Multi-agent reinforcement learning aided smart agriculture networks

Abstract

An unmanned aerial vehicle (UAV) agent for forming a two-tier hybrid smart agriculture network architecture is provided. The UAV agent is configured to support two communication protocols, a short-range communication protocol and a long-range communication protocol. The agriculture sensor gathers agriculture data such as soil temperature and participates in a first-tier short range wireless communication network to send the collected data to at least one UAV agent. A UAV agent participates in one or more first-tier short-range communication networks to pick up sensor data from agriculture sensors in one or more clusters and also participates in a second-tier long-range communication network to route the collected sensor data to at least one cloud server. The tasks in both tier networks are formulated as optimization problems to achieve optimal data delivery and solved by using multi-agent reinforcement learning (MARL), which is implemented by the invented Focus Coordination Multi-Agent Deep Deterministic Policy Gradient (FC-MADDPG) algorithm.