An Energy Management Optimization Method for Arctic Space Environment Monitoring Buoys Based on Deep Reinforcement Learning

To address the long-term operational challenges of space environment monitoring buoys under extreme Arctic conditions, this paper proposes an energy management optimization method based on deep reinforcement learning algorithms. By constructing a buoy system model integrating renewable energy and lithium-ion battery power supply units, battery energy storage units, and multi-sensor load units, and incorporating Arctic environmental models with low-temperature battery efficiency degradation patterns, a reward function was designed to minimize unsupplied energy while ensuring functional integrity. Using the Twin Delay Deep Deterministic Policy Gradient (TD3) algorithm on the MATLAB simulation platform, the effectiveness of different energy storage configurations for achieving long-term observation in Arctic environments was compared. Results demonstrate that this method significantly enhances the buoy’s endurance and scheduling intelligence, offering new insights for energy management in intelligent polar observation equipment.