Research Article
Deep Reinforcement Learning-Based Channel and Power Allocation in Multibeam LEO Satellite Systems
@INPROCEEDINGS{10.1007/978-3-031-70507-6_9, author={Junrong Li and Fuzhou Peng and Xijun Wang and Xiang Chen}, title={Deep Reinforcement Learning-Based Channel and Power Allocation in Multibeam LEO Satellite Systems}, proceedings={IoT as a Service. 9th EAI International Conference, IoTaaS 2023, Nanjing, China, October 27-29, 2023, Proceedings}, proceedings_a={IOTAAS}, year={2024}, month={10}, keywords={Multibeam satellite system Dynamic resource allocation Deep reinforcement learning}, doi={10.1007/978-3-031-70507-6_9} }- Junrong Li
Fuzhou Peng
Xijun Wang
Xiang Chen
Year: 2024
Deep Reinforcement Learning-Based Channel and Power Allocation in Multibeam LEO Satellite Systems
IOTAAS
Springer
DOI: 10.1007/978-3-031-70507-6_9
Abstract
With the continuous growth in communication demand, improving the efficiency of resource allocation becomes crucial. Furthermore, flexible resource allocation for meeting the non-uniform and time-varying traffic demand has emerged as an important task in multi-beam satellite systems. To improve power utilization and meet dynamic traffic demand, this paper formulates an optimization objective that minimizes the trade-off between the unmet traffic demand and power consumption. This is realized by optimizing the allocation of channel and their power, while considering the impact of co-channel interference(CCI). We propose the deep reinforcement learning (DRL) technique to optimize resource allocation. Simulation comparisons between our proposed algorithm and benchmark schemes show its effectiveness in achieving a balance between power allocation and traffic demands. Notably, our algorithm outperforms others in terms of power consumption and meeting traffic demand.
