Abstract
The increasing evolution of computing technologies has fostered the new intelligent concept of Ubiquitous computing (Ubicomp). Ubicomp environments encompass the introduction of new paradigms, such as Internet of Things (IoT), Mobile computing, and Wearable computing, into communication networks, which demands more efficient strategies to deliver tasks and services, considering heterogeneity, scalability, reliability, and efficient energy consumption of the connected devices. Middlewares have a crucial role to deal with all these aspects, by implementing efficient load balancing methods based on the hardware characterization and the computational cost of the queries and tasks. However, most existing solutions do not take into account both considerations in conjunction. In this context, we propose a methodology to characterize distributed servers, services, and network delays in Ubicomp environments, based on the Server Ability to Answer a Query (SAAQ). To evaluate our SAAQ-based methodology, we implemented a simple middleware in a museum context, in which different IoT devices (e.g., social robots, mobile devices) and distributed servers with different capabilities can participate, and performed a set of experiments in scenarios with diverse hardware and software characteristics. Results show that the middleware is able to distribute queries to servers with adequate capacity, freeing from service requests to devices with hardware restrictions; thus, our SAAQ-based middleware has a good performance regarding throughput (22.52 ms for web queries), end-to-end delay communications (up to 193.30 ms between San Francisco and Amsterdam), and good management of computing resources (up to 80% of CPU consumption).