Online Computation Offloading in NOMA-Based Multi-Access Edge Computing: A Deep Reinforcement Learning Approach

Nduwayezu, Maurice; Pham, Quoc-Viet; Hwang, Won-Joo

doi:10.1109/access.2020.2997925

Cited by 41 publications

(14 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3], the proposed algorithm is composed of two alternating phases: i) offloading action generation to quantize the relaxed offloading decision as a set of binary actions, and ii) offloading policy update to select the best offloading action among quantized ones. Similarly, the authors in [272] extended the framework proposed in [253] for multi-carrier NOMA based MEC systems.…”

Section: ) Joint Optimizationmentioning

confidence: 99%

A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art

et al. 2020

Self Cite

View full text Add to dashboard Cite

Driven by the emergence of new compute-intensive applications and the vision of the Internet of Things (IoT), it is foreseen that the emerging 5G network will face an unprecedented increase in traffic volume and computation demands. However, end users mostly have limited storage capacities and finite processing capabilities, thus how to run compute-intensive applications on resource-constrained users has recently become a natural concern. Mobile edge computing (MEC), a key technology in the emerging fifth generation (5G) network, can optimize mobile resources by hosting compute-intensive applications, process large data before sending to the cloud, provide the cloud-computing capabilities within the radio access network (RAN) in close proximity to mobile users, and offer context-aware services with the help of RAN information. Therefore, MEC enables a wide variety of applications, where the real-time response is strictly required, e.g., driverless vehicles, augmented reality, robotics, and immerse media. Indeed, the paradigm shift from 4G to 5G could become a reality with the advent of new technological concepts. The successful realization of MEC in the 5G network is still in its infancy and demands for constant efforts from both academic and industry communities. In this survey, we first provide a holistic overview of MEC technology and its potential use cases and applications. Then, we outline up-to-date researches on the integration of MEC with the new technologies that will be deployed in 5G and beyond. We also summarize testbeds and experimental evaluations, and open source activities, for edge computing. We further summarize lessons learned from state-of-the-art research works as well as discuss challenges and potential future directions for MEC research.

show abstract

Section: ) Joint Optimizationmentioning

confidence: 99%

A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Diao et al [24] examined the D2D-assisted and NOMA-based MEC network to reduce the total cost of users in terms of latency and energy consumed. Nduwayezu et al [25] proposed an algorithm using deep reinforcement learning to maximize the total computational rate for multi-carrier NOMA-MEC systems by jointly optimizing the computation offloading decision-making and sub-carrier allocation. Fang et al [26] minimized the overall task latency of mobile users for NOMA-MEC systems.…”

Section: Related Workmentioning

confidence: 99%

Joint Computational Offloading and Data-Content Caching in NOMA-MEC Networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

Multi-access edge computing (MEC) can improve the users' computational capacity and battery life by moving computing services to the network edge. In addition, data-content caching on a MEC server improves the user quality of experience and decreases the backhaul network congestion. Moreover, non-orthogonal multiple access (NOMA) has recently been implemented to increase network throughput and capacity. Combining these techniques can improve the user performance and benefit the network. This paper investigates a combined computational offloading and data-content caching problem for NOMA-MEC systems. The aim was to achieve the minimum total completion latency of all users by jointly optimizing the offloading decision, caching strategy, computational resource, and power allocation. This satisfies the constraints within the scope of the potential violation for energy consumption, offloading decision, and the computation and storage capacity of the MEC server. The formulated problem is a mixed-integer non-linear programming and a non-convex problem. To solve this challenging problem, a block successive upper-bound minimization method was implemented to obtain efficient solutions. Numerous simulation results were presented to demonstrate the convergence and efficacy of the proposed algorithm. Compared with other schemes of all-offloading, local-only, and equal resources, our proposed algorithm can approximately reduce the total completion latency by 17.68%, 26.02%, and 70.98%. INDEX TERMS Multi-access edge computing, non-orthogonal multiple access, block successive upper-bound minimization, computational offloading, data-content caching.

show abstract

“…RL has been considered the most effective way to maximize the long-term reward for dynamic systems among dynamic resource allocation methods [22]. In recent studies, the RL algorithms have been applied successfully as an alternative to model-based optimization, which is difficult to handle because of dynamics complexity involving slice requests and resource allocation [6], [7], [23]- [25]. In [2], we focused on the dynamic resource allocation of network slicing against upcoming resource demand by applying Qlearning.…”

Section: Related Workmentioning

confidence: 99%

Multi-Agent Reinforcement Learning-Based Resource Management for End-to-End Network Slicing

Kim

Lim

2021

IEEE Access

View full text Add to dashboard Cite

To meet the explosive growth of mobile traffic, the 5G network is designed to be flexible and support multi-access edge computing (MEC), thereby improving the end-to-end quality of service (QoS). In particular, 5G network slicing, which allows a physical infrastructure to split into multiple logical networks, keeps the balance of network resource allocation among different service types with on-demand resource requests. However, achieving effective resource allocation across the end-to-end network is difficult due to the dynamic characteristics of slicing requests such as uncertain real-time resource demand and heterogeneous requirements. In this paper, we develop a reinforcement learning (RL)-based dynamic resource allocation framework for end-to-end network slicing with heterogeneous requirements in multi-layer MEC environments. We first design a hierarchical MEC architecture and formulate a resource allocation problem for the end-to-end network slicing as an optimization problem using the Markov decision process (MDP). Using proximal policy optimization (PPO), we develop independently-collaborative and jointlycollaborative dynamic resource allocation algorithms to maximize resource efficiency while satisfying the QoS of slices. Experimental results show that the proposed algorithms can recognize the characteristics of slice requests and coming resource demands and efficiently allocate resources with a high QoS satisfaction rate.INDEX TERMS 5G, network slicing, multi-access edge computing, network resource management, multiagent reinforcement learning.

show abstract

Online Computation Offloading in NOMA-Based Multi-Access Edge Computing: A Deep Reinforcement Learning Approach

Cited by 41 publications

References 46 publications

A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art

A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art

Joint Computational Offloading and Data-Content Caching in NOMA-MEC Networks

Multi-Agent Reinforcement Learning-Based Resource Management for End-to-End Network Slicing

Contact Info

Product

Resources

About