With the rapid proliferation of intelligent video analytics in real-time applications such as the Internet of Vehicles and urban surveillance, Mobile Edge Computing (MEC) systems face persistent challenges, including complex inter-frame dependencies, severe bandwidth fluctuations, and intensive resource contention. Conventional offloading strategies based on fixed rules or static weights are often inadequate for maintaining robustness in scenarios with conflicting multi-objective requirements. To address these challenges, this paper proposes PGN-MO-DDQN, an adaptive multi-objective reinforcement learning framework for task offloading and scheduling, driven by a Preference Generation Network (PGN). The proposed framework leverages the multi-objective architecture of Double-DQN and incorporates a PGN to automatically produce dynamic weight vectors for latency, load balancing, and analytical accuracy (mean average precision, mAP) according to real-time system states, while dynamically determining the offloading ratio between local and edge processing to balance communication latency and computational load, thereby enabling adaptive multi-objective optimization. Experimental evaluations conducted on the EdgeSimPy platform show that, compared with representative baseline algorithms such as Greedy, Fixed-DDQN, HRL-V2I, and TOLB, PGN-MO-DDQN reduces average task latency by 17%, decreases server load imbalance by 13%, and improves mAP by 5.8%. Overall, the proposed framework provides a robust solution for adaptive multi-objective video offloading, effectively balancing latency, accuracy, and resource use in dynamic edge environments.
更多
原文链接
分享
引用
