TY - GEN
T1 - Optimizing Communication with DDQN-Based Adaptive Modulation Coding
T2 - 2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023
AU - Zhang, Lingling
AU - Zhang, Jianan
AU - Tan, Weijie
AU - Tang, Chengkai
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In this paper, we present an adaptive modulation coding scheme based on DDQN algorithm. Taking the different need of communication system into account, we construct two communication strategies, which are energy efficiency prioritized strategy and reliability prioritized strategy. Simulation is conducted over the time varying underwater acoustic channel, with comparison to traditional fixed link and DQN adaptive method. The results show that based on the reliability priority strategy, the DDQN method can select the modulation mode that makes the BER lower in the current environment for data transmission, while based on the energy efficiency priority strategy, the DDQN method could reach higher system throughput and energy efficiency compared to the fixed MCS and DQN adaptive method.
AB - In this paper, we present an adaptive modulation coding scheme based on DDQN algorithm. Taking the different need of communication system into account, we construct two communication strategies, which are energy efficiency prioritized strategy and reliability prioritized strategy. Simulation is conducted over the time varying underwater acoustic channel, with comparison to traditional fixed link and DQN adaptive method. The results show that based on the reliability priority strategy, the DDQN method can select the modulation mode that makes the BER lower in the current environment for data transmission, while based on the energy efficiency priority strategy, the DDQN method could reach higher system throughput and energy efficiency compared to the fixed MCS and DQN adaptive method.
KW - Adaptive Modulation and Coding
KW - Deep Reinforcement Learning
KW - Double Deep Q-network
KW - Underwater Acoustic Communication
UR - http://www.scopus.com/inward/record.url?scp=85184849717&partnerID=8YFLogxK
U2 - 10.1109/ICSPCC59353.2023.10400211
DO - 10.1109/ICSPCC59353.2023.10400211
M3 - 会议稿件
AN - SCOPUS:85184849717
T3 - Proceedings of 2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023
BT - Proceedings of 2023 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 14 November 2023 through 17 November 2023
ER -