针对无线接入网负载高波动的特点, 提出一种基于随机超时阈值的多路载频自适应开启的动态功耗控制策略, 在满足多类业务~QoS 的同时, 降低系统基站的能耗. 构建事件驱动的连续时间~Markov 控制过程系统分析模型, 将自适应载频开启节能控制转化为一个带约束的优化问题. 结合性能梯度估计与随机逼近, 提出一种基于策略梯度的在线自适应优化算法. 仿真实验结果验证了方法的有效性.

A stochastic timeout threshold based dynamic power management (DPM) strategy is presented for conserving energy of base stations in wireless multimedia access networks. It dynamically changes the operation state of multiple frequency carriers with the fluctuation of workloads to guarantee the QoS with minimum power consumption. First, an event-driven continuous-time Markov control processes model is introduced to formulate the DPM problem as a constrained optimization problem. Then, a reinforcement learning algorithm that combines policy gradient estimation and stochastic approximation is proposed for optimizing the DPM policy online. Simulation results demonstrate the effectiveness of the presented approach.