Learning in Wireless Control Systems Over Nonstationary Channels
Learning in Wireless Control Systems Over Nonstationary Channels
复制标题
DOI：
10.1109/tsp.2018.2890056
复制
发表时间：
2019-03-01
影响因子：
5.4
通讯作者：
Ribeiro, Alejandro
中科院分区：
文献类型：
--
作者：
Eisen, Mark;Gatsis, Konstantinos;Ribeiro, Alejandro
本文考虑了一组多个独立的控制系统，每个连接在一个非平稳的无线信道。目标是通过在固定预算内分配发射功率来最大化所有系统的控制性能。这可以用拉格朗日对偶来表示为一个约束优化问题。通过在每个时间点对未知无线信道进行采样，所产生的问题呈现出经验风险最小化的形式，这是机器学习中一个研究得很好的问题。由于无线信道的非平稳性，最佳分配必须不断学习和更新的信道演变。牛顿方法的二次收敛特性促使其用于随着信道随时间的推移而在采样的对偶函数上学习近似最优的功率分配策略。条件下，牛顿的方法学习近似解与一个单一的更新，并随后的次优控制问题的进一步特点。数值模拟说明了近最优性能的方法和所产生的无线控制问题的稳定性。
This paper considers a set of multiple independent control systems that are each connected over a nonstationary wireless channel. The goal is to maximize control performance over all the systems through the allocation of transmitting power within a fixed budget. This can be formulated as a constrained optimization problem examined using Lagrangian duality. By taking samples of the unknown wireless channel at every time instance, the resulting problem takes on the form of empirical risk minimization, a well-studied problem inmachine learning. Due to the nonstationarity of wireless channels, optimal allocations must be continuously learned and updated as the channel evolves. The quadratic convergence property of Newton's method motivates its use in learning approximately optimal power allocation policies over the sampled dual function as the channel evolves over time. Conditions are established under which Newton's method learns approximate solutions with a single update, and the subsequent suboptimality of the control problem is further characterized. Numerical simulations illustrate the near-optimal performance of the method and resulting stability on awireless control problem.