scholarly journals Task Migration Based on Reinforcement Learning in Vehicular Edge Computing

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Sungwon Moon ◽  
Jaesung Park ◽  
Yujin Lim
Keyword(s):  
Quality Of Service ◽  
Reinforcement Learning ◽  
Load Balancing ◽  
Learning Algorithm ◽  
High Mobility ◽  
Edge Computing ◽  
Task Completion ◽  
Task Migration ◽  
Delay Constraints

Multiaccess edge computing (MEC) has emerged as a promising technology for time-sensitive and computation-intensive tasks. With the high mobility of users, especially in a vehicular environment, computational task migration between vehicular edge computing servers (VECSs) has become one of the most critical challenges in guaranteeing quality of service (QoS) requirements. If the vehicle’s tasks unequally migrate to specific VECSs, the performance can degrade in terms of latency and quality of service. Therefore, in this study, we define a computational task migration problem for balancing the loads of VECSs and minimizing migration costs. To solve this problem, we adopt a reinforcement learning algorithm in a cooperative VECS group environment that can collaborate with VECSs in the group. The objective of this study is to optimize load balancing and migration cost while satisfying the delay constraints of the computation task of vehicles. Simulations are performed to evaluate the performance of the proposed algorithm. The results show that compared to other algorithms, the proposed algorithm achieves approximately 20–40% better load balancing and approximately 13–28% higher task completion rate within the delay constraints.

scholarly journals Video Pre-Caching Joint Hand-Off and Content Delivery in Multi-Access Edge Computing Based EONs

2021 ◽  
Author(s):  
Yutong Chai ◽  
Shan Yin ◽  
Lihao Liu ◽  
Liyou Jiang ◽  
Shanguo Huang
Keyword(s):  
Quality Of Service ◽  
High Mobility ◽  
Content Delivery ◽  
Edge Computing ◽  
The Other ◽  
Latency Time ◽  
Hand Off ◽  
Simulation Results ◽  
Multi Access

Multi-access Edge Computing (MEC) performs as a feasible solution when it comes to content delivery, for it can bring contents much closer to users. However, the hand-off (HO) and latency that occur in user movement reduce the users’ quality of service. In this work, we consider the problem of high mobility handoff and content delivery of video streaming in the MEC based EONs. We propose a video pre-caching algorithm considering handoff and content delivery. The algorithm firstly selects the content delivery method and chunks the video accordingly using a preset threshold. Secondly, the algorithm chooses the shortest transmission path and calculates the latency time using Dijkstra method. Simulation results show that our algorithm significantly reduces the latency time and balances the server load compared to the other two baselines.

scholarly journals Perbaikan Mekanisme Load Balancing untuk Komputasi Klaster pada Kondisi Dinamis

2017 ◽  
Vol 2 (2) ◽  
pp. 89
Author(s):  
Mohammad Zarkasi
Keyword(s):  
Quality Of Service ◽  
Reinforcement Learning ◽  
Load Balancing

Salah satu permasalahan yang sering terjadi pada lingkungan komputasi klaster adalah terjadinya beban yang tidak seimbang yang dapat menurunkan Quality of Service (QoS). Oleh sebab itu, dibutuhkan metode load balancing yang handal dalam pendistribusian beban. Pada beberapa kasus, metode load balancing dinamis gagal berperan sebagai metode load balancing yang optimal jika lingkungan implementasi tidak sesuai dengan lingkungan yang diasumsikan saat metode tersebut dikembangkan. Dalam penelitian ini diusulkan metode load balancing adaptif dengan menggunakan algoritma reinforcement learning (RL) yang mampu beradaptasi terhadap perubahan lingkungan. Hasil pengujian menunjukkan bahwa kinerja dari metode load balancing yang diusulkan lebih efisien dibandingkan dengan metode load balancing dinamis baik pada kondisi lingkungan tidak mengalami beban dengan peningkatan total waktu eksekusi sebesar 45% maupun pada saat lingkungan mengalami beban yang tidak seimbang dengan peningkatan waktu eksekusi sebesar 21%.

scholarly journals Dynamic Task Migration Combining Energy Efficiency and Load Balancing Optimization in Three-Tier UAV-Enabled Mobile Edge Computing System

Electronics ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 190
Author(s):  
Wu Ouyang ◽  
Zhigang Chen ◽  
Jia Wu ◽  
Genghua Yu ◽  
Heng Zhang
Keyword(s):  
Energy Consumption ◽  
Load Balancing ◽  
Markov Decision Process ◽  
Decision Process ◽  
Base Station ◽  
Edge Computing ◽  
Mobile Edge Computing ◽  
Task Migration ◽  
Migration Strategy ◽  
Markov Decision

As transportation becomes more convenient and efficient, users move faster and faster. When a user leaves the service range of the original edge server, the original edge server needs to migrate the tasks offloaded by the user to other edge servers. An effective task migration strategy needs to fully consider the location of users, the load status of edge servers, and energy consumption, which make designing an effective task migration strategy a challenge. In this paper, we innovatively proposed a mobile edge computing (MEC) system architecture consisting of multiple smart mobile devices (SMDs), multiple unmanned aerial vehicle (UAV), and a base station (BS). Moreover, we establish the model of the Markov decision process with unknown rewards (MDPUR) based on the traditional Markov decision process (MDP), which comprehensively considers the three aspects of the migration distance, the residual energy status of the UAVs, and the load status of the UAVs. Based on the MDPUR model, we propose a advantage-based value iteration (ABVI) algorithm to obtain the effective task migration strategy, which can help the UAV group to achieve load balancing and reduce the total energy consumption of the UAV group under the premise of ensuring user service quality. Finally, the results of simulation experiments show that the ABVI algorithm is effective. In particular, the ABVI algorithm has better performance than the traditional value iterative algorithm. And in a dynamic environment, the ABVI algorithm is also very robust.

scholarly journals A Load Balancing Per Connection Classifier Dengan Pengukuran Quality of Service Pada Jaringan LAN Lingkup Universitas

2020 ◽  
Vol 2 (2) ◽  
pp. 40-53
Author(s):  
Aulia Desy Aulia Nur Utomo
Keyword(s):  
Quality Of Service ◽  
Load Balancing ◽  
Packet Loss ◽  
Service Providers ◽  
Network Configuration ◽  
Network Connection ◽  
Before And After ◽  
Internet Connections ◽  
Use Of Internet

Abstract In the use of internet networks that are general in nature need to implement an appropriate network configuration to maximize the use of internet connections provided by service providers. This is important for the optimal use of internet services and in accordance with utilities that are basically general and shared can be achieved. Per Connection Classifier is a load balancing method for distributing traffic loads to more than one network connection point in a balanced way, so that traffic can run optimally. This research focuses on network configuration methods to maximize internet usage for all users. Quality of Service is used to see the performance of network traffic which is indicated by the value of the parameter delay, throughput, and packet loss. Based on the results of testing and research that have been carried out before and after using load balancing per connection clasifier, the delay value is decreased from 180.26 ms to 148.36 ms and throughput increased from 1.76% to 2.03%, then packet loss decreased from 25.37% to 18.59% according to the TIPHON standard. Keywords: Quality of Service, Per Connection Classification, load balancing, delay, throughput, packet loss

Energy-Efficient Virtualized Scheduling and Load Balancing Algorithm in Cloud Data Centers

2021 ◽  
Vol 11 (3) ◽  
pp. 34-48
Author(s):  
J. K. Jeevitha ◽  
Athisha G.
Keyword(s):  
Quality Of Service ◽  
Load Balancing ◽  
Energy Efficient ◽  
Data Centers ◽  
Scheduling Algorithm ◽  
Cloud Data ◽  
The Third ◽  
Cloud Data Centers ◽  
Load Balancing Algorithm

To scale back the energy consumption, this paper proposed three algorithms: The first one is identifying the load balancing factors and redistribute the load. The second one is finding out the most suitable server to assigning the task to the server, achieved by most efficient first fit algorithm (MEFFA), and the third algorithm is processing the task in the server in an efficient way by energy efficient virtual round robin (EEVRR) scheduling algorithm with FAT tree topology architecture. This EEVRR algorithm improves the quality of service via sending the task scheduling performance and cutting the delay in cloud data centers. It increases the energy efficiency by achieving the quality of service (QOS).

Sign in / Sign up

Export Citation Format

Share Document