In-Network Distributed Solar Current Prediction

TL;DR

This paper introduces a distributed solar current prediction model using linear regression that leverages local and neighboring data, significantly improving prediction accuracy with minimal additional energy cost, validated through a 7-week experiment.

Contribution

The paper presents a novel distributed prediction algorithm that combines local and neighbor data for improved solar current forecasting in sensor networks.

Findings

Prediction accuracy improved by 39.7%

Additional energy cost is negligible at 4.5mJ

Model validated over a 7-week deployment

Abstract

Long-term sensor network deployments demand careful power management. While managing power requires understanding the amount of energy harvestable from the local environment, current solar prediction methods rely only on recent local history, which makes them susceptible to high variability. In this paper, we present a model and algorithms for distributed solar current prediction, based on multiple linear regression to predict future solar current based on local, in-situ climatic and solar measurements. These algorithms leverage spatial information from neighbors and adapt to the changing local conditions not captured by global climatic information. We implement these algorithms on our Fleck platform and run a 7-week-long experiment validating our work. In analyzing our results from this experiment, we determined that computing our model requires an increased energy expenditure of 4.5mJ over simpler models (on the order of 10^{-7}% of the harvested energy) to gain a prediction improvement of 39.7%.