Zhiming Dai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhiming Dai has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Chunhua Gu
School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China
2 shared publications - Qi Min
School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
2 shared publications - Weichao Ding
School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200237, China
2 shared publications - Baohua Yao
Shanghai Institute of Civil Defense Science, Shanghai 200020, China
1 shared publication - He Yang
Sinopec Research Institute of Petroleum Processing Co., Ltd., Beijing 100083, China
1 shared publication - Qingchao Jiang
Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 26 April 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (9) , 5412
A Meta Reinforcement Learning-Based Task Offloading Strategy for IoT Devices in an Edge Cloud Computing Environment
Developing an effective task offloading strategy has been a focus of research to improve the task processing speed of IoT devices in recent years. Some of the reinforcement learning-based policies can improve the dependence of heuristic algorithms on models through continuous interactive exploration of the edge environment; however, when the environment changes, such reinforcement learning algorithms cannot adapt to the environment and need to spend time on retraining. This paper proposes an adaptive task offloading strategy based on meta reinforcement learning with task latency and device energy consumption as optimization targets to overcome this challenge. An edge system model with a wireless charging module is developed to improve the ability of IoT devices to provide service constantly. A Seq2Seq-based neural network is built as a task strategy network to solve the problem of difficult network training due to different dimensions of task sequences. A first-order approximation method is proposed to accelerate the calculation of the Seq2Seq network meta-strategy training, which involves quadratic gradients. The experimental results show that, compared with existing methods, the algorithm in this paper has better performance in different tasks and network environments, can effectively reduce the task processing delay and device energy consumption, and can quickly adapt to new environments.
- 26 April 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (9) , 5412
Open AccessA Meta Reinforcement Learning-Based Task Offloading Strategy for IoT Devices in an Edge Cloud Computing Environment
Developing an effective task offloading strategy has been a focus of research to improve the task processing speed of IoT devices in recent years. Some of the reinforcement learning-based policies can improve the dependence of heuristic algorithms on models through continuous interactive exploration of the edge environment; however, when the environment changes, such reinforcement learning algorithms cannot adapt to the environment and need to spend time on retraining. This paper proposes an adaptive task offloading strategy based on meta reinforcement learning with task latency and device energy consumption as optimization targets to overcome this challenge. An edge system model with a wireless charging module is developed to improve the ability of IoT devices to provide service constantly. A Seq2Seq-based neural network is built as a task strategy network to solve the problem of difficult network training due to different dimensions of task sequences. A first-order approximation method is proposed to accelerate the calculation of the Seq2Seq network meta-strategy training, which involves quadratic gradients. The experimental results show that, compared with existing methods, the algorithm in this paper has better performance in different tasks and network environments, can effectively reduce the task processing delay and device energy consumption, and can quickly adapt to new environments.
- Open Access
M-E-AWA: A Novel Task Scheduling Approach Based on Weight Vector Adaptive Updating for Fog Computing
Task offloading and real-time scheduling are hot topics in fog computing. This paper aims to address the challenges of complex modeling and solving multi-objective task scheduling in fog computing environments caused by widely distributed resources and strong load uncertainties. Firstly, a task unloading model based on dynamic priority adjustment is proposed. Secondly, a multi-objective optimization model is constructed for task scheduling based on the task unloading model, which optimizes time delay and energy consumption. The experimental results show that M-E-AWA (MOEA/D with adaptive weight adjustment based on external archives) can effectively handle multi-objective optimization problems with complex Pareto fronts and reduce the response time and energy consumption costs of task scheduling.
Open AccessM-E-AWA: A Novel Task Scheduling Approach Based on Weight Vector Adaptive Updating for Fog Computing
Task offloading and real-time scheduling are hot topics in fog computing. This paper aims to address the challenges of complex modeling and solving multi-objective task scheduling in fog computing environments caused by widely distributed resources and strong load uncertainties. Firstly, a task unloading model based on dynamic priority adjustment is proposed. Secondly, a multi-objective optimization model is constructed for task scheduling based on the task unloading model, which optimizes time delay and energy consumption. The experimental results show that M-E-AWA (MOEA/D with adaptive weight adjustment based on external archives) can effectively handle multi-objective optimization problems with complex Pareto fronts and reduce the response time and energy consumption costs of task scheduling.