A Joint Learning and Game-Theoretic Approach to Multi-Dimensional Resource Management in Fog Radio Access Networks
A Joint Learning and Game-Theoretic Approach to Multi-Dimensional Resource Management in Fog Radio Access Networks
复制标题
一种基于学习和博弈理论的雾天无线接入网多维资源管理方法
DOI：
10.1109/tvt.2022.3214075
复制
发表时间：
2023-02
影响因子：
6.8
通讯作者：
Yaohua Sun;Siqi Chen;Zeyu Wang;S. Mao
中科院分区：
文献类型：
--
作者：
Yaohua Sun;Siqi Chen;Zeyu Wang;S. Mao
雾无线接入网（F-RAN）已经被认为是通过利用雾接入点（F-AP）的计算和缓存能力来支持延迟敏感和计算密集型服务的有希望的范例。为了执行卸载的计算任务，必须在F-AP处预存储必要的程序和数据库，称为服务缓存。然而，由于系统动力学和耦合的决定，高速缓存，无线电和计算资源管理在F-RAN是一个具有挑战性的问题。本文提出了一个多维资源联合优化问题，目标是最小化期望延迟代价和缓存代价的加权和，该问题具有双时标结构.对于无线电和计算资源分配在一个小的时间尺度上，联盟博弈的方法提出了给定的缓存决策。在更大的时间尺度上，使用多代理强化学习算法在每个F-AP处缓存服务。所提出的算法的优点是，他们可以隐式地考虑到小时间尺度的资源分配的影响，同时适应长期的信道系数和用户服务请求的统计。我们分析了所提出的算法的收敛性，最优性和复杂性，并验证其性能与广泛的模拟，其中观察到的上级性能超过几个基线计划。
Fog radio access networks (F-RANs) have been regarded as a promising paradigm to support latency-sensitive and computation-intensive services by leveraging computing and caching capabilities of fog access points (F-APs). To execute offloaded computation tasks, it is essential to pre-store necessary programs and databases at F-APs, referred as service caching. However, due to system dynamics and the coupling of decisions, cache, radio, and computation resource management at F-RANs is a challenging problem. In this paper, a joint multi-dimensional resource optimization problem is formulated, aiming at minimizing the weighted sum of expected latency cost and caching cost, which is featured by a two-timescale structure. For radio and computation resource allocation on a small timescale, a coalitional game based approach is proposed under given caching decisions. On a larger timescale, services are cached at each F-AP using a multi-agent reinforcement learning algorithm. The advantage of the proposed algorithms is that they can implicitly take the impact of small timescale resource allocation into account while adapting to the long-term statistics of channel coefficients and user service requests. We analyze the proposed algorithms with respect to their convergence, optimality, and complexity, and validate their performance with extensive simulations, where superior performance is observed over several baseline schemes.