摘要：

移动边缘计算（MEC）将计算、存储、网络资源和服务向网络边缘下沉，并允许用户在边缘服务器上处理任务。然而，在实际应用中，用户请求的任务卸载量和无线信道状态随时间不断变化，同时计算和通信资源受限也对任务卸载和资源分配任务带来了挑战。针对该问题，构建一种资源约束下面向动态环境的系统效用优化模型。该模型中各个终端设备均配备能量收集装置，充分利用外界可再生能源来支持系统处理任务。运用Lyapunov优化理论消除优化模型对不确定信息的依赖，将原依赖未知信息的目标优化问题转化为只依赖当前时间片系统信息的优化问题，使用归约法证明该优化问题为一个NP-hard问题。结合深度强化学习方法设计一种资源约束下的自适应卸载算法LyUO，该算法在系统动态信息未知的情况下实时确定近优任务卸载决策及MEC服务器通信/计算资源分配策略。仿真结果表明，LyUO算法在任务到达率和无线信道状态变化时可使系统中所有设备的任务队列保持稳定，在满足队列长期约束的同时使系统效用较基准算法提升约15%。

关键词: 移动边缘计算, 自适应卸载算法, Lyapunov优化理论, 深度强化学习, 系统稳定, 资源分配

Abstract:

In Mobile Edge Computing (MEC), computing, storage, network resources, and services are relegated to the edge of the network, allowing users to process tasks on edge servers. However, in practical applications, the amount of task offloading requested by users and the state of wireless channels constantly change over time, which poses challenges to task offloading and resource allocation, as computing and communication resources are limited. To address this issue, a system utility optimization model is constructed to handle dynamic environments under resource constraints. In this model, each terminal device is equipped with energy harvesting devices, fully utilizing external renewable energy to support system processing tasks.The dependence of optimization models on uncertain information is eliminated using Lyapunov optimization theory, whereby the original optimization objective that relies on unknown information is transformed into an optimization problem that only relies on the current time slice system information. This optimization is an NP-hard problem, which is proved using the reduction method.Subsequently, Deep Reinforcement Learning(DRL) method is used to design an adaptive unloading algorithm, LyUO, under resource constraints. When the system dynamic information is unknown, this algorithm is responsible for the near optimal task unloading decision and the MEC server communication/computing resource allocation strategy in real time.The simulation results show that the LyUO algorithm can keep the task queue stable for all devices in the system even when the task arrival rate and wireless channel state change, improving the system utility by about 15% compared to the benchmark algorithm while meeting the long-term constraints of the queue.

Key words: Mobile Edge Computing(MEC), adaptive offloading algorithm, Lyapunov optimization theory, Deep Reinforcement Learning(DRL), system stability, resource allocation