A New Cloudlet Placement Method Based on Affinity Propagation for Cyber-Physical-Social Systems in Wireless Metropolitan Area Networks

Peng, Kai; Qian, Xingda; Zhao, Bohai; Zhang, Kejia; Liu, Yang

doi:10.1109/access.2020.2974895

Cited by 12 publications

(8 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To define the optimal number of cloudlets to have a trade-off between the QoS and the cost for the service provider, Peng et al [26] used an improved affinity propagation algorithm. In their clustering, they considered user movement and load balancing.…”

Section: Background and Related Workmentioning

confidence: 99%

“…They compared their proposed approach with the two other greedy methods, where the nearest edge server or the edge server with the most available computing power is selected. To find the optimal placement and resource allocation in MEC, various approaches are investigated, including mainly: clustering [26], top-K [2], MIP [8], combination of MIP and K-means [27], heuristics [29], [28], ILP and game theory [30].…”

Section: Background and Related Workmentioning

confidence: 99%

“…Edge server placement in 5G and 6G networks can be shown by an undirected graph G = (V, E), where V = BS ES and E is the representation of the connections between base stations and edge servers. Usually, for simplicity purposes, it is assumed the edge servers are co-located with the existing base stations [8], [26].…”

Section: Edge Server Placement Modelling a System Model And Problem D...mentioning

confidence: 99%

See 2 more Smart Citations

Reinforcement Learning Framework for Server Placement and Workload Allocation in Multi-Access Edge Computing

Mazloomi¹,

Sami²,

Otrok³

et al. 2022

Preprint

View full text Add to dashboard Cite

Cloud computing is a reliable solution to provide distributed computation power. However, real-time response is still challenging regarding the enormous amount of data generated by the IoT devices in 5G and 6G networks. Thus, multi-access edge computing (MEC), which consists of distributing the edge servers in the proximity of end-users to have low latency besides the higher processing power, is increasingly becoming a vital factor for the success of modern applications. This paper addresses the problem of minimizing both, the network delay, which is the main objective of MEC, and the number of edge servers to provide a MEC design with minimum cost. This MEC design consists of edge servers placement and base stations allocation, which makes it a joint combinatorial optimization problem (COP). Recently, reinforcement learning (RL) has shown promising results for COPs. However, modeling real-world problems using RL when the state and action spaces are large still needs investigation. We propose a novel RL framework with an efficient representation and modeling of the state space, action space and the penalty function in the design of the underlying Markov Decision Process (MDP) for solving our problem. This modeling makesthe Temporal Difference learning (TD) applicable for a large-scale real-world problem while minimizing the cost of network design. We introduce the TD(λ) with eligibility traces for Minimizing the Cost (TDMC) algorithm, in addition to Q-Learning for the same problem (QMC) when λ = 0. Furthermore, we discuss the impact of state representation, action space, and penalty function on the convergence of each model. Extensive experiments using a realworld dataset from Shanghai Telecommunication demonstrate that in the light of an efficient model, TDMC/QMC are able to find the actions that are the source of lower delayed penalty. The reported results show that our algorithm outperforms the other benchmarks by creating a trade-off among multiple objectives.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Section: Background and Related Workmentioning

confidence: 99%

Section: Edge Server Placement Modelling a System Model And Problem D...mentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning Framework for Server Placement and Workload Allocation in Multi-Access Edge Computing

Mazloomi¹,

Sami²,

Otrok³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To be concrete, UAVs continuously change their locations which lead to the energy-inefficiency and increased transmission delay, hence the interference management under fixed locations is urgently needed. In addition, the nature of mitigating interference and strengthening transmission quality in CoMP [ 28 , 29 , 30 ] has not been fully applied in UAV systems. The regularity of cluster forming in UAV networks has not been thoroughly studied, including average cluster number and average cluster size (the number of UAVs in a cluster).…”

Section: Introductionmentioning

confidence: 99%

Power Control and Clustering-Based Interference Management for UAV-Assisted Networks

Zhang

Chuai

Gao

2020

Sensors

View full text Add to dashboard Cite

Unmanned Aerial Vehicle (UAV) has been widely used in various applications of wireless network. A system of UAVs has the function of collecting data, offloading traffic for ground Base Stations (BSs) and illuminating coverage holes. However, inter-UAV interference is easily introduced because of the huge number of LoS paths in the air-to-ground channel. In this paper, we propose an interference management framework for UAV-assisted networks, consisting of two main modules: power control and UAV clustering. The power control is executed first to adjust the power levels of UAVs. We model the problem of power control for UAV networks as a non-cooperative game which is proved to be an exact potential game and the Nash equilibrium is reached. Next, to further improve system user rate, coordinated multi-point (CoMP) technique is implemented. The cooperative UAV sets are established to serve users and thus transforming the interfering links into useful links. Affinity propagation is applied to build clusters of UAVs based on the interference strength. Simulation results show that the proposed algorithm integrating power control with CoMP can effectively reduce the interference and improve system sum-rate, compared to Non-CoMP scenario. The law of cluster formation is also obtained where the average cluster size and the number of clusters are affected by inter-UAV distance.

show abstract

“…First, the population density of urban areas in WMANs is relatively high, and the computing performance of edge servers can be used more effectively. Second, because of the large scale of WMANs, MEC service providers can exploit economies of scale to improve the acceptability of MEC services to the public [17, 18].…”

Section: Introductionmentioning

confidence: 99%

Load balancing edge server placement method with QoS requirements in wireless metropolitan area networks

Zeng

Fang

et al. 2020

IET Communications

View full text Add to dashboard Cite

Mobile edge computing (MEC) is concerned with moving complex tasks from data sources to nearby computing resources, which can reduce computing latency and remote cloud workload. Although there has been significant research in the field of MEC, research on edge server placement in wireless metropolitan area networks (WMANs) is overlooked, and the load balancing problem of edge servers is seldom discussed. From a practical perspective, how to place edge servers efficiently in WMANs while considering load balancing between edge servers is studied. A greedy algorithm is proposed that can balance the workload of edge servers more effectively. However, the performance of the greedy algorithm as the number of servers placed increases is not ideal. Therefore, the authors combine the greedy algorithm with a genetic algorithm (GA) to minimise the number of edge servers while ensuring load balancing between edge servers and quality of service (QoS) requirements for mobile users. Finally, they conduct simulation experiments and compare the proposed algorithms with other algorithms. The improved GA proposed is superior to the greedy algorithm in terms of load balancing and the number of servers. The experimental results demonstrate that the algorithm has excellent performance.

show abstract

A New Cloudlet Placement Method Based on Affinity Propagation for Cyber-Physical-Social Systems in Wireless Metropolitan Area Networks

Cited by 12 publications

References 51 publications

Reinforcement Learning Framework for Server Placement and Workload Allocation in Multi-Access Edge Computing

Reinforcement Learning Framework for Server Placement and Workload Allocation in Multi-Access Edge Computing

Power Control and Clustering-Based Interference Management for UAV-Assisted Networks

Load balancing edge server placement method with QoS requirements in wireless metropolitan area networks

Contact Info

Product

Resources

About