Search

Designing energy-efficient communication protocols is one of the main challenges in wireless sensor networks. This work presents an adaptive radio scheduling schema employing a reinforcement learning algorithm for reducing the energy consumption while preserving the other network performances. By means of a decentralized on-line approach, each nodes determines the most beneficial radio schedule by dynamically adapting to its own traffic load and to the neighbors’ communication activities. We compare our approach with other learning-based MAC protocols as well as conventional MAC approaches and show that, under different simulating scenarios and traffic conditions, our protocol achieves better trade-offs in terms of energy consumption, latency and throughput.

WSNs are becoming an increasingly attractive technology thanks to the significant benefits they can offer to a wide range of application domains. Extending the system lifetime while preserving good network performance is one of the main challenges in WSNs. In this paper, a novel MAC protocol (QL-MAC) based on Q-Learning is proposed. Thanks to a distributed learning approach, the radio sleep-wakeup schedule is able to adapt to the network traffic load. The simulation results show that QL-MAC provides significant improvements in terms of network lifetime and packet delivery ratio with respect to standard MAC protocols. Moreover, the proposed protocol has a moderate computational complexity so to be suitable for practical deployments in currently available WSNs.

Due to the growing exploitation of wireless sensor networks (WSNs) for enhancing all major conventional application domains and enabling brand new application domains, the development of applications based on WSNs has recently gained a significant focus. Thus, design methods, middleware and frameworks have been defined and made available to support high-level programming of WSN applications. However, even though many proposals do exist, more research efforts should still be devoted to the definition of WSN-oriented methodologies and tools fully supporting the development lifecycle of WSN applications. In this chapter, we promote the use of the mobile agent paradigm for the development of WSN applications and, specifically, describe issues and solutions for the development of mobile agent systems on resource-constrained wireless sensor platforms. In particular we discuss about the design of MAPS (Mobile Agent Platform for Sun SPOTs) and TinyMAPS, our Java-based mobile agent systems for WSNs, which enable agent-oriented development of WSN applications. In particular, while MAPS can run on the capable SunSPOT sensor devices, TinyMAPS is a version of MAPS tailored for more constrained Java-based sensor platforms such as Sentilla JCreate. An analysis of MAPS and TinyMAPS is provided showing analogies and differences among the two platforms. Finally a comparison of MAPS with AFME, another Java-based mobile agent system running on SunSPOT and based on a different architecture and programming model, is presented.

Recent years have seen rapid advancements in wireless sensor networks (WSNs) and software agents resulting, among others, in maturation of their technology platforms. Furthermore, benefits of combining these research areas have been analyzed. The MAPS agent platform allows fusion of agents and WSNs. However, due to the hardware limitation, MAPS misses important functionalities needed, for instance, in advanced decision support. Such functions are available, among others, in the JADE agent platform, geared towards more powerful computing devices. Therefore, integration of MAPS and JADE had to be considered. The aim of this paper is to discuss technical issues involved in achieving this goal.

In the context of the development of wireless sensor network (WSN) applications, effective programming frameworks and middlewares for rapid and efficient prototyping of resource-constrained applications are highly required. Mobile agents are an effective distributed programming paradigm that is being used for WSN programming. However its diffusion is limited mainly due to the scarce availability of usable mobile agent systems for WSNs. This paper proposes TinyMAPS, a mobile agent system for programming WSNs based on the Sentilla sensor platform. TinyMAPS derives from MAPS (Mobile Agent Platform for Sun SPOT) and is specifically tailored for sensors more constrained than the Sun SPOTs. After providing a description of TinyMAPS and its comparison with MAPS, a simple yet effective case study implemented with TinyMAPS and concerning a real-time WBSN-based system for human activity monitoring is described.

This paper proposes an architecture conceived for supporting rapid design and implementation of Wireless Body Sensor Network (WBSN) applications having autonomic characteristics. WBSNs represent the most suitable systems for monitoring and controlling physical and biochemical parameters on the human body, and thus supporting high-impact applications in a variety of human-centered domains The effectiveness of WBSN applications is a critical issue since their correctness and efficiency have to be assured not only at design/implementation time but notably at execution time. The autonomic computing paradigm can perfectly meet the critical requirements of WBSN applications such as fault tolerance, adaptability, and reliability, due to its fundamental self-* properties. In particular, our solution is based on the SPINE2 framework and its important distinctive feature is an architecture for guaranteeing the separation of concerns between the user-defined application logic and the autonomic-related operations. Our proposal is finally exemplified through a case study concerning the development of an autonomic application for human activity monitoring.

This paper proposes an overview and comparison of mobile agent platforms for the development of wireless sensor network applications. In particular, the architecture, programming model and basic performance of two Java-based agent platforms, Mobile Agent Platform for Sun SPOT (MAPS) and Agent Factory Micro Edition (AFME), are discussed and evaluated. Finally, a simple yet effective case study concerning a mobile agent-based monitoring system for remote sensing and aggregation is proposed. The proposed case study is developed both in MAPS and AFME so allowing to analyze the differences of their programming models.