Adaptive and Priority-Based Resource Allocation for Efficient Resources Utilization in Mobile-Edge Computing

Sharif, Zubair; Jung, Low Tang; Razzak, Muhammad Imran; Alazab, Mamoun

doi:10.1109/jiot.2021.3111838

Cited by 42 publications

(9 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many studies discussing how to improve this point. Sharif et al proposed a scheme that adaptively allocates available resources by prioritizing incoming requests [ 13 ]. In [ 14 ], Chen et al established a two-stage bargaining-based incentive scheme for task offloading and cooperative computing.…”

Section: Related Workmentioning

confidence: 99%

Two-Layer Edge Intelligence for Task Offloading and Computing Capacity Allocation with UAV Assistance in Vehicular Networks

Bi,

Zhao

2024

Sensors

View full text Add to dashboard Cite

With the exponential growth of wireless devices and the demand for real-time processing, traditional server architectures face challenges in meeting the ever-increasing computational requirements. This paper proposes a collaborative edge computing framework to offload and process tasks efficiently in such environments. By equipping a moving unmanned aerial vehicle (UAV) as the mobile edge computing (MEC) server, the proposed architecture aims to release the burden on roadside units (RSUs) servers. Specifically, we propose a two-layer edge intelligence scheme to allocate network computing resources. The first layer intelligently offloads and allocates tasks generated by wireless devices in the vehicular system, and the second layer utilizes the partially observable stochastic game (POSG), solved by duelling deep Q-learning, to allocate the computing resources of each processing node (PN) to different tasks. Meanwhile, we propose a weighted position optimization algorithm for the UAV movement in the system to facilitate task offloading and task processing. Simulation results demonstrate the improved performance by applying the proposed scheme.

show abstract

Section: Related Workmentioning

confidence: 99%

Two-Layer Edge Intelligence for Task Offloading and Computing Capacity Allocation with UAV Assistance in Vehicular Networks

Bi,

Zhao

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Next, consider scenario μ ̃= 1 𝐹 𝑖+1 ⁄ . According to equation (6), it is evident that for values μ ̃andμ * , when condition m = 1, ⋯ iholds true, 𝑥 𝑚 = 0occurs; similarly, when condition m = i + 1, ⋯ M is satisfied, 𝑥 𝑖 = 1 follows. Hence, the total CPU cycles for the summation of data ∑ 𝑚 𝑚 𝑥 𝑚 𝑐 𝑚 𝑀 𝑚=1…”

Section: Appendix Amentioning

confidence: 99%

“…It aids in capturing strategic interactions, incentives, and conflicts that arise in such systems. Autonomous group robots, being typical distributed systems, are characterized by moments of games between service providers and users, as well as between different users.In competitive markets, the quantity of resources produced by service providers depends on factors such as demand, costs, market conditions, and the objectives of the providers themselves [6] . Furthermore, the pricing of computational resources by service providers is also crucial in achieving their ultimate goals.…”

mentioning

confidence: 99%

Research on Price-Based Autonomous Group Robot Resource Allocation Strategy in Emergency Scenarios

Yi,

Xiao

2023

Preprint

View full text Add to dashboard Cite

In unknown and dynamic emergency scenarios, achieving the collaboration of autonomous group robots for search and rescue operations can be regarded as resource allocation among robots at the micro-level. The resource allocation problem for autonomous group robots can be abstracted as a non-cooperative game, and in a dynamically changing environment, pricing becomes a critical factor for effective resource allocation.This paper starts from the perspectives of uniform pricing strategy and differential pricing strategy, respectively. It establishes master-slave game models for these two pricing strategies to describe resource allocation between resource providers and resource consumers. Furthermore, the paper utilizes game theory to model the competition for computational resources between resource-providing robots and resource-consuming robots, and solves for their Nash equilibrium solution, demonstrating its existence and uniqueness.Additionally, performance analysis and numerical analysis are conducted on both the uniform pricing model and the differential pricing model, thereby highlighting the advantages and disadvantages of different pricing models for dynamic adjustment of pricing strategies. Meanwhile, the differential pricing model introduces a fairness factor to enhance collaboration between robots and prevent resource accumulation. Simulation results indicate that under the same CPU cycle, the average processing time is shorter in the uniform pricing model, while in the differential pricing model, the resource-providing robots yield higher profits. Hence, the suitable pricing strategy can be chosen based on specific requirements.Simultaneously, as the CPU cycle increases, the cost for resource-consuming robots decreases, average processing time reduces, and the payment enthusiasm of resource-consuming robots increases. Therefore, the CPU cycle is related to the overall well-being of the autonomous group robot system.

show abstract

“…For the network cost problem of the large-scale heterogeneous system, Cao et al [ 14 ] improved the network coverage using an adaptive seagull algorithm. In addition, various joint allocation methods have been proposed to maximize the rate, energy efficiency, and spectral efficiency [ 15 , 16 , 17 ]. The above-mentioned research works are based on traditional methods, such as the genetic algorithm [ 18 ], game theory [ 19 ], water-filling method [ 20 ], graph theory [ 21 ], and so on.…”

Section: Introductionmentioning

confidence: 99%

“…As shown in Figure 2, the structure is a binary tree with a root node at the top, and there are only two child nodes for each node of the upper level. For the leaf nodes at the bottom, the tuple S t , A p t , R t , S t+1 , V ϕ t of transition ϕ is stored with its probability according to Equation (16). Note that the value of each node is the sum of its child nodes' value.…”

mentioning

confidence: 99%

Joint Optimization of Bandwidth and Power Allocation in Uplink Systems with Deep Reinforcement Learning

Zhang,

Lv,

Huang

et al. 2023

Sensors

View full text Add to dashboard Cite

Wireless resource utilizations are the focus of future communication, which are used constantly to alleviate the communication quality problem caused by the explosive interference with increasing users, especially the inter-cell interference in the multi-cell multi-user systems. To tackle this interference and improve the resource utilization rate, we proposed a joint-priority-based reinforcement learning (JPRL) approach to jointly optimize the bandwidth and transmit power allocation. This method aims to maximize the average throughput of the system while suppressing the co-channel interference and guaranteeing the quality of service (QoS) constraint. Specifically, we de-coupled the joint problem into two sub-problems, i.e., the bandwidth assignment and power allocation sub-problems. The multi-agent double deep Q network (MADDQN) was developed to solve the bandwidth allocation sub-problem for each user and the prioritized multi-agent deep deterministic policy gradient (P-MADDPG) algorithm by deploying a prioritized replay buffer that is designed to handle the transmit power allocation sub-problem. Numerical results show that the proposed JPRL method could accelerate model training and outperform the alternative methods in terms of throughput. For example, the average throughput was approximately 10.4–15.5% better than the homogeneous-learning-based benchmarks, and about 17.3% higher than the genetic algorithm.

show abstract

Adaptive and Priority-Based Resource Allocation for Efficient Resources Utilization in Mobile-Edge Computing

Cited by 42 publications

References 38 publications

Two-Layer Edge Intelligence for Task Offloading and Computing Capacity Allocation with UAV Assistance in Vehicular Networks

Two-Layer Edge Intelligence for Task Offloading and Computing Capacity Allocation with UAV Assistance in Vehicular Networks

Research on Price-Based Autonomous Group Robot Resource Allocation Strategy in Emergency Scenarios

Joint Optimization of Bandwidth and Power Allocation in Uplink Systems with Deep Reinforcement Learning

Contact Info

Product

Resources

About