面向分層異構(gòu)網(wǎng)絡(luò)的資源分配：一種穩(wěn)健分層博弈學(xué)習(xí)方案
doi: 10.11999/JEIT160285 cstr: 32379.14.JEIT160285
-
2.
(解放軍理工大學(xué)通信工程學(xué)院 南京 210007) ②(南京電訊技術(shù)研究所 南京 210007) ③(解放軍信息工程大學(xué)信息系統(tǒng)工程學(xué)院 鄭州 450000) ④(洛陽(yáng)理工學(xué)院 洛陽(yáng) 471023)
基金項(xiàng)目:
國(guó)家自然科學(xué)基金(61471395, 61401508)，江蘇省自然科學(xué)基金(BK20161125)
Resource Allocation for Heterogeneous Wireless Networks: A Robust Layered Game Learning Solutions
-
2.
(College of Communications Engineering, PLA University of Science and Technology, Nanjing 210007, China)
Funds:
The National Natural Science Foundation of China (61471395, 61401508), The Natural Science Foundation of Jiangsu Province, China (BK20161125)
-
摘要: 該文研究了信道狀態(tài)不確定條件下分層異構(gòu)微蜂窩網(wǎng)絡(luò)中的無(wú)線資源分配優(yōu)化問(wèn)題。首先引入信道不確定模型描述無(wú)線信道的隨機(jī)動(dòng)態(tài)性，并將該問(wèn)題建模為考慮信道不確定度的雙層魯棒斯坦伯格博弈；然后給出了該博弈的均衡點(diǎn)分析；最后提出了一種分布式改進(jìn)型分層Q學(xué)習(xí)方案以實(shí)現(xiàn)宏基站和微基站的均衡策略搜索。理論分析和仿真表明，所提出的分層博弈模型可以有效抑制由于信道狀態(tài)不確定引起的收益下降。所采用的學(xué)習(xí)方案較傳統(tǒng)Q學(xué)習(xí)方案收斂速度明顯加快，更加適用于短時(shí)快變的通信環(huán)境。
-
關(guān)鍵詞:
- 異構(gòu)網(wǎng)絡(luò) /
- 斯坦伯格博弈 /
- 不完美信道信息 /
- 魯棒決策 /
- 雙層Q學(xué)習(xí) /
- 離散策略
Abstract: This paper investigates a resource allocation scheme in heterogeneous wireless small cell networks with imperfect Channel State Information (CSI). In this work, the math expression for the stochastic dynamic uncertainty in CSI is proposed for model analysis and the robust Stackelberg game model with various interference power constraints is established firstly. Then, the Stackelberg game Equilibrium (SE) is obtained and analyzed. Lastly, an improved hierarchical Q-learning algorithm is also given to search the Stackelberg equilibrium strategies of macro-cell base station and small-cell base station. Both theoretical analysis and simulation results verify the proposed scheme can effectively restrain declining revenue due to incomplete CSI and the proposed algorithms can improves the convergence rate, especially applicable to the fast varying communication environment. -
ZAHIR T, ARSHAD K, NAKATA A, et al. Interference management in femtocells[J]. IEEE Communication Survey Tutorials, 2013, 15(1): 293-311. doi: 10.1109/SURV.2012. 020212.00101. HAN Zhu, NIYATO D, SAAD W, et al. Game Theory in Wireless and Communication Networks[M]. Cambridge: UK, Cambridge University Press, 2012: 88-91. 扶奉超, 張志才, 路兆銘, 等. Femtocell雙層網(wǎng)絡(luò)中基于Stackelberg博弈的節(jié)能功率控制算法[J]. 電子科技大學(xué)學(xué)報(bào), 2015, 44(3): 363-368. FU Fengchao, ZHANG Zhicai, LU Zhaoming, et al. Energy- efficient power control algorithm based on Stackelberg game in two-tier femtocell Networks[J]. Journal of University of Electronic Science and Technology of China, 2015, 44(3): 363-368. LASHGARI M, MAHAM B, KEBRIAEI H, et al. Distributed power allocation and interference mitigation in two-tier femtocell networks: A game-theoretic approach[C]. Wireless Communications and Mobile Computing Conference, Dubrovnik, Croatia, 2015: 55-60. DUONG N D, MADHUKUMAR A S, and NIYATO D. Stackelberg Bayesian game for power allocation in two-tier networks[J]. IEEE Transactions on Vehicular Technology, 2016, 65(4): 2341-2354. doi: 10.1109/TVT.2015.2418297. ZHU Kun, HOSSAIN E, and ANPALAGAN A. Downlink power control in two-tier cellular OFDMA networks under uncertainties: A robust Stackelberg game[J]. IEEE Transactions on Communications, 2015, 63(2): 520-535. doi: 10.1109/TCOMM.2014.2382095. 吳敏, 何勇. 魯棒控制理論[M]. 北京: 高等教育出版社, 2010. ZHANG H, VENTURINO L, PRASAD N, et al. Weighted sum-rate maximization in multi-cell networks via coordinated scheduling and discrete power control[J]. IEEE Journal on Selected Areas in Communications, 2011, 29(6): 1214-1224. doi: 10.1109/JSAC.2011.110609. YANG K, WU Y, and HUANG J. Distributed robust optimization for communication networks[C]. IEEE Infocom Conference, Phoenix, AZ, USA, 2008: 1157-1165. doi: 10.1109/ INFOCOM.2008.171. FUDENBURG D and TIROLE J. Game Theory[M]. Cambridge, MA, USA, The MIT Press, 1991: 29-34. CHEN X, ZHANG H, CHEN T et al. Improving energy efficiency in femtocell networks: A hierarchical reinforcement learning framework[C]. IEEE International Conference on Communications (ICC), Budapest, Hungary, 2013: 2241- 2245. doi: 10. 1109/ICC.2013.6654861. WATKINS C and DAYAN P. Q-learning[J]. Journal of Machine Learning Research, 1992, 8(1): 279-292. -
計(jì)量
- 文章訪問(wèn)數(shù): 1430
- HTML全文瀏覽量: 180
- PDF下載量: 390
- 被引次數(shù): 0
下載:
