Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing Systems

Ming Tang, Vincent W. S. Wong

IEEE Transactions on Mobile Computing · 2020 · 531 citations · 28 references

Concepts

TL;DR

Mobile edge computing systems can become overloaded when many devices offload tasks, causing large delays or task drops due to uncertain load dynamics. The study formulates a task‑offloading problem that minimizes expected long‑term cost for non‑divisible, delay‑sensitive tasks. A model‑free deep reinforcement learning algorithm is proposed, employing LSTM, dueling DQN, and double‑DQN to estimate long‑term cost in a distributed setting. Simulations demonstrate that the algorithm better exploits edge node capacities, significantly reducing dropped‑task ratios and average delay compared with existing methods.

Abstract

In mobile edge computing systems, an edge node may have a high load when a large number of mobile devices offload their tasks to it. Those offloaded tasks may experience large processing delay or even be dropped when their deadlines expire. Due to the uncertain load dynamics at the edge nodes, it is challenging for each device to determine its offloading decision (i.e., whether to offload or not, and which edge node it should offload its task to) in a decentralized manner. In this work, we consider non-divisible and delay-sensitive tasks as well as edge load dynamics, and formulate a task offloading problem to minimize the expected long-term cost. We propose a model-free deep reinforcement learning-based distributed algorithm, where each device can determine its offloading decision without knowing the task models and offloading decision of other devices. To improve the estimation of the long-term cost in the algorithm, we incorporate the long short-term memory (LSTM), dueling deep Q-network (DQN), and double-DQN techniques. Simulation results show that our proposed algorithm can better exploit the processing capacities of the edge nodes and significantly reduce the ratio of dropped tasks and average delay when compared with several existing algorithms.

References

28