| Sequential dynamic resource allocation in multi-beam satellite systems:A learning-based optimization method |
| |
| 作者姓名： | Yixin HUANG Shufan WU Zhankui ZENG Zeyu KANG Zhongcheng MU Hai HUANG |
| |
| 作者单位： | 1. School of Aeronautics and Astronautics, Shanghai Jiao Tong University;2. Shanghai Academy of Spaceflight Technology;3. School of Astronautics, Beihang University |
| |
| 基金项目： | co-supported by the National Natural Science Foundation of China (No. U20B2056)； |
| |
| 摘 要： | Multi-beam antenna and beam hopping technologies are an effective solution for scarce satellite frequency resources. One of the primary challenges accompanying with Multi-Beam Satellites(MBS) is an efficient Dynamic Resource Allocation(DRA) strategy. This paper presents a learning-based Hybrid-Action Deep Q-Network(HADQN) algorithm to address the sequential decision-making optimization problem in DRA. By using a parameterized hybrid action space,HADQN makes it possible to schedule the beam patte...
|
| 收稿时间： | 26 May 2022 |
Sequential dynamic resource allocation in multi-beam satellite systems: A learning-based optimization method |
| |
| Yixin HUANG,Shufan WU,Zhankui ZENG,Zeyu KANG,Zhongcheng MU,Hai HUANG.Sequential dynamic resource allocation in multi-beam satellite systems:A learning-based optimization method[J].Chinese Journal of Aeronautics,2023,36(6):288-301. |
| |
| Institution: | 1. School of Aeronautics and Astronautics, Shanghai Jiao Tong University, Shanghai 200240, China;2. Shanghai Academy of Spaceflight Technology, Shanghai 200240, China;3. School of Astronautics, Beihang University, Beijing 100191, China |
| |
| Abstract: | Multi-beam antenna and beam hopping technologies are an effective solution for scarce satellite frequency resources. One of the primary challenges accompanying with Multi-Beam Satellites (MBS) is an efficient Dynamic Resource Allocation (DRA) strategy. This paper presents a learning-based Hybrid-Action Deep Q-Network (HADQN) algorithm to address the sequential decision-making optimization problem in DRA. By using a parameterized hybrid action space, HADQN makes it possible to schedule the beam pattern and allocate transmitter power more flexibly. To pursue multiple long-term QoS requirements, HADQN adopts a multi-objective optimization method to decrease system transmission delay, loss ratio of data packets and power consumption load simultaneously. Experimental results demonstrate that the proposed HADQN algorithm is feasible and greatly reduces in-orbit energy consumption without compromising QoS performance. |
| |
| Keywords: | Beam hopping Deep reinforcement learning Dynamic resource allocation Mixed-integer programming Multi-beam satellite systems Multi-objective optimization |
| 本文献已被 ScienceDirect 等数据库收录！ |
