Computation offloading and scheduling in Mobile Edge Networks and SDN DOI Creative Commons

Dinesh Kumar S,

parvathi R.M.S

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 4, 2024

Abstract The development of recent new applications, such as augmented reality, self-driving, and different cognitive has resulted in an increase the number computation-intensive data-intensive jobs that are sensitive to delays. It is anticipated mobile edge computing on ultra-dense networks would prove be efficient solution for satisfying need low latency resources. On other hand, scattered resource cloud energy dynamics battery devices make it difficult offload work users. To improve IoT support, (MEC) may provide nearby enhanced processing capability. At reachable access point (AP), tasks outsourced completed by Internet Things (IoT) devices. meet demanding requirements this paradigm brings computer resources closer load balancing seldom addressed previous MEC research concentrate offloading allocating end, there immediate MEC-aware task techniques take into account. Because SDN's rule-based forwarding policy assist determining most appropriate channel AP doing computation, software-defined networking (SDN) technology used article solve problem. So, order suggested SDN-assisted design responsive possible, we create a optimization issue achieve goal. proposed approach utilizes Deep Reinforcement Learning (DRL) estimate best polynomial time. effectiveness method been tested via simulation. According findings simulations, our lowest reaction compared others.

Language: Английский

Handover Decision with Multi-Access Edge Computing in 6G Networks: A Survey DOI Creative Commons
Saeid Jahandar, Ibraheem Shayea, Emre Güreş

et al.

Results in Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 103934 - 103934

Published: Jan. 1, 2025

Language: Английский

Citations

3
A Prediction Based Resource Reservation Algorithm for Service Handover in Edge Computing DOI
Peiyuan Guan, Yushuai Li, Amir Taherkordi

et al.

Published: July 1, 2023

Handover is a crucial issue in ensuring the continuity of edge services computing (EC) systems. Failure to handle hand-off properly may result delays, data loss, or service interruption during switching. Therefore, optimizing process ensure and satisfactory user experience significant challenge design In this paper, we propose resource reservation algorithm that reserves portion resources each base station meet quality (QoS) requirements We use an LSTM model predict number new existing users at future time point provide decision guidance for algorithm. Extensive simulation experiments demonstrate proposed outperforms benchmark algorithms variety environmental conditions.

Language: Английский

Citations

3
TiWA: Achieving Tetra Indicator Wi-Fi Associations in Software Defined Wi-Fi Networks DOI Creative Commons
Sohaib Manzoor, Muhammad Akbar Kayani, Nouman Ali

et al.

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 89520 - 89534

Published: Jan. 1, 2023

With the rise in smart devices, challenges such as traffic management particularly indoor scenarios have also increased. Wireless technologies seek to address these needs by using new radio access that offer faster connectivity and Internet. While 4G 5G provide outdoor, Wi-Fi still remains dominant technology due its low cost easy deployment. However, IEEE 802.11 standard does not fairness of load user-access point (AP) associations, resulting unequal user distributions subpar resource utilization. Densification has been employed past aforementioned issue, but it is costly requires more hardware. Load balancing necessary high-density networks order guarantee quality service (QoS). To avoid densification issues related at APs this paper introduces tetra indicator associations (TiWA), a combined SDN-based association channel assignment solution for networks. TiWA considers multi-criteria make better decisions. The wireless stations from an overloaded OpenFlow enabled AP (OAP) are handed underloaded OAP considering multi-metrics packet loss rate, received signal strength (RSSI), throughput occupancy. Extensive experimentations on EmPOWER platform show surpasses previous research methods based terms aggregated 39%, offering superior level supporting greater numbers users prior hitting which required.

Language: Английский

Citations

3
Optical wireless communication based mobile edge computing integrated channel allocation using scheduling with machine learning protocols in advanced 5G networks DOI

Rahul Vishnoi,

P. Pradeepa, Deepak Kumar

et al.

Optical and Quantum Electronics, Journal Year: 2023, Volume and Issue: 56(1)

Published: Dec. 13, 2023

Language: Английский

Citations

2
Computation offloading and scheduling in Mobile Edge Networks and SDN DOI Creative Commons

Dinesh Kumar S,

parvathi R.M.S

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 4, 2024

Abstract The development of recent new applications, such as augmented reality, self-driving, and different cognitive has resulted in an increase the number computation-intensive data-intensive jobs that are sensitive to delays. It is anticipated mobile edge computing on ultra-dense networks would prove be efficient solution for satisfying need low latency resources. On other hand, scattered resource cloud energy dynamics battery devices make it difficult offload work users. To improve IoT support, (MEC) may provide nearby enhanced processing capability. At reachable access point (AP), tasks outsourced completed by Internet Things (IoT) devices. meet demanding requirements this paradigm brings computer resources closer load balancing seldom addressed previous MEC research concentrate offloading allocating end, there immediate MEC-aware task techniques take into account. Because SDN's rule-based forwarding policy assist determining most appropriate channel AP doing computation, software-defined networking (SDN) technology used article solve problem. So, order suggested SDN-assisted design responsive possible, we create a optimization issue achieve goal. proposed approach utilizes Deep Reinforcement Learning (DRL) estimate best polynomial time. effectiveness method been tested via simulation. According findings simulations, our lowest reaction compared others.

Language: Английский

Citations

0