Task Offloading Based on LSTM Prediction and Deep Reinforcement Learning for Efficient Edge Computing in IoT

Tu, Youpeng; Chen, Haiming; Yan, Linjie; Zhou, Xinyan

doi:10.3390/fi14020030

Cited by 35 publications

(11 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 26 , 27 , 28 ] the authors discussed and provided the task offloading schemes with limitations, similarly the other authors proposed secure task offloading scheme for drone technologies to gather and control the drone technology in efficient manner. However they emphasis that IoT task offloading and scheduling is still NP-Hard problem which need further analysis and require more optimize solution.…”

Section: Related Workmentioning

confidence: 99%

Multi-Objective Task-Aware Offloading and Scheduling Framework for Internet of Things Logistics

Umer,

Ali,

Jehangiri

et al. 2024

Sensors

View full text Add to dashboard Cite

IoT-based smart transportation monitors vehicles, cargo, and driver statuses for safe movement. Due to the limited computational capabilities of the sensors, the IoT devices require powerful remote servers to execute their tasks, and this phenomenon is called task offloading. Researchers have developed efficient task offloading and scheduling mechanisms for IoT devices to reduce energy consumption and response time. However, most research has not considered fault-tolerance-based job allocation for IoT logistics trucks, task and data-aware scheduling, priority-based task offloading, or multiple-parameter-based fog node selection. To overcome the limitations, we proposed a Multi-Objective Task-Aware Offloading and Scheduling Framework for IoT Logistics (MT-OSF). The proposed model prioritizes the tasks into delay-sensitive and computation-intensive tasks using a priority-based offloader and forwards the two lists to the Task-Aware Scheduler (TAS) for further processing on fog and cloud nodes. The Task-Aware Scheduler (TAS) uses a multi-criterion decision-making process, i.e., the analytical hierarchy process (AHP), to calculate the fog nodes’ priority for task allocation and scheduling. The AHP decides the fog nodes’ priority based on node energy, bandwidth, RAM, and MIPS power. Similarly, the TAS also calculates the shortest distance between the IoT-enabled vehicle and the fog node to which the IoT tasks are assigned for execution. A task-aware scheduler schedules delay-sensitive tasks on nearby fog nodes while allocating computation-intensive tasks to cloud data centers using the FCFS algorithm. Fault-tolerant manager is used to check task failure; if any task fails, the proposed system re-executes the tasks, and if any fog node fails, the proposed system allocates the tasks to another fog node to reduce the task failure ratio. The proposed model is simulated in iFogSim2 and demonstrates a 7% reduction in response time, 16% reduction in energy consumption, and 22% reduction in task failure ratio in comparison to Ant Colony Optimization and Round Robin.

show abstract

Section: Related Workmentioning

confidence: 99%

Multi-Objective Task-Aware Offloading and Scheduling Framework for Internet of Things Logistics

Umer,

Ali,

Jehangiri

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…In addition, the combination of future information prediction and DRL has also been extensively studied [32]. Specifically, the authors investigated state prediction for agents' pre-training and allocating resources in advance [33], [34]. Besides, authors in [35] and [36] studied reward prediction and proposed using prediction to control agents' future actions.…”

Section: B Slice Migration and Resource Allocationmentioning

confidence: 99%

Federated Deep Reinforcement Learning for Prediction-Based Network Slice Mobility in 6 G Mobile Networks

Ming,

Yu,

Taleb

2024

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

Network slices are generally coupled with services and face service continuity/unavailability concerns due to the high mobility and dynamic requests from users. Network slice mobility (NSM), which considers user mobility, service migration, and resource allocation from a holistic view, is witnessed as a key technology in enabling network slices to respond quickly to service degradation. Existing studies on NSM either ignored the trigger detection before NSM decision-making or didn't consider the prediction of future system information to improve the NSM performance, and the training of deep reinforcement learning (DRL) agents also faces challenges with incomplete observations. To cope with these challenges, we consider that network slices migrate periodically and utilize the prediction of system information to assist NSM decision-making. The periodical NSM problem is further transformed into a Markov decision process, and we creatively propose a prediction-based federated DRL framework to solve it. Particularly, the learning processes of the prediction model and DRL agents are performed in a federated learning paradigm. Based on extensive experiments, simulation results demonstrate that the proposed scheme outperforms the considered baseline schemes in improving long-term profit, reducing communication overhead, and saving transmission time.

show abstract

“…Several centralized offloading algorithms are proposed in [17][18][19] to solve the above problems while considering the total system state. An online predictive offloading algorithm based on DRL and Long Short-Term Memory (LSTM) networks is proposed in [17], it predicts the load of the ES in real time during the model's training phase and allocates the computational resources for the task in advance to substantially increase the convergence speed and accuracy of the DRL algorithm during the offloading process.…”

Section: Related Workmentioning

confidence: 99%

DRL-Based Distributed Task Offloading Framework in Edge-Cloud Environment

Nashaat,

Hashem,

Rizk

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The Internet of Things (IoT), real-time media streaming, and other related technologies have increased due to the rapid development of wireless communication technologies and the enormous growth of computation, storage, and data transmission tasks. Edge-Cloud Computing (ECC) is a technology that can be used to better meet the diverse needs of IoT users, it combines the benefits of Mobile Cloud Computing (MCC) and Mobile Edge Computing (MEC) to meet energy consumption and delay requirements, and achieve more stable and affordable task execution. The most significant challenge in ECC is making realtime task offloading decisions. In order to generate offloading decisions in ECC environments in an efficient and near optimal manner, a Deep Reinforcement Learning (DRL)-based Distributed task Offloading (DRL-DO) framework is proposed. Simulation results demonstrate the accuracy of the DRL-DO framework, it achieves high Gain Ratio (GR) and greatly reduces the energy consumption, response time, while attaining moderate time cost compared with other offloading algorithms.

show abstract

Task Offloading Based on LSTM Prediction and Deep Reinforcement Learning for Efficient Edge Computing in IoT

Cited by 35 publications

References 42 publications

Multi-Objective Task-Aware Offloading and Scheduling Framework for Internet of Things Logistics

Multi-Objective Task-Aware Offloading and Scheduling Framework for Internet of Things Logistics

Federated Deep Reinforcement Learning for Prediction-Based Network Slice Mobility in 6 G Mobile Networks

DRL-Based Distributed Task Offloading Framework in Edge-Cloud Environment

Contact Info

Product

Resources

About