Large scale testing of pervasive computing systems using multi-agent simulation

Abstract

The rapid growth of handheld computing devices such as mobile phones, PDAs or palmtops is paving the way for the emergence of pervasive computing systems. Just as in the case of traditional computing systems, pervasive computing systems need to be tested in the large before they can be deployed in the field. As opposed to traditional computing systems, however, large-scale testing of pervasive computing systems requires the presence of dozens (perhaps hundreds) of physical devices, arranged together in a network, executing a variety of complex scenarios. In order to reduce the cost of such testing, it would be better to simulate the operation of a pervasive computing system using well-known techniques from multi-agent simulation, by representing each (hardware or software) component of the system as a software agent. In this paper we describe our ongoing work, where we extend our earlier work on multi-agent simulation, for pervasive computing systems. Since adaptation in pervasive computing systems is expected to be common, we also show that our simulation technique can model adaptation.