Predicting Quality‐of‐Service for Nomadic Applications Using Intelligent Agents
P. Misikangas, Mikko Mäkelä, Kimmo E. E. Raatikainen · 2001
Chapter fifteen addresses an important problem associated with adapting wireline software applications for wireless networks, namely variations in Quality-of-Service (QoS). The research project Monads studies the short term predictability of available QoS, enabling applications to adjust their behaviour dynamically to the forthcoming QoS. The results presented clearly indicate that intelligent agents can learn the key characteristics, including the tempo-spatial variation of available QoS, quite quickly, so that reasonable predictions of available QoS in the near feature are possible.