paper we propose a Just-in-Time LEarning-based Adaptive Parameterudtuning (JIT-LEAP) algorithm that adapts the CSMA/CA parameter setting to the time-varying operatingudconditions by also exploiting the past history to find the most appropriate setting for the currentudconditions. Following the approach of active adaptive algorithms, the adaptation mechanism of JIT-LEAPudis triggered by a change detection test only when needed (i.e., in response to a change in the operatingudconditions). Simulation results show that the proposed algorithm outperforms other similar algorithms,udboth in stationary and dynamic scenarios.