IEEE Transactions on Mobile Computing · 2020 · 531 citations · 28 references
ComputingComputer ScienceComputer SystemsDistributed SystemsEdge ComputingMobile ComputingEdge DevicesEdge Resource ManagementMobile Edge ComputingMulti-access Edge ComputingTask OffloadingDeep Reinforcement LearningEdge Computing OffloadingEdge NodesEdge OffloadingEdge Task OffloadingLoad DynamicsMobile Edge OffloadingWorkload Offloading
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.
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.
28
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Karl R. Weiss, Taghi M. Khoshgoftaar, Dingding Wang · Journal Of Big Data · 2016 · 6.2K citations · Full text
Deep Reinforcement Learning with Double Q-Learning
Hado van Hasselt, Arthur Guez, David Silver · 2016 · 6K citations · Full text
Fog computing and its role in the internet of things
Flavio Bonomi, Rodolfo Milito, Jiang Zhu et al. · 2012 · 6K citations · Full text