A study of dynamic load balancing in grid environment

Desai, Hruta; Oza, Rachana

doi:10.1109/wispnet.2016.7566105

Cited by 10 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The objective is to balance the wireless networks by moving some users from the heavily congested BSs to uncongested ones, thus improving BSs utilization and providing enhanced QoS provisioning. Although the load balancing field has been heavily investigated in the literature using conventional resource management approaches, as in [207]- [209], there still a research gap in applying DRL for such a field. In this context, DRL can be adopted to realize the self-sustaining (or self-organization) vision of next generation wireless networks [3].…”

Section: D) Drl-based Load Balancing For Self-sustaining Networkmentioning

confidence: 99%

The Frontiers of Deep Reinforcement Learning for Resource Management in Future Wireless HetNets: Techniques, Challenges, and Research Directions

Alwarafy

Abdallah

Çiftler

et al. 2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Next generation wireless networks are expected to be extremely complex due to their massive heterogeneity in terms of the types of network architectures they incorporate, the types and numbers of smart IoT devices they serve, and the types of emerging applications they support. In such large-scale and heterogeneous networks (HetNets), radio resource allocation and management (RRAM) becomes one of the major challenges encountered during system design and deployment. In this context, emerging Deep Reinforcement Learning (DRL) techniques are expected to be one of the main enabling technologies to address the RRAM in future wireless HetNets. In this paper, we conduct a systematic in-depth, and comprehensive survey of the applications of DRL techniques in RRAM for next generation wireless networks. Towards this, we first overview the existing traditional RRAM methods and identify their limitations that motivate the use of DRL techniques in RRAM. Then, we provide a comprehensive review of the most widely used DRL algorithms to address RRAM problems, including the value-and policy-based algorithms. The advantages, limitations, and use-cases for each algorithm are provided. We then conduct a comprehensive and in-depth literature review and classify existing related works based on both the radio resources they are addressing and the type of wireless networks they are investigating. To this end, we carefully identify the types of DRL algorithms utilized in each related work, the elements of these algorithms, and the main findings of each related work. Finally, we highlight important open challenges and provide insights into several future research directions in the context of DRL-based RRAM. This survey is intentionally designed to guide and stimulate more research endeavors towards building efficient and fine-grained DRL-based RRAM schemes for future wireless networks.

show abstract

Section: D) Drl-based Load Balancing For Self-sustaining Networkmentioning

confidence: 99%

The Frontiers of Deep Reinforcement Learning for Resource Management in Future Wireless HetNets: Techniques, Challenges, and Research Directions

Alwarafy

Abdallah

Çiftler

et al. 2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…As a result, it cannot be applied to conditions where the end-users can directly access back-end servers. Similarly, a dynamic load-balancing scheme that utilizes dynamic DNS updates and a round-robin mechanism was proposed [ 19 ]. The scheme can add or remove a server from the DNS list according to load variations.…”

Section: Related Workmentioning

confidence: 99%

Integrated Resource Management for Fog Networks

Yang

2022

Sensors

View full text Add to dashboard Cite

In this paper, we consider integrated resource management for fog networks inclusive of intelligent energy perception, service level agreement (SLA) planning and replication-based hotspot offload (RHO). In the beginning, we propose an intelligent energy perception scheme which dynamically classifies the fog nodes into a hot set, a warm set or a cold set, based on their load conditions. The fog nodes in the hot set are responsible for a quality of service (QoS) guarantee and the fog nodes in the cold set are maintained at a low-energy state to save energy consumption. Moreover, the fog nodes in the warm set are used to balance the QoS guarantee and energy consumption. Secondly, we propose an SLA mapping scheme which effectively identifies the SLA elements with the same semantics. Finally, we propose a replication-based load-balancing scheme, namely RHO. The RHO can leverage the skewed access pattern caused by the hotspot services. In addition, it greatly reduces communication overheads because the load conditions are updated only when the load variations exceed a specific threshold. Finally, we use computer simulations to compare the performance of the RHO with other schemes under a variety of load conditions. In a word, we propose a comprehensive and feasible solution that contributes to the integrated resource management of fog networks.

show abstract

“…The objective is to balance the wireless networks by moving some users from the heavily congested BSs to uncongested ones, thus improving BSs utilization and providing enhanced QoS provisioning. Although the load balancing field has been heavily investigated in the literature using conventional resource management approaches, as in [192]- [194], there still a research gap in applying DRL for such a field. In this context, DRL can be adopted to realize the self-sustaining (or self-organization) vision of next generation wireless networks [3].…”

Section: D) Drl-based Load Balancing For Self-sustaining Networkmentioning

confidence: 99%

Deep Reinforcement Learning for Radio Resource Allocation and Management in Next Generation Heterogeneous Wireless Networks: A Survey

Alwarafy¹,

Abdallah²,

Çiftler³

et al. 2021

Preprint

View full text Add to dashboard Cite

<div>Next generation wireless networks are expected to be extremely complex due to their massive heterogeneity in terms of the types of network architectures they incorporate, the types and numbers of smart IoT devices they serve, and the types of emerging applications they support. In such large-scale and heterogeneous networks (HetNets), radio resource allocation and management (RRAM) becomes one of the major challenges encountered during system design and deployment. In this context, emerging Deep Reinforcement Learning (DRL) techniques are expected to be one of the main enabling technologies to address the RRAM in future wireless HetNets. In this paper, we conduct a systematic in-depth, and comprehensive survey of the applications of DRL techniques in RRAM for next generation wireless networks. Towards this, we first overview the existing traditional RRAM methods and identify their limitations that motivate the use of DRL techniques in RRAM. Then, we provide a comprehensive review of the most widely used DRL algorithms to address RRAM problems, including the value- and policy-based algorithms. The advantages, limitations, and use-cases for each algorithm are provided. We then conduct a comprehensive and in-depth literature review and classify existing related works based on both the radio resources they are addressing and the type of wireless networks they are investigating. To this end, we carefully identify the types of DRL algorithms utilized in each related work, the elements of these algorithms, and the main findings of each related work. Finally, we highlight important open challenges and provide insights into several future research directions in the context of DRL-based RRAM. This survey is intentionally designed to guide and stimulate more research endeavors towards building efficient and fine-grained DRL-based RRAM schemes for future wireless networks.</div>

show abstract

A study of dynamic load balancing in grid environment

Cited by 10 publications

References 6 publications

The Frontiers of Deep Reinforcement Learning for Resource Management in Future Wireless HetNets: Techniques, Challenges, and Research Directions

The Frontiers of Deep Reinforcement Learning for Resource Management in Future Wireless HetNets: Techniques, Challenges, and Research Directions

Integrated Resource Management for Fog Networks

Deep Reinforcement Learning for Radio Resource Allocation and Management in Next Generation Heterogeneous Wireless Networks: A Survey

Contact Info

Product

Resources

About