A Self-Supervised Learning Approach for Accelerating Wireless Network Optimization
A Self-Supervised Learning Approach for Accelerating Wireless Network Optimization
复制标题
DOI：
10.1109/tvt.2023.3244043
复制
发表时间：
2023-06
影响因子：
6.8
通讯作者：
Shuai Zhang;O. Ajayi;Yu-long Cheng
中科院分区：
文献类型：
--
作者：
Shuai Zhang;O. Ajayi;Yu-long Cheng
多跳线无线网络中的主要问题是干涉管理，这反对传统路由和调度算法的效率。我们开发了一种自我监督的学习方法，以解决多跳无线网络上经典的NP容量优化问题，在该网络中，路由和调度决策得到了深入的耦合。我们的两个阶段设计利用历史计算经验来加速新问题实例的优化，其中一个实例代表包含网络拓扑，干扰模型和其他用户级流量约束的应用程序级输入。第一个阶段是调度结构分类（SSC），将历史优化实例的调度结构提炼成适当数量的类，通过无需事先假设或知识的正确设计的聚类算法。第二阶段使用从第一阶段标记的类信息标记的实例来培训应用程序识别（AID）神经网络模型，能够预测其应用程序级信息的未来问题实例的调度类。在求解新实例时，将利用其预测的调度类和相关的调度结构来计算有效的近似解决方案，从而避免使用常规方法实践的时间耗时的迭代搜索。我们将方法应用于各种网络大小和不同流量要求的不同类型的无线多商品流问题。结果表明，我们的方法可将计算时间稳健地减少至少70％，而解决方案质量仅略有损失。
The prevailing issue in multi-hop wireless networking is interference management, which militates against the efficiency of traditional routing and scheduling algorithms. We develop a self-supervised learning approach to address the classic NP-hard problem of capacity optimization over a multi-hop wireless network, where the routing and scheduling decisions are deeply coupled. Our two-stage design leverages historical computation experiences to accelerate the optimization of new problem instances, where an instance represents the application-level input containing network topology, interference model, and other user-level traffic constraints. The first stage, Scheduling Structure Classification (SSC), distills the scheduling structure of the historical optimization instances into an appropriate number of classes, through a properly designed clustering algorithm without prior assumption or knowledge. The second stage uses the instances labelled with class information from the first stage to train an Application Identification (AID) neural network model capable of predicting a future problem instance's scheduling class given its application-level information. When solving the new instance, its predicted scheduling class and the associated scheduling structure are exploited to compute an efficient approximate solution, avoiding the time-consuming iterative search for such scheduling structure as practiced by the conventional approaches. We apply our method to different types of wireless multi-commodity flow problems across various network sizes and disparate flow requirements. The results demonstrate that our method significantly reduces the computation time robustly by at least 70% with only slight loss in the solution quality.