Robust Computation Offloading in Fog Radio Access Network With Fronthaul Compression

Tan, Jinghong; Chang, Tsung-Hui; Guo, Kun; Quek, Tony Q. S.

doi:10.1109/twc.2021.3074810

Cited by 8 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [22], the authors considered a robust offloading strategy against realistic channel estimation errors in fog-IoT systems and minimized the power consumption of UEs with the latency requirements. In computation robustness design, the authors in [23] investigated the fog radio access network in which the knowledge of computation provision with bounded perturbations is inaccurate and developed a computation offloading mechanism with the goal of minimizing the UEs' energy consumption. In [24], the authors focused on the demand uncertainty with a single cache-enabled UAV and minimized the delay brought by the UAV-assisted caching by jointly optimizing the trajectory and caching of the UAV.…”

Section: Related Workmentioning

confidence: 99%

Robust Computation Offloading and Trajectory Optimization for Multi-UAV-Assisted MEC: A Multiagent DRL Approach

Li,

Yang,

Liu

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

For multiple Unmanned-Aerial-Vehicles (UAVs) assisted Mobile Edge Computing (MEC) networks, we study the problem of combined computation and communication for user equipments deployed with multi-type tasks. Specifically, we consider that the MEC network encompasses both communication and computation uncertainties, where the partial channel state information and the inaccurate estimation of task complexity are only available. We introduce a robust design accounting for these uncertainties and minimize the total weighted energy consumption by jointly optimizing UAV trajectory, task partition, as well as the computation and communication resource allocation in the multi-UAV scenario. The formulated problem is challenging to solve with the coupled optimization variables and the high uncertainties. To overcome this issue, we reformulate a multi-agent Markov decision process and propose a multi-agent proximal policy optimization with Beta distribution framework to achieve a flexible learning policy. Numerical results demonstrate the effectiveness and robustness of the proposed algorithm for the multi-UAV-assisted MEC network, which outperforms the representative benchmarks of the deep reinforcement learning and heuristic algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Robust Computation Offloading and Trajectory Optimization for Multi-UAV-Assisted MEC: A Multiagent DRL Approach

Li,

Yang,

Liu

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

show abstract

“…Many previous works used traditional optimization methods to investigate computation offloading and resource allocation strategies in F-RANs [11][12][13][14][15][16]. For instance, the authors in [11] have proposed a coordinated offloading scheme in the centralized F-RAN based on an alternating convex optimization method, where the UE's task can be split into the cloud computing part and the fog computing part to be executed as minimizing the sum of energy consumption with satisfying the delay tolerance of each task.…”

Section: Related Workmentioning

confidence: 99%

“…The authors in [15] have proposed a genetic convex optimization algorithm for user association, computing offloading, and resource allocation in the F-RAN to maximize the user rate and minimize the delay of all computing tasks. The authors in [16] have proposed a low-complexity algorithm based on the penalty method and the differenceof-convex functions programming to find a local optimal solution of joint computation offloading and resource allocation problem. However, the traditional optimization methods used in previous works generally require the complete and accurate system information, which is difficult to collect in real networks due to highly dynamic wireless networks.…”

Section: Related Workmentioning

confidence: 99%

“…The authors in [15] have proposed a genetic convex optimization algorithm for user association, computing offloading, and resource allocation in the F‐RAN to maximize the user rate and minimize the delay of all computing tasks. The authors in [16] have proposed a low‐complexity algorithm based on the penalty method and the difference‐of‐convex functions programming to find a local optimal solution of joint computation offloading and resource allocation problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep reinforcement learning‐based joint optimization of computation offloading and resource allocation in F‐RAN

Jo¹,

Kim²,

Kim³

et al. 2022

IET Communications

View full text Add to dashboard Cite

The fog radio access network (F-RAN) has been regarded as a promising wireless access network architecture in the fifth generation (5G) and beyond systems to satisfy the increasing requirements for low-latency and high-throughput services by providing fog computing. However, because the cloud computing centre and fog computing-enabled access points (F-APs) in the F-RAN have different computation and communication capabilities, it is crucial to make an efficient computation offloading and resource allocation strategy that can fully exploit the potential of the F-RAN system. In this paper, the authors investigate a decentralized low-complexity deep reinforcement learning (DRL)based framework for joint computation task offloading and resource allocation in the F-RAN, which supports assistive computing-enabled tasks offloading between F-APs. Considering the constraints of task latency, wireless transmission rate, transmission power, and computational resource capacity, the authors formulate the system processing efficiency maximization problem by jointly optimizing offloading mode selection, channel allocation, power control, and computation resource allocation in the F-RAN. To solve this non-linear and non-convex problem, the authors propose a federated DRL-based computation offloading and resource allocation algorithm to improve the task processing efficiency and ensure privacy in the system, which can significantly reduce the computing complexity and signalling overhead of the training process compared with the centralized learning-based method. Specifically, each local F-AP agent consists of dueling deep Q-network (DDQN) and deep deterministic policy gradient (DDPG) networks to appropriately deal with discrete and continuous valuable action spaces, respectively. Finally, the simulation results show that the proposed federated DRL algorithm can achieve significant performance improvements in terms of system processing efficiency and task latency compared with other benchmarks.

show abstract

“…Limited by hardware technology, battery life, and other factors, mobile devices have limited computational resources and often need the help of remote servers to complete computing tasks efficiently. The research on related problems has also attracted the attention of academia and industry [7,12,13]. During the execution of the computing task, it is encapsulated in the virtual machine and offloaded to the remote server for performance [14].…”

Section: Related Workmentioning

confidence: 99%

A Time-Driven Cloudlet Placement Strategy for Workflow Applications in Wireless Metropolitan Area Networks

Zhang

Zheng

et al. 2022

Sensors

View full text Add to dashboard Cite

With the rapid development of mobile technology, mobile applications have increasing requirements for computational resources, and mobile devices can no longer meet these requirements. Mobile edge computing (MEC) has emerged in this context and has brought innovation into the working mode of traditional cloud computing. By provisioning edge server placement, the computing power of the cloud center is distributed to the edge of the network. The abundant computational resources of edge servers compensate for the lack of mobile devices and shorten the communication delay between servers and users. Constituting a specific form of edge servers, cloudlets have been widely studied within academia and industry in recent years. However, existing studies have mainly focused on computation offloading for general computing tasks under fixed cloudlet placement positions. They ignored the impact on computation offloading results from cloudlet placement positions and data dependencies among mobile application components. In this paper, we study the cloudlet placement problem based on workflow applications (WAs) in wireless metropolitan area networks (WMANs). We devise a cloudlet placement strategy based on a particle swarm optimization algorithm using genetic algorithm operators with the encoding library updating mode (PGEL), which enables the cloudlet to be placed in appropriate positions. The simulation results show that the proposed strategy can obtain a near-optimal cloudlet placement scheme. Compared with other classic algorithms, this algorithm can reduce the execution time of WAs by 15.04–44.99%.

show abstract

Robust Computation Offloading in Fog Radio Access Network With Fronthaul Compression

Cited by 8 publications

References 32 publications

Robust Computation Offloading and Trajectory Optimization for Multi-UAV-Assisted MEC: A Multiagent DRL Approach

Robust Computation Offloading and Trajectory Optimization for Multi-UAV-Assisted MEC: A Multiagent DRL Approach

Deep reinforcement learning‐based joint optimization of computation offloading and resource allocation in F‐RAN

A Time-Driven Cloudlet Placement Strategy for Workflow Applications in Wireless Metropolitan Area Networks

Contact Info

Product

Resources

About