Juan Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Juan Chen has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Huanlai Xing
Southwest Jiaotong University
2 shared publications - Zhiwen Xiao
Southwest Jiaotong University
2 shared publications - Bin Lu
Department of Computer, North China Electric Power University, Baoding 071003, China
1 shared publication - Lexi Xu
China United Network Communications Corporation
1 shared publication - Muhammad Azhar Iqbal
School of Computing and Artificial Intelligence
1 shared publication - Penglin Dai
Southwest Jiaotong University
1 shared publication
Latest Publications
- 9 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 25 (9) , 2968-2972
Dynamic Computation Offloading With Energy Harvesting Devices: A Graph-Based Deep Reinforcement Learning Approach
We study a joint partial offloading and resource allocations (JPORA) problem for the mobile edge computing (MEC) with energy harvesting (EH), where the number of MDs, computation task, and harvested energy of mobile device (MD) are highly dynamic. It is critical to acquire an algorithm that optimally adapts JPORA decisions. Recent studies employ deep deterministic policy gradient (DDPG) agent to tackle the JPORA problem. However, traditional DDPG cannot generalize well to different MEC network scale, due to the deep neural networks in DDPG can only extract latent representation from Euclidean data, with the characteristics of MEC network structural information ignored. To this end, by taking advantage of the graph-based relationship deduction ability form graph convolutional networks (GCN) and the self-evolution ability from the experience training of DDPG, we propose a centralized GCN-DDPG agent to learn making decisions for MDs, including offloading ratio, local computation capacity, and uplink transmission power. Experimental results show that the proposed GCN-DDPG provides significant performance improvement over a number of state-of-the-art DRL agents.
- 9 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Communications Letters
- Vol. 25 (9) , 2968-2972
Dynamic Computation Offloading With Energy Harvesting Devices: A Graph-Based Deep Reinforcement Learning Approach
We study a joint partial offloading and resource allocations (JPORA) problem for the mobile edge computing (MEC) with energy harvesting (EH), where the number of MDs, computation task, and harvested energy of mobile device (MD) are highly dynamic. It is critical to acquire an algorithm that optimally adapts JPORA decisions. Recent studies employ deep deterministic policy gradient (DDPG) agent to tackle the JPORA problem. However, traditional DDPG cannot generalize well to different MEC network scale, due to the deep neural networks in DDPG can only extract latent representation from Euclidean data, with the characteristics of MEC network structural information ignored. To this end, by taking advantage of the graph-based relationship deduction ability form graph convolutional networks (GCN) and the self-evolution ability from the experience training of DDPG, we propose a centralized GCN-DDPG agent to learn making decisions for MDs, including offloading ratio, local computation capacity, and uplink transmission power. Experimental results show that the proposed GCN-DDPG provides significant performance improvement over a number of state-of-the-art DRL agents.
- Top Cited Papers
- 19 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 8 (24) , 17508-17524
A DRL Agent for Jointly Optimizing Computation Offloading and Resource Allocation in MEC
This article studies the joint optimization problem of computation offloading and resource allocation (JCORA) in mobile-edge computing (MEC). Deep reinforcement learning (DRL) is one of the ideal techniques for addressing the dynamic JCORA problem. However, it is still challenging to adapt traditional DRL methods for the problem since they usually lead to slow and unstable convergence in model training. To this end, we propose a temporal attentional deterministic policy gradient (TADPG) to tackle JCORA. Based on the deep deterministic policy gradient (DDPG), TADPG has two significant features. First, a temporal feature extraction network consisting of a 1-D convolution (Conv1D) residual block and an attentional long short-term memory (LSTM) network is designed, which is beneficial to high-quality state representation and function approximation. Second, a rank-based prioritized experience replay (rPER) method is devised to accelerate and stabilize the convergence of model training. Experimental results demonstrate that the decentralized TADPG-based mechanism can achieve more efficient JCORA performance than the centralized one, and the proposed TADPG outperforms a number of state-of-the-art DRL agents in terms of the task completion time and energy consumption.
- 19 May 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 8 (24) , 17508-17524
Top Cited PapersA DRL Agent for Jointly Optimizing Computation Offloading and Resource Allocation in MEC
This article studies the joint optimization problem of computation offloading and resource allocation (JCORA) in mobile-edge computing (MEC). Deep reinforcement learning (DRL) is one of the ideal techniques for addressing the dynamic JCORA problem. However, it is still challenging to adapt traditional DRL methods for the problem since they usually lead to slow and unstable convergence in model training. To this end, we propose a temporal attentional deterministic policy gradient (TADPG) to tackle JCORA. Based on the deep deterministic policy gradient (DDPG), TADPG has two significant features. First, a temporal feature extraction network consisting of a 1-D convolution (Conv1D) residual block and an attentional long short-term memory (LSTM) network is designed, which is beneficial to high-quality state representation and function approximation. Second, a rank-based prioritized experience replay (rPER) method is devised to accelerate and stabilize the convergence of model training. Experimental results demonstrate that the decentralized TADPG-based mechanism can achieve more efficient JCORA performance than the centralized one, and the proposed TADPG outperforms a number of state-of-the-art DRL agents in terms of the task completion time and energy consumption.
- Open Access
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
STDPG: A Spatio-Temporal Deterministic Policy Gradient Agent for Dynamic Routing in SDN
Dynamic routing in software-defined networking (SDN) can be viewed as a centralized decision-making problem. Most of the existing deep reinforcement learning (DRL) agents can address it, thanks to the deep neural network (DNN) incorporated. However, fully-connected feed-forward neural network (FFNN) is usually adopted, where spatial correlation and temporal variation of traffic flows are ignored. This drawback usually leads to significantly high computational complexity due to large number of training parameters. To overcome this problem, we propose a novel model-free framework for dynamic routing in SDN, which is referred to as spatio-temporal deterministic policy gradient (STDPG) agent. Both the actor and critic networks are based on identical DNN structure, where a combination of convolutional neural network (CNN) and long short-term memory network (LSTM) with temporal attention mechanism, CNN-LSTM-TAM, is devised. By efficiently exploiting spatial and temporal features, CNN-LSTM-TAM helps the STDPG agent learn better from the experience transitions. Furthermore, we employ the prioritized experience replay (PER) method to accelerate the convergence of model training. The experimental results show that STDPG can automatically adapt for current network environment and achieve robust convergence. Compared with a number state-of the-art DRL agents, STDPG achieves better routing solutions in terms of the average end-to-end delay.
- 1 June 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Open AccessSTDPG: A Spatio-Temporal Deterministic Policy Gradient Agent for Dynamic Routing in SDN
Dynamic routing in software-defined networking (SDN) can be viewed as a centralized decision-making problem. Most of the existing deep reinforcement learning (DRL) agents can address it, thanks to the deep neural network (DNN) incorporated. However, fully-connected feed-forward neural network (FFNN) is usually adopted, where spatial correlation and temporal variation of traffic flows are ignored. This drawback usually leads to significantly high computational complexity due to large number of training parameters. To overcome this problem, we propose a novel model-free framework for dynamic routing in SDN, which is referred to as spatio-temporal deterministic policy gradient (STDPG) agent. Both the actor and critic networks are based on identical DNN structure, where a combination of convolutional neural network (CNN) and long short-term memory network (LSTM) with temporal attention mechanism, CNN-LSTM-TAM, is devised. By efficiently exploiting spatial and temporal features, CNN-LSTM-TAM helps the STDPG agent learn better from the experience transitions. Furthermore, we employ the prioritized experience replay (PER) method to accelerate the convergence of model training. The experimental results show that STDPG can automatically adapt for current network environment and achieve robust convergence. Compared with a number state-of the-art DRL agents, STDPG achieves better routing solutions in terms of the average end-to-end delay.
- 1 December 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 813-817
Load Balancing Oriented Economic Grid Resource Scheduling
As grid technologies evolve quickly on Internet, research related to resource scheduling faces new opportunities and challenges. These new technologies, ideas and approaches provide a new environment for researching and developing the economy-based resource scheduling system. Aiming at the hierarchical grid model, following load balancing thinking and cost-time optimization strategies, this paper proposes a new grid resource scheduling algorithm, which can not only increase the utilization of resources and system throughput, but also realize the load balancing and utility optimization between resource providers and users within grid systems. On the basis of having described the different functional parts of the proposed algorithm, two kinds of simulative experiments about completion time and cost of tasks are conducted. Finally, the experiment results show that the proposed algorithm is effective.
- 1 December 2008
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 813-817
Load Balancing Oriented Economic Grid Resource Scheduling
As grid technologies evolve quickly on Internet, research related to resource scheduling faces new opportunities and challenges. These new technologies, ideas and approaches provide a new environment for researching and developing the economy-based resource scheduling system. Aiming at the hierarchical grid model, following load balancing thinking and cost-time optimization strategies, this paper proposes a new grid resource scheduling algorithm, which can not only increase the utilization of resources and system throughput, but also realize the load balancing and utility optimization between resource providers and users within grid systems. On the basis of having described the different functional parts of the proposed algorithm, two kinds of simulative experiments about completion time and cost of tasks are conducted. Finally, the experiment results show that the proposed algorithm is effective.