arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1103.3541cs.GTcs.LGcs.NI
收藏

多址信道中功率分配的分布式学习策略

Distributed Learning Policies for Power Allocation in Multiple Access Channels

Centre National de la Recherche Scientifique (CNRS)(法国国家科学研究中心);Laboratoire d’Informatique de Grenoble(格勒诺布尔计算机实验室);École Polytechnique(巴黎综合理工学院);ETIS/ENSEA – Université de Cergy-Pontoise – CNRS(ETIS/ENSEA–塞尔吉-蓬图瓦兹大学–法国国家科学研究中心);Supélec(高等电力学院);University of Athens(雅典大学);Laboratoire des Signaux et Systèmes, Supélec(信号与系统实验室,高等电力学院)

Panayotis Mertikopoulos, Elena V. Belmega, Aris L. Moustakas, Samson Lasaulce

摘要:

我们分析了正交多址接入信道的分布式功率分配问题,考虑一个连续的非合作博弈,其策略空间代表用户在网络信道上的传输功率分布。当渠道是静态的,我们发现,这个游戏承认一个确切的潜在功能,这使我们能够表明,它有一个唯一的平衡几乎肯定。此外,使用游戏的潜在属性,我们推导出一个修改后的版本的复制动态的进化博弈论,适用于这个连续的游戏,我们表明,如果网络的用户采用分布式学习计划的基础上,这些动态,然后他们收敛到均衡指数迅速。另一方面,如果信道不保持静态而是随时间随机波动,遵循平稳遍历过程,则会出现重大挑战。在这种情况下,相关的遍历博弈仍然存在唯一的均衡,但学习分析变得更加复杂,因为复制者的动态不再是确定性的。尽管如此,通过采用随机近似理论的结果,我们表明,用户仍然收敛到游戏的唯一均衡。我们的分析取决于一个博弈理论的结果,这是独立的利益:在有限的球员游戏,承认(可能是非线性的)凸势函数,复制动力学(适当修改,以考虑非线性收益)收敛到一个eps-邻居的平衡在O(log(1/eps))的时间。

英文摘要:

We analyze the problem of distributed power allocation for orthogonal multiple access channels by considering a continuous non-cooperative game whose strategy space represents the users' distribution of transmission power over the network's channels. When the channels are static, we find that this game admits an exact potential function and this allows us to show that it has a unique equilibrium almost surely. Furthermore, using the game's potential property, we derive a modified version of the replicator dynamics of evolutionary game theory which applies to this continuous game, and we show that if the network's users employ a distributed learning scheme based on these dynamics, then they converge to equilibrium exponentially quickly. On the other hand, a major challenge occurs if the channels do not remain static but fluctuate stochastically over time, following a stationary ergodic process. In that case, the associated ergodic game still admits a unique equilibrium, but the learning analysis becomes much more complicated because the replicator dynamics are no longer deterministic. Nonetheless, by employing results from the theory of stochastic approximation, we show that users still converge to the game's unique equilibrium. Our analysis hinges on a game-theoretical result which is of independent interest: in finite player games which admit a (possibly nonlinear) convex potential function, the replicator dynamics (suitably modified to account for nonlinear payoffs) converge to an eps-neighborhood of an equilibrium at time of order O(log(1/eps)).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑