TY - GEN
T1 - Joint Power Optimization of BS and UE in Wireless Networks
AU - Zhang, Dongpo
AU - Tao, Ye
AU - Ding, Lei
AU - Zhu, Lina
AU - Luan, Hao
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The optimization of power control for base station (BS) and user equipment (UE) is crucial to enhance network performance in the dynamic landscape of wireless communication. With the advent of Sixth Generation (6G) communication systems, the demand for real-time communication has surged, leading to a pressing need to develop power optimization strategies that can tackle network latency. We propose a joint power optimization method for both BS and user UE based on the Age of Information (AoI), and address the challenge of power allocation in multi-user communication systems. We begin by modeling a single BS and studying the impact of its power on the AoI. Next, we design a UE power allocation algorithm that considers limited conditions. To achieve this, we transform the problem into a Markov decision problem and solve for the optimal solution using a deep learning algorithm. Our proposed method provides an effective approach to optimize power allocation in multi-user communication systems. The simulation results demonstrate that our proposed algorithm can effectively minimize AoI and achieve on-demand power allocation. Compared to the mean algorithm for power allocation, our proposed algorithm has better performance.
AB - The optimization of power control for base station (BS) and user equipment (UE) is crucial to enhance network performance in the dynamic landscape of wireless communication. With the advent of Sixth Generation (6G) communication systems, the demand for real-time communication has surged, leading to a pressing need to develop power optimization strategies that can tackle network latency. We propose a joint power optimization method for both BS and user UE based on the Age of Information (AoI), and address the challenge of power allocation in multi-user communication systems. We begin by modeling a single BS and studying the impact of its power on the AoI. Next, we design a UE power allocation algorithm that considers limited conditions. To achieve this, we transform the problem into a Markov decision problem and solve for the optimal solution using a deep learning algorithm. Our proposed method provides an effective approach to optimize power allocation in multi-user communication systems. The simulation results demonstrate that our proposed algorithm can effectively minimize AoI and achieve on-demand power allocation. Compared to the mean algorithm for power allocation, our proposed algorithm has better performance.
KW - Age of information
KW - Deep Reinforcement Learning(DRL)
KW - Power allocation
UR - https://www.scopus.com/pages/publications/85181167874
U2 - 10.1109/VTC2023-Fall60731.2023.10333647
DO - 10.1109/VTC2023-Fall60731.2023.10333647
M3 - 会议稿件
AN - SCOPUS:85181167874
T3 - IEEE Vehicular Technology Conference
BT - 2023 IEEE 98th Vehicular Technology Conference, VTC 2023-Fall - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 98th IEEE Vehicular Technology Conference, VTC 2023-Fall
Y2 - 10 October 2023 through 13 October 2023
ER -