多波束卫星动态信道资源分配算法
|
摘要
多波束卫星移动通信系统通过频率复用技术提升了频谱效率,但由于波束间通信业务量分布具有非均匀特性,导致资源利用率较低。针对以上问题,结合强化学习技术,研究设计能够避免同频干扰的动态资源分配算法,结果表明,该算法大大降低了系统阻塞概率,信道资源得到进一步有效利用。
The multi-beam satellite mobile communication system improves the spectrum efficiency through frequency reuse technology, but the resource utilization is low due to the non-uniform characteristics of inter-beam communication traffic distributions. In view of the above problems, a dynamic resource allocation algorithm to avoid co-channel interference is investigated based on reinforcement learning techniques. Simulation results show that the proposed algorithm not only greatly reduces the system blocking probability, but also effective utilizes channel resources.
The multi-beam satellite mobile communication system improves the spectrum efficiency through frequency reuse technology, but the resource utilization is low due to the non-uniform characteristics of inter-beam communication traffic distributions. In view of the above problems, a dynamic resource allocation algorithm to avoid co-channel interference is investigated based on reinforcement learning techniques. Simulation results show that the proposed algorithm not only greatly reduces the system blocking probability, but also effective utilizes channel resources.
引文
[1]Vasavada Y,Gopal R,Ravishankar C,et al.Architectures for next generation high throughput satellite systems[J].International Journal of Satellite Communications and Networking,2016,34(4):523-546.
[2]杨澄雄,徐智超.多波束卫星通信系统资源的动态分配研究[J].信息通信,2015(5):209.
[3]焦李成,赵进,杨淑媛,等.深度学习、优化与识别[M].北京:清华大学出版社,2017:197-208.
[4]Xu Z,Wang Y,Tang J,et al.A deep reinforcement learning based framework for power-effi cient resource allocation in cloud RANs[C]//IEEE International Conference on Communications.IEEE,2017.
[5]R Sutton,A Barto.Reinforcement Learning:an Introduction(second edition)[M].2017:1-7.
[6]Santos E C.A Simple Reinforcement Learning Mechanism for Resource Allocation in LTE-A Networks with Markov Decision Process and Q-Learning[J].2017.
[7]周志华.机器学习[M].北京:清华大学出版社,2016:371-397.
[8]Mengmeng C,Weina H.A printed quadrifilar-helical antenna for Ku-band mobile satellite communication terminal[C]//2017 IEEE 17th International Conference on Communication Technology(ICCT).IEEE,2017:755-759.
[9]Wang X,Li X,Leung V C M.Artificial IntelligenceBased Techniques for Emerging Heterogeneous Network:State of the Arts,Opportunities,and Challenges[J].IEEEAccess,2017(3):1379-1391.
[10]Li R,Zhao Z,Xuan Z,et al.Intelligent 5G:When Cellular Networks Meet Artifi cial Intelligence[J].IEEEWireless Communications,2017(99):2-10.
[11]Sanctis M D,Cianca E,Araniti G,et al.Satellite Communications Supporting Internet of Remote Things[J].IEEE Internet of Things Journal,2016,3(1):113-123.
[2]杨澄雄,徐智超.多波束卫星通信系统资源的动态分配研究[J].信息通信,2015(5):209.
[3]焦李成,赵进,杨淑媛,等.深度学习、优化与识别[M].北京:清华大学出版社,2017:197-208.
[4]Xu Z,Wang Y,Tang J,et al.A deep reinforcement learning based framework for power-effi cient resource allocation in cloud RANs[C]//IEEE International Conference on Communications.IEEE,2017.
[5]R Sutton,A Barto.Reinforcement Learning:an Introduction(second edition)[M].2017:1-7.
[6]Santos E C.A Simple Reinforcement Learning Mechanism for Resource Allocation in LTE-A Networks with Markov Decision Process and Q-Learning[J].2017.
[7]周志华.机器学习[M].北京:清华大学出版社,2016:371-397.
[8]Mengmeng C,Weina H.A printed quadrifilar-helical antenna for Ku-band mobile satellite communication terminal[C]//2017 IEEE 17th International Conference on Communication Technology(ICCT).IEEE,2017:755-759.
[9]Wang X,Li X,Leung V C M.Artificial IntelligenceBased Techniques for Emerging Heterogeneous Network:State of the Arts,Opportunities,and Challenges[J].IEEEAccess,2017(3):1379-1391.
[10]Li R,Zhao Z,Xuan Z,et al.Intelligent 5G:When Cellular Networks Meet Artifi cial Intelligence[J].IEEEWireless Communications,2017(99):2-10.
[11]Sanctis M D,Cianca E,Araniti G,et al.Satellite Communications Supporting Internet of Remote Things[J].IEEE Internet of Things Journal,2016,3(1):113-123.