OFDM Relay Cognitive Radio Multiple Antennas Resource Allocation Full Duplex Spectrum Sensing Synchronization Spectrum Sharing Interference Cancellation Channel Estimation Feedback Heterogeneous Networks Bi-directional Energy Harvesting Stochastic Geometry HetNet relay networks FBMC Equalization channel capacity TVWS CDMA interference in-band full-duplex system Duplex MIMO Ultra Low Power C-V2V 5G Reliability SC-FDMA interference suppression D-TDD CLI indoor positioning reinforcement learning RSRP weighting - Computation offloading smart factory Cell-free multi-access edge computing estimated position overlapping —Device-to-device (D2D) estimated position updating mMIMO control overhead hybrid NR positioning Femtocell Rat-dependent positioning frame structure Zigbee body area networks channel estimation error Handoff CoMP User grouping power uncertainty ultra-dense small cell network mode selection antenna arrays 5G mobile communication UFMC resource block management inter user interference WVAN health care partial overlap GFDM Dynamic TDD Multi-user Receiver Number of training blocks Uplink SCMA system V2X Vehicular communication cross-link interference LTE-TDD FS-NOMA Location-based user fairness Mode 3 QR Factorization Metaheuristics P-NOMA non-orthogonal multiple access dynamic HetNet spectrum partitioning and 5G networks. massive connectivity non-orthogonal multiple access (NOMA) overloading DQN OTDOA distributed mode Communication range resource selection maximum likelihood method Resource sharing Power allocation packet delay
Status : Presented 
Date : 2020-12 
Title : Deep Reinforcement Learning-based Task Offloading Decision in the Time Varying Channel 
Authors : Jinkyo Jeong, Ilmin Kim, and Daesik Hong 
Conference : ICEIC 
Abstract : This paper proposes a dynamic task offloading decision control scheme to minimize the total delay to execute computation task taking into account the time-varying channel. Specifically, we consider the practical task offloading process, where executing computation task is carried out over multiple channel coherence times. In order to make an accurate decision on the task offloading process performed over multiple channel coherence times, we utilize the model-free reinforcement learning, since environment dynamics of the system, channel transition probabilities, is challenging to estimate. We formulate a problem of minimizing the total delay of executing computation task based on a Markov decision process (MDP). In order to solve the MDP problem, we develop a model-free reinforcement learning algorithm. Simulation results show that our proposed scheme outperforms the conventional scheme. 

.

List of Articles
No.
Status Datesort
» [ICEIC] Jinkyo Jeong, Ilmin Kim, and Daesik Hong, "Deep Reinforcement Learning-based Task Offloading Decision in the Time Varying Channel" ICEIC 2021 Presented  2020-12