Wireless sensor network (WSN) technology promises to have a high potential to tackle environmental challenges and to monitor and reduce energy and greenhouse gas emissions. Indeed, WSNs have already been successfully employed in applications such as intelligent buildings, smart grids and energy control systems, transportation and logistics, and precision agriculture. All these applications generally require the exchange of a large amount of data and the localization of the sensor nodes. Both these two tasks can be particularly energy-hungry. Since sensor nodes are typically powered by small batteries, appropriate energy saving strategies have to be employed so as to prolong the lifetime of the WSNs and to make their use attractive and effective. To this aim, the study of data compression algorithms suitable for the reduced storage and computational resources of a sensor node, and the exploration of node localization techniques aimed at estimating the positions of all sensor nodes of a WSN from the knowledge of the exact locations of a restricted number of these nodes, have attracted a large interest in the last years. In this chapter, we discuss how multi-objective evolutionary algorithms can successfully be exploited to generate energy-aware data compressors and to solve the node localization problem. Simulation results show that, in both the tasks, the solutions produced by the evolutionary processes outperform the most interesting approaches recently proposed in the literature.
Exploiting Multi-Objective Evolutionary Algorithms for Designing Energy-Efficient Solutions to Data Compression and Node Localization in Wireless Sensor Networks
VECCHIO, MASSIMO
2013-01-01
Abstract
Wireless sensor network (WSN) technology promises to have a high potential to tackle environmental challenges and to monitor and reduce energy and greenhouse gas emissions. Indeed, WSNs have already been successfully employed in applications such as intelligent buildings, smart grids and energy control systems, transportation and logistics, and precision agriculture. All these applications generally require the exchange of a large amount of data and the localization of the sensor nodes. Both these two tasks can be particularly energy-hungry. Since sensor nodes are typically powered by small batteries, appropriate energy saving strategies have to be employed so as to prolong the lifetime of the WSNs and to make their use attractive and effective. To this aim, the study of data compression algorithms suitable for the reduced storage and computational resources of a sensor node, and the exploration of node localization techniques aimed at estimating the positions of all sensor nodes of a WSN from the knowledge of the exact locations of a restricted number of these nodes, have attracted a large interest in the last years. In this chapter, we discuss how multi-objective evolutionary algorithms can successfully be exploited to generate energy-aware data compressors and to solve the node localization problem. Simulation results show that, in both the tasks, the solutions produced by the evolutionary processes outperform the most interesting approaches recently proposed in the literature.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.