Adaptive Deadline- and Energy-Aware Caching Algorithms in Dynamic Multi-UAV Edge Networks

The paper proposes two caching strategies for multi‑UAV edge networks that jointly consider content deadlines, UAV communication energy, and energy imbalance. The first, DE‑UBAC, uses a rule‑based hierarchical approach with deadline prioritization and cooperative placement, but its fixed thresholds limit adaptability. The second, GRU‑DEPPO, integrates GRU‑based temporal representations with a centralized PPO actor‑critic, achieving a 61% lower deadline‑miss rate and 40% reduced energy imbalance compared to DE‑UBAC.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• reinforcement-learning