Affiliation:
1. Beijing Advanced Innovation Center for Materials Genome Engineering, Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services, University of Science and Technology Beijing, Beijing, China
2. The School of Automation Science and Electrical Engineering, University of Science and Technology Beijing, Beijing, China
Abstract
Affective services will become a research hotspot in
artificial intelligence (AI)
in the next decade. In this paper, a novel service paradigm combined with wireless communication in
integrated satellite-terrestrial network (ISTN)
is proposed. On this basis, an
affective services computing offloading and transmission network (ASCTN)
with a three-tier computation architecture is proposed, which is able to assist users to obtain affective computing services and regulate emotions. The optimization problem is investigated in the ASCTN, which is a discrete, non-linear, and non-convex problem with the limitation of computation ability of satellite and transmit power. Specifically, with the objective to minimize the cost utility related to latency and energy consumption, a joint affective services tasks computing offloading strategy, sub-channel, and power allocation algorithm based on
dueling deep Q-network (Dueling-DQN)
is proposed, which is in possession of better stability. The simulation results reveal the effectiveness of the optimization algorithm in terms of the cost utility in the ASCTN system.
Funder
National Key R&D Program of China
National Natural Science Foundation of China
Beijing Natural Science Foundation
China University Industry-University-Research Collaborative Innovation Fund
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications,Hardware and Architecture
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献