A load balancing and optimization strategy (LBOS) using reinforcement learning in fog computing environment

Talaat, Fatma M.; Saraya, Mohamed S.; Saleh, Ahmed I.; Ali, Hesham A.; Ali, Shereen H.

doi:10.1007/s12652-020-01768-8

Cited by 110 publications

(45 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the year 2020, Talaat et al [105] proposed resource allocation-based load balancing approach which depends upon reinforcement learning. This approach keeps track of network traffic by measuring server loads that help it to handle incoming requests.…”

Section: Year-wise Review Of Load Balancing Techniquesmentioning

confidence: 99%

“…In case of more IoT devices used for e-health systems, by implementing load balancing in the fog layer, all requests generated by IoT sensors can be equally assigned to all resources for fast processing. Due to its less latency feature, fog can help to build efficient e-healthcare systems that can help to store and process patient's data in fractional seconds [105]. • FoAgro: Fog computing has a wide scope in agriculture also.…”

Section: Applications Of Fog Computing With Load Balancingmentioning

confidence: 99%

See 1 more Smart Citation

A systematic study of load balancing approaches in the fog computing environment

Kaur

Aron

2021

J Supercomput

View full text Add to dashboard Cite

Internet of Things has been growing, due to which the number of user requests on fog computing layer has also increased. Fog works in a real-time environment and offers from connected devices need to be processed immediately. With the increase in users requests on fog layer, virtual machines (VMs) at fog layer become overloaded. Load balancing mechanism can distribute load among all the VMs in equal proportion. It has become a necessity in the fog layer to equally, and equitably distribute all the workload among the existing VMs in the segment. Till now, many load balancing techniques have been proposed for fog computing. An empirical study of existing methods in load balancing have been conducted, and taxonomy has been presented in a hierarchical form. Besides, the article contains the year-wise comprehensive review and summary of research articles published in the area of load balancing from 2013 to 2020. Furthermore, article also contains our proposed fog computing architecture to resolve load balancing problem. It also covers current issues and challenges that can be resolved in future research works. The paper concludes by providing future directions.

show abstract

Section: Year-wise Review Of Load Balancing Techniquesmentioning

confidence: 99%

Section: Applications Of Fog Computing With Load Balancingmentioning

confidence: 99%

A systematic study of load balancing approaches in the fog computing environment

Kaur

Aron

2021

J Supercomput

View full text Add to dashboard Cite

show abstract

“…In [23], a workload balancing and cloud resource optimization approach was proposed. The proposed method deploys the dynamic cloud resource allotment approach based on reinforcement learning and genetic algorithm to ceaselessly monitor network traffic, gather information about the load on every server, manage incoming requests, and equally distribute the request to available servers using dynamic resource allocation strategy.…”

Section: Literature Reviewmentioning

confidence: 99%

A Multi Agent Based Dynamic Resource Allocation in Fog-Cloud Computing Environment

et al. 2021

View full text Add to dashboard Cite

Cloud high latency limitation has necessitated the introduction of Fog computing paradigm that extends computing infrastructures in the cloud data centers to the edge network. Extended cloud resources provide processing, storage and network services to time sensitive request associated to the Internet of Things (IoT) services in network edge. The rapid increase in adoption of IoT devices, variations in user requirements, limited processing and storage capacity of fog resources and problem of fog resources over saturation has made provisioning and allotment of computing resources in fog environment a formidable task. Satisfying application and request deadline is the most substantial challenge compared to other dynamic variations in parameters of client requirements. To curtail these issues, the integrated fog-cloud computing environment and efficient resource selection method is highly required. This paper proposed an agent based dynamic resource allocation that employs the use of host agent to analyze the QoSrequirements of application and request and select a suitable execution layer. The host agent forwards the application request to a layer agent which is responsible for the allocation of best resource that satisfies the requirement of the application request. Host agent and layers agents maintains resource information tables for matching of task and computing resources. CloudSim toolkit functionalities were extended to simulate a realistic fog environment where the proposed method is evaluated. The experimental results proved that the proposed method performs better in terms of processing time, latency and percentage QoS delivery. HIGHLIGHTS The distance between the cloud infrastructure and the edge IoT devices makes the cloud not too competent for some IoT applications, especially the sensitive ones To minimize the latency in the cloud and ensure prompt response to user requests, Fog computing, which extends the cloud services to edge network was introduced The proliferation in adoption of IoT devices and fog resource limitations has made resource scheduling in fog computing a tedious one GRAPHICAL ABSTRACT

show abstract

“…So, awell-organized load balancing tactic is needed in fog computing, which automatically expands the QoS aspects [8][9]. This is the dissemination of tasks procedure amidnumerous fog nodes along thesustenance of well-organized load balancing tactic [10][11].…”

Section: Introductionmentioning

confidence: 99%

“… The evaluation metrices, viz Response Time, Load Balancing Rate, Scheduling Time, Delay, Energy Consumption with count of tasks are analyzed.  Then the simulation performance of IDRAM-LB-FC-Hyb-HySTFOA is analyzed and it was compared with the existing methods, like DRAM-LB-FC-GA [21] and EDRAM-LB-FC-PSOA [22]. The remaining manuscript is structured as: Section 2 presents the Literature survey.…”

Section: Introductionmentioning

confidence: 99%

Load balancing using a Hybrid Hydrozoan and Sea Turtle Foraging Optimization Algorithm in FOG Computing

Renuka¹

2021

Proceedings of the First International Conference on Combinatorial and Optimization, ICCAP 2021, December 7-8 2021, Chennai, In

View full text Add to dashboard Cite

Internet of Things (IoT) is network of huge and intricate devices, wherein fog computing systems is significantwith the intention of handling the data flow of such huge and intricate network. Customarily, in fog computing environments, load balancing delinquent ariseswhen a large count of new IoT user requests are linked with specific fog nodes. So, a well-organized load balancing tactic is needed in fog computing. Therefore, in this manuscript, a Hybrid Hydrozoan and Sea Turtle Foraging optimization Algorithmsbased improved energy efficient Resource AllocationMethod to load balance in fog computing (IDRAM-LB-FC-Hyb-HySTFOA)is effectively proposed for reducing task waiting time, Load Balancing Rate, Scheduling Time, Delay and Energy Consumption. The evaluation metrics, like Response Time, Load Balancing Rate, Scheduling Time, Delay,and Energy Consumption are analyzed. Then the simulation performance of the Improved energy efficient resource allocation method for load balancing in Fog computing using Hybrid Hydrozoan and Sea Turtle Foraging optimization Algorithms(IDRAM-LB-FC-Hyb-HySTFOA) provide 32.82% and 25.32% low delay, 38.22% and 25.46% low energy consumption compared with the existing methods, like dynamic resource allocation method based load balancing using genetic algorithm in fog computing environment (DRAM-LB-FC-GA) and Load balancing in the fog nodes using particle swarm optimization-based enhanced dynamic resource allocation method (EDRAM-LB-FC-PSOA).

show abstract

A load balancing and optimization strategy (LBOS) using reinforcement learning in fog computing environment

Cited by 110 publications

References 40 publications

A systematic study of load balancing approaches in the fog computing environment

A systematic study of load balancing approaches in the fog computing environment

A Multi Agent Based Dynamic Resource Allocation in Fog-Cloud Computing Environment

Load balancing using a Hybrid Hydrozoan and Sea Turtle Foraging Optimization Algorithm in FOG Computing

Contact Info

Product

Resources

About