A New Approach for the Composition of Adaptive Pervasive Systems

Abstract

In the real world, the assumption that, once generated, a pervasive system of systems and the services it provides will remain static is false. Systems can leave or enter, and service availability in systems can change along with the environmental conditions. The dynamic composition and adaptation of pervasive systems of systems enable them to expand their functionality through leverage resources in the user vicinity. Most of the adaptation approaches based on <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ad hoc</i> networks use service adaptation created from scratch. That is, each time the environment changes, the system starts the composition process over again, resulting in the depletion of system resources and network capacity. We present a protocol for dynamic composition of a pervasive system of systems and their services in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ad hoc</i> networks. Our proposal uses a dynamic and distributed constraint satisfaction approach to establish the pervasive-system-of-systems requirements. In this paper, we deal with spatial and temporal constraints. However, any other kind of restriction, for instance, quality, can be addressed in the same manner. Additionally, a heuristic allowing recomposing services based on the identification of service components disqualified due to the dynamism of the environment is presented. Thus, the adaptation of services is not necessarily done from scratch. Finally, we present simulations that show the performance of our proposal regarding the nearest work in the state of the art, both in time and in number of messages consumed for adapting services.