scholarly journals Decentralized computation offloading for multi-user mobile edge computing: a deep reinforcement learning approach

2020 ◽  
Vol 2020 (1) ◽  
Author(s):  
Zhao Chen ◽  
Xiaodong Wang
Keyword(s):  
Reinforcement Learning ◽  
Mimo System ◽  
Edge Computing ◽  
Action Space ◽  
Computation Offloading ◽  
Learning Approaches ◽  
Mobile Edge Computing ◽  
Computation Cost ◽  
Continuous Power ◽  
And Task

Abstract Mobile edge computing (MEC) emerges recently as a promising solution to relieve resource-limited mobile devices from computation-intensive tasks, which enables devices to offload workloads to nearby MEC servers and improve the quality of computation experience. In this paper, an MEC enabled multi-user multi-input multi-output (MIMO) system with stochastic wireless channels and task arrivals is considered. In order to minimize long-term average computation cost in terms of power consumption and buffering delay at each user, a deep reinforcement learning (DRL)-based dynamic computation offloading strategy is investigated to build a scalable system with limited feedback. Specifically, a continuous action space-based DRL approach named deep deterministic policy gradient (DDPG) is adopted to learn decentralized computation offloading policies at all users respectively, where local execution and task offloading powers will be adaptively allocated according to each user’s local observation. Numerical results demonstrate that the proposed DDPG-based strategy can help each user learn an efficient dynamic offloading policy and also verify the superiority of its continuous power allocation capability to policies learned by conventional discrete action space-based reinforcement learning approaches like deep Q-network (DQN) as well as some other greedy strategies with reduced computation cost. Besides, power-delay tradeoff for computation offloading is also analyzed for both the DDPG-based and DQN-based strategies.

D3PG: Dirichlet DDGP for Task Partitioning and Offloading with Constrained Hybrid Action Space in Mobile Edge Computing

2021 ◽  
Author(s):  
Laha Ale ◽  
Scott King ◽  
Ning Zhang ◽  
Abdul Sattar ◽  
Janahan Skandaraniyam
Keyword(s):  
Reinforcement Learning ◽  
Dynamic Environment ◽  
Edge Computing ◽  
Action Space ◽  
Computation Offloading ◽  
Mobile Edge Computing ◽  
Continuous Variables ◽  
Task Partitioning ◽  
Policy Gradient ◽  
Service Latency

<div> Mobile Edge Computing (MEC) has been regarded as a promising paradigm to reduce service latency for data processing in Internet of Things, by provisioning computing resources at network edge. In this work, we jointly optimize the task partitioning and computational power allocation for computation offloading in a dynamic environment with multiple IoT devices and multiple edge servers. We formulate the problem as a Markov decision process with constrained hybrid action space, which cannot be well handled by existing deep reinforcement learning (DRL) algorithms. Therefore, we develop a novel Deep Reinforcement Learning called Dirichlet Deep Deterministic Policy Gradient (D3PG), which </div><div>is built on Deep Deterministic Policy Gradient (DDPG) to solve the problem. The developed model can learn to solve multi-objective optimization, including maximizing the number of tasks processed before expiration and minimizing the energy cost and service latency. More importantly, D3PG can effectively deal with constrained distribution-continuous hybrid action space, where the distribution variables are for the task partitioning and offloading, while the continuous variables are for computational frequency control. Moreover, the D3PG can address many similar issues in MEC and general reinforcement learning problems. Extensive simulation results show that the proposed D3PG outperforms the state-of-art methods.</div><div> Mobile Edge Computing (MEC) has been regarded as a promising paradigm to reduce service latency for data processing in Internet of Things, by provisioning computing resources at network edge. In this work, we jointly optimize the task partitioning and computational power allocation for computation offloading in a dynamic environment with multiple IoT devices and multiple edge servers. We formulate the problem as a Markov decision process with constrained hybrid action space, which cannot be well handled by existing deep reinforcement learning (DRL) algorithms. Therefore, we develop a novel Deep Reinforcement Learning called Dirichlet Deep Deterministic Policy Gradient (D3PG), which is built on Deep Deterministic Policy Gradient (DDPG) to solve the problem. The developed model can learn to solve multi-objective optimization, including maximizing the number of tasks processed before expiration and minimizing the energy cost and service latency. More importantly, D3PG can effectively deal with constrained distribution-continuous hybrid action space, where the distribution variables are for the task partitioning and offloading, while the continuous variables are for computational frequency control. Moreover, the D3PG can address many similar issues in MEC and general reinforcement learning problems. Extensive simulation results show that the proposed D3PG outperforms the state-of-art methods.</div>

scholarly journals D3PG: Dirichlet DDGP for Task Partitioning and Offloading with Constrained Hybrid Action Space in Mobile Edge Computing

2021 ◽  
Author(s):  
Laha Ale ◽  
Scott King ◽  
Ning Zhang ◽  
Abdul Sattar ◽  
Janahan Skandaraniyam
Keyword(s):  
Reinforcement Learning ◽  
Dynamic Environment ◽  
Edge Computing ◽  
Action Space ◽  
Computation Offloading ◽  
Mobile Edge Computing ◽  
Continuous Variables ◽  
Task Partitioning ◽  
Policy Gradient ◽  
Service Latency

<div> Mobile Edge Computing (MEC) has been regarded as a promising paradigm to reduce service latency for data processing in Internet of Things, by provisioning computing resources at network edge. In this work, we jointly optimize the task partitioning and computational power allocation for computation offloading in a dynamic environment with multiple IoT devices and multiple edge servers. We formulate the problem as a Markov decision process with constrained hybrid action space, which cannot be well handled by existing deep reinforcement learning (DRL) algorithms. Therefore, we develop a novel Deep Reinforcement Learning called Dirichlet Deep Deterministic Policy Gradient (D3PG), which </div><div>is built on Deep Deterministic Policy Gradient (DDPG) to solve the problem. The developed model can learn to solve multi-objective optimization, including maximizing the number of tasks processed before expiration and minimizing the energy cost and service latency. More importantly, D3PG can effectively deal with constrained distribution-continuous hybrid action space, where the distribution variables are for the task partitioning and offloading, while the continuous variables are for computational frequency control. Moreover, the D3PG can address many similar issues in MEC and general reinforcement learning problems. Extensive simulation results show that the proposed D3PG outperforms the state-of-art methods.</div><div> Mobile Edge Computing (MEC) has been regarded as a promising paradigm to reduce service latency for data processing in Internet of Things, by provisioning computing resources at network edge. In this work, we jointly optimize the task partitioning and computational power allocation for computation offloading in a dynamic environment with multiple IoT devices and multiple edge servers. We formulate the problem as a Markov decision process with constrained hybrid action space, which cannot be well handled by existing deep reinforcement learning (DRL) algorithms. Therefore, we develop a novel Deep Reinforcement Learning called Dirichlet Deep Deterministic Policy Gradient (D3PG), which is built on Deep Deterministic Policy Gradient (DDPG) to solve the problem. The developed model can learn to solve multi-objective optimization, including maximizing the number of tasks processed before expiration and minimizing the energy cost and service latency. More importantly, D3PG can effectively deal with constrained distribution-continuous hybrid action space, where the distribution variables are for the task partitioning and offloading, while the continuous variables are for computational frequency control. Moreover, the D3PG can address many similar issues in MEC and general reinforcement learning problems. Extensive simulation results show that the proposed D3PG outperforms the state-of-art methods.</div>

scholarly journals Dependency-Aware Computation Offloading in Mobile Edge Computing: A Reinforcement Learning Approach

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 134742-134753 ◽  
Author(s):  
Shengli Pan ◽  
Zhiyong Zhang ◽  
Zongwang Zhang ◽  
Deze Zeng
Keyword(s):  
Reinforcement Learning ◽  
Edge Computing ◽  
Computation Offloading ◽  
Learning Approach ◽  
Mobile Edge Computing
Sign in / Sign up

Export Citation Format

Share Document