Energy Availability Forecasting for Harvesting-aware Wireless Sensor Networks: Analysis of Energy Demand of a Predictor Based on Evolutionary Fuzzy Rules

Environmental monitoring sensor networks often operate in remote locations and thus must be designed for energy-efficiency and reliability. The first goal of energy efficiency can be achieved through low-power design of the monitoring hardware, often supplemented by energy management schemes of varying complexity and sophistication. In case of sensor nodes endowed with energy-harvesting capabilities, the energy management systems can take advantage of harvesting outlook that can take the form of prediction of energy available for harvest in the near future. When designing such sophisticated prediction and management schemes, it is important to consider the energy cost of gathering the predictor data and executing the forecasting algorithm. This contribution describes the results of experiments designed to assess the energy required to run a recently introduced energy-availability forecasting algorithm based on evolutionary fuzzy rules. In particular, it presents an analysis of experiments conducted using several hardware platforms typically used to implement the computational core of environmental sensor nodes. The results clearly show the advantages of using modern low-power, 32-bit hardware platforms. In addition, they demonstrate the advantages of support for floating point operations, as well the importance of embedded code optimization to maximize the benefits of the modern microcontroller units.