Pro-Energy: A novel energy prediction model for solar and wind energy-harvesting wireless sensor networks

  • Authors:

  • Alessandro Cammarano;Chiara Petrioli;Dora Spenza

  • Affiliations:

  • Computer Science Department Sapienza University of Rome Rome, Italy;Computer Science Department Sapienza University of Rome Rome, Italy;Computer Science Department Sapienza University of Rome Rome, Italy

  • Venue:
  • MASS '12 Proceedings of the 2012 IEEE 9th International Conference on Mobile Ad-Hoc and Sensor Systems (MASS)
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Energy harvesting is one of the most promising technologies towards the goal of perpetual operation of wireless sensor networks (WSNs). Environmentally-powered systems, however, have to deal with the variable behavior of ambient energy sources, which results in different amounts and rates of energy available over time. To alleviate the problem of the harvested power being neither constant nor continuous, energy prediction methods can be employed. Such models forecast the source availability and estimate the expected energy intake, allowing the system to take critical decisions about the utilization of the available energy. In this work, we present a novel energy prediction model, named Pro-Energy (PROfile energy prediction model), for multi-source energy harvesting WSNs, which is able to leverage past energy observations to provide accurate estimations of future energy availability. To assess the performance of our proposed solution, we use real-life solar and wind traces that we collected by interfacing TelosB nodes with solar cells and wind micro-turbines, as well as public available traces of solar and wind obtained from weather monitoring stations in the US. A comparative performance evaluation between Pro-Energy and energy predictors previously proposed in the literature, such as EWMA and WCMA, has shown that our solution significantly outperforms existing algorithms for both short and medium term prediction horizons, improving the prediction accuracy up to 60%.