An Online Optimization Framework for Distributed Fog Network Formation With Minimal Latency

Lee, Gilsoo; Saad, Walid; Bennis, Mehdi

doi:10.1109/twc.2019.2901850

Cited by 103 publications

(45 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The bandwidth for each fog node is 1MHz. The transmission power of the fog node is 20dBm, while the noise power density is -174dBm/Hz [8]. In regard to resource capacity distribution at fog nodes, the CPU speed of a fog node is randomly sampled from [5GHz, 6GHz, 7GHz, 8GHz, 9GHz, 10GHz], where the memory size of a fog node is randomly sampled from [2.4GB, 4GB, 8GB].…”

Section: A Simulation Settingsmentioning

confidence: 99%

“…In contrast to the cloud server, the computing capacity of fog nodes is usually limited and in-homogeneous. Thus, computation-intensive tasks often exhibit poor performance when they are processed by fog nodes with extremely limited resource capacities [8], [9]. In this context, offloading and distributing tasks over the network while guaranteeing the Quality-of-Service (QoS) requirements of the users, can be particularly useful.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Heterogeneous Task Offloading and Resource Allocations via Deep Recurrent Reinforcement Learning in Partial Observable Multifog Networks

Baek

Kaddoum²

2021

IEEE Internet Things J.

103

View full text Add to dashboard Cite

As wireless services and applications become more sophisticated and require faster and higher-capacity networks, there is a need for an efficient management of the execution of increasingly complex tasks based on the requirements of each application. In this regard, fog computing enables the integration of virtualized servers into networks and brings cloud services closer to end devices. In contrast to the cloud server, the computing capacity of fog nodes is limited and thus a single fog node might not be capable of computing-intensive tasks. In this context, task offloading can be particularly useful at the fog nodes by selecting the suitable nodes and proper resource management while guaranteeing the Quality-of-Service (QoS) requirements of the users. This paper studies the design of a joint task offloading and resource allocation control for heterogeneous service tasks in multi-fog nodes systems. This problem is formulated as a partially observable stochastic game, in which each fog node cooperates to maximize the aggregated local rewards while the nodes only have access to local observations. To deal with partial observability, we apply a deep recurrent Q-network (DRQN) approach to approximate the optimal value functions. The solution is then compared to a deep Q-network (DQN) and deep convolutional Q-network (DCQN) approach to evaluate the performance of different neural networks. Moreover, to guarantee the convergence and accuracy of the neural network, an adjusted explorationexploitation method is adopted. Provided numerical results show that the proposed algorithm can achieve a higher average success rate and lower average overflow than baseline methods.

show abstract

Section: A Simulation Settingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Heterogeneous Task Offloading and Resource Allocations via Deep Recurrent Reinforcement Learning in Partial Observable Multifog Networks

Baek

Kaddoum²

2021

IEEE Internet Things J.

103

View full text Add to dashboard Cite

show abstract

“…To remedy the limitations of MEC network, usercooperative computing have draw much attention recently [6]- [8]. In [6], a self-coordinated protocol for user-cooperative computing system was firstly proposed.…”

Section: Introductionmentioning

confidence: 99%

Energy Minimization for D2D-Assisted Mobile Edge Computing Networks

Kai

Wang

Zhu

2019

ICC 2019 - 2019 IEEE International Conference on Communications (ICC)

View full text Add to dashboard Cite

This paper addresses the energy minimization problem in Device-to-Device (D2D) assisted Mobile Edge Computing (MEC) networks under the latency constraint of each individual task and the computing resource constraint of each computing entity. The energy minimization problem is formed as a twostage optimization problem. Specifically, in the first stage, an initial feasibility problem is formed to maximize the number of executed tasks and the global energy minimization problem is tackled in the second stage while maintaining the maximum number of executed tasks. Both of the optimization problems in two stages are NP-hard, therefore a low-complexity algorithm is developed for the initial feasibility problem with a supplementary algorithm further proposed for energy minimization. Simulation results demonstrate the near-optimal performance of the proposed algorithms and the fact that with the assistance of D2D communication, the number of executed tasks is greatly increased and the energy consumption per executed task is significantly reduced in MEC networks, especially in dense user scenario.

show abstract

“…Game theory is also used in [13] to model the competition of IoT nodes over the fog network resources with the aim of minimizing both energy and delay. The fog network formation under the uncertainty of arriving and departing nodes is investigated in [5,14,15] with the aim of minimizing the maximum computing delay.…”

Section: Introductionmentioning

confidence: 99%

“…Each unmatched UN constructs its preference list as per(14). 4: Each cloudlet constructs its preference list as per(16) 5…”

mentioning

confidence: 99%

Proactive edge computing in fog networks with latency and reliability guarantees

Elbamby

Bennis

Saad

et al. 2018

J Wireless Com Network

Self Cite

View full text Add to dashboard Cite

This paper studies the problem of task distribution and proactive edge caching in fog networks with latency and reliability constraints. In the proposed approach, user nodes (UNs) offload their computing tasks to edge computing servers (cloudlets). Cloudlets leverage their computing and storage capabilities to proactively compute and store cacheable computing results. In this regard, a task popularity estimation and caching policy schemes are proposed. Furthermore, the problem of UNs' tasks distribution to cloudlets is modeled as a one-to-one matching game. In this game, UNs whose requests exceed a delay threshold use the notion of hedged-requests to enqueue their request in another cloudlet, and offload the task data to whichever is available first. A matching algorithm based on the deferred-acceptance matching is used to solve this game. Simulation results show that the proposed approach guarantees reliable service and minimal latency, reaching up to 50 and 65% reduction in the average delay and the 99th percentile delay, as compared to reactive baseline schemes.

show abstract

An Online Optimization Framework for Distributed Fog Network Formation With Minimal Latency

Cited by 103 publications

References 31 publications

Heterogeneous Task Offloading and Resource Allocations via Deep Recurrent Reinforcement Learning in Partial Observable Multifog Networks

Heterogeneous Task Offloading and Resource Allocations via Deep Recurrent Reinforcement Learning in Partial Observable Multifog Networks

Energy Minimization for D2D-Assisted Mobile Edge Computing Networks

Proactive edge computing in fog networks with latency and reliability guarantees

Contact Info

Product

Resources

About