6G will move mobile networks towards increasing levels of complexity. To deal with this complexity, optimization of network parameters is key to ensure high performance and timely adaptivity to dynamic network environments. The optimization of the antenna tilt provides a practical and cost-efficient method to improve coverage and capacity in the network. Previous methods based on Reinforcement Learning (RL) have shown great promise for tilt optimization by learning adaptive policies outperforming traditional tilt optimization methods. However, most existing RL methods are based on single-cell features representation, which fails to fully characterize the agent state, resulting in suboptimal performance. Also, most of such methods lack scalability, due to state-action explosion, and generalization ability. In this paper, we propose a Graph Attention Q-learning (GAQ) algorithm for tilt optimization. GAQ relies on a graph attention mechanism to select relevant neighbors information, improve the agent state representation, and update the tilt control policy based on a history of observations using a Deep Q-Network (DQN). We show that GAQ efficiently captures important network information and outperforms standard DQN with local information by a large margin. In addition, we demonstrate its ability to generalize to network deployments of different sizes and densities.
翻译:处理这一复杂程度,优化网络参数是确保高性能和及时适应动态网络环境的关键。天线倾斜优化提供了提高网络覆盖面和容量的实用和成本效率方法。基于强化学习(RL)的以往方法显示极有可能通过学习适应性政策实现倾斜优化,优于传统的倾斜优化方法。然而,大多数现有RL方法都基于单细胞特征代表制,它未能充分描述代理人状态,导致不优化性能。此外,由于州行动爆炸和通用化能力,大多数这类方法缺乏可缩放性。在本文件中,我们建议采用图表关注Q-学习(GAQ)算法来优化倾斜度。GAQ依靠图形关注机制来选择相关邻居信息,改进代理州代表制,并根据使用深Q-网络的观察历史更新倾斜控制政策。我们显示,GAQ高效地收集了重要的网络信息,并大大超出标准DQN的本地信息。此外,我们展示了以大比例部署网络的能力。