Cache-Assisted Task Offloading and Resource Optimization for LEO Network

We proposed a cache-assisted task offloading and resource allocation model and a deep reinforcement learning (DRL) based method for low-earth orbit (LEO) network. Our method takes obvious advantages in reducing delay and energy consumption.

I. Introduction

In low-earth orbit (LEO) satellite networks, the application of Mobile Edge Computing (MEC) demonstrates a significant impact on network performance and user experience [1]. Traditional cloud computing models often centralize computing and data processing tasks in data centers located far from end-user devices, resulting in high data transfer latency and limitations for applications with stringent real-time requirements. MEC, on the other hand, extends computing capabilities to the network edge, bringing data processing closer to end-users, effectively reducing latency, and enhancing real-time performance. In LEO satellite systems, the deployment of MEC enables satellites to flexibly execute data processing tasks, thereby improving the efficiency and performance of communication networks.