Optimizing AIGC Service Provider Selection Based on Deep Q-Network for Edge-Enabled Healthcare Consumer Electronics Systems
Xiaohong Lyu, Shalli Rani, Yanhong Feng · IEEE Transactions on Consumer Electronics · 2024
Artificial Intelligence Generated Content (AIGC) offers to significantly augment Healthcare Consumer Electronics (HCE) systems and advance chronic disease management and patient care by automating diagnostics, and optimizing medical records management. Despite AIGC’s potential, its integration into healthcare poses significant challenges, primarily due to the substantial computational resources required and the paramount importance of securing sensitive health data. The collaborative AIGC framework offers a promising solution by deploying trained AIGC models on network edge servers. This study addresses the complex challenge of selecting an AIGC Service Provider (ASP) within the collaborative AIGC framework for HCE, identifying the optimization of service provision and energy consumption as critical objectives. It models the ASP selection problem as a Markov Decision Process (MDP), proposing a novel Deep Q-Network (DQN)-based algorithm with a dual reward function focusing on maximizing user utility and minimizing energy consumption. Through simulation experiments and comparative analysis, the study validates the effectiveness of the DQN algorithm in optimizing ASP selection, contributing to the fields of AIGC and HCE.