Partner selection in self-organised wireless sensor networks for opportunistic energy negotiation: A multi-armed bandit based approach

The proliferation of “Things” over a network creates the Internet Things (IoT), where sensors integrate to collect data from environment long periods time. growth IoT applications will inevitably involve co-locating multiple wireless sensor networks, each serving different with, possibly, needs and constraints. Since energy is scarce in nodes equipped with non-rechargeable batteries, harvesting technologies have been focus research recent years. However, new problems arise as result their wide spatio-temporal variation. Such shortcoming can be avoided if co-located networks cooperate other share available energy. Due unique characteristics owners, recently, we proposed negotiation approach deal conflict preferences. Unfortunately, impractical large number participants, especially an open environment. Given this, introduce partner selection technique based on multi-armed bandits (MAB), that enables node learn strategy optimises its resources term. Our results show solution allows repeatedly current best dynamic performance such evaluated through simulation shows achieve efficiency 72% against optimal most challenging scenario studied this work.