Litcius/Paper detail

DRL based Joint Affective Services Computing and Resource Allocation in ISTN

Kexin Xu, Haijun Zhang, Keping Long, Jianquan Wang, Lei Sun

2022ACM Transactions on Multimedia Computing Communications and Applications13 citationsDOI

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.

Topics & Concepts

Computer scienceComputation offloadingComputationDistributed computingOptimization problemLatency (audio)Energy consumptionResource allocationWirelessComputer networkArtificial intelligenceEdge computingTelecommunicationsAlgorithmBiologyEnhanced Data Rates for GSM EvolutionEcologySatellite Communication SystemsIoT and Edge/Fog ComputingAdvanced Wireless Communication Technologies
DRL based Joint Affective Services Computing and Resource Allocation in ISTN | Litcius