Urgency-Aware Reward Redesign for Quality-of-Experience-Oriented Computation Offloading in Deadline-Constrained Mobile Edge Computing
Mobile edge computing (MEC) enables mobile devices to offload computation-intensive tasks to nearby edge nodes in order to reduce delay and improve service continuity. The Quality-of-Experience-Oriented Computation Offloading (QECO) algorithm addresses this problem through a QoE-oriented deep reinforcement learning framework that models computation offloading as a Markov decision process and uses a D3QN-LSTM architecture to jointly consider task completion, delay, and energy consumption [1]. However, the original QECO reward formulation does not explicitly distinguish highly urgent near-deadline tasks from newly arrived tasks with larger timing slack. This limitation may lead to urgency-blind decisions in deadline-constrained MEC environments. In this paper, we propose an urgency-aware reward redesign for QECO while preserving the original MEC system model, state-action representation, and DRL backbone. The proposed modification amplifies the delay penalty according to task urgency and introduces a stronger penalty for unfinished tasks, thereby encouraging more deadline-sensitive offloading behavior without increasing architectural complexity. Experimental comparison with the reproduced original QECO implementation shows lower average delay and fewer dropped tasks, although at the cost of higher energy consumption. Because the redesigned reward uses a different numerical scale from the baseline, absolute QoE/reward magnitudes are reported only with appropriate scale interpretation; performance claims are based primarily on operational metrics such as delay, energy consumption, and task drops. The results indicate that urgency-aware reward shaping is a lightweight and effective extension for improving deadline-constrained MEC offloading.