Dynamic Task Software Caching-assisted Computation Offloading for Multi-Access Edge Computing

TL;DR

This paper proposes a dynamic task software caching and computation offloading framework for MEC, using deep reinforcement learning to adapt to time-varying user demands, reducing energy consumption and improving efficiency.

Contribution

It introduces a joint optimization model for caching and offloading, and develops a novel DDQN-based method with state coding and action aggregation to efficiently solve the problem.

Findings

Achieves over 12% energy savings compared to existing schemes.

Converges faster with fewer training episodes.

Effective handling of large state-action spaces in MEC caching and offloading.

Abstract

In multi-access edge computing (MEC), most existing task software caching works focus on statically caching data at the network edge, which may hardly preserve high reusability due to the time-varying user requests in practice. To this end, this work considers dynamic task software caching at the MEC server to assist users' task execution. Specifically, we formulate a joint task software caching update (TSCU) and computation offloading (COMO) problem to minimize users' energy consumption while guaranteeing delay constraints, where the limited cache size and computation capability of the MEC server, as well as the time-varying task demand of users are investigated. This problem is proved to be non-deterministic polynomial-time hard, so we transform it into two sub-problems according to their temporal correlations, i.e., the real-time COMO problem and the Markov decision process-based TSCU problem. We first model the COMO problem as a multi-user game and propose a decentralized algorithm to address its Nash equilibrium solution. We then propose a double deep Q-network (DDQN)-based method to solve the TSCU policy. To reduce the computation complexity and convergence time, we provide a new design for the deep neural network (DNN) in DDQN, named state coding and action aggregation (SCAA). In SCAA-DNN, we introduce a dropout mechanism in the input layer to code users' activity states. Additionally, at the output layer, we devise a two-layer architecture to dynamically aggregate caching actions, which is able to solve the huge state-action space problem. Simulation results show that the proposed solution outperforms existing schemes, saving over 12% energy, and converges with fewer training episodes.