Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/481730
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.coverage.spatial | Optimal resource allocation using greedy adaptive firefly algorithm in cloud computing | |
dc.date.accessioned | 2023-05-08T11:47:47Z | - |
dc.date.available | 2023-05-08T11:47:47Z | - |
dc.identifier.uri | http://hdl.handle.net/10603/481730 | - |
dc.description.abstract | The service provider s resources such as memory, power, network newlinebandwidth and storage can be easily monitored in the cloud. An efficient newlinetechnology known as cloud computing effectively overcomes complex and newlinemassive computations in cloud environment. Cloud computing performs newlinesecure data service integration, stores scalable data and parallel processing. It newlineprocesses the information, store and transfer on infrastructure of service newlineprovider to meet the requirements of QoS in customer control policy. Cloud newlinecomputing allows commercial clients to contract and expand resource newlineutilization depending upon their requirements. However in cloud computing, newlinethere is a high demand in resource allocation since it is necessary to provide newlineavailable resource when internet in cloud application requires resources. newlineHence an optimal resource allocation based on multi-agent system is required newlineto overcome such issues. Local agents for resource management and global newlineagents for resource scheduling make up the multi-agent system. To boost newlineperformance, the agents should help each other make excellent judgments newlineabout their behaviours. Here, multi agent-based Deep Reinforcement newlineLearning (DRL) is used to manage the resources by reformulating requests newlinebased on wasted resources in the request history made by the user. newlineReinforcement learning (RL) takes an immediate action to provide a high newlinereward or explores its surroundings to maximize the average benefit it newlinereceives over time by action performance. Global agents provide the Greedy newlineAdaptive Firefly Algorithm (GAF) to efficiently schedule resources after newlinereformulating the requests. newline | |
dc.format.extent | xviii,115p. | |
dc.language | English | |
dc.relation | 9-p.101-114 | |
dc.rights | university | |
dc.title | Optimal resource allocation using greedy adaptive firefly algorithm in cloud computing | |
dc.title.alternative | ||
dc.creator.researcher | Chitharanjan K | |
dc.subject.keyword | Cloud Computing | |
dc.subject.keyword | Deep Reinforcement Learning | |
dc.subject.keyword | Adaptive Firefly Algorithm | |
dc.description.note | ||
dc.contributor.guide | Radha Senthilkumar | |
dc.publisher.place | Chennai | |
dc.publisher.university | Anna University | |
dc.publisher.institution | Faculty of Information and Communication Engineering | |
dc.date.registered | ||
dc.date.completed | 2022 | |
dc.date.awarded | 2022 | |
dc.format.dimensions | 21cm | |
dc.format.accompanyingmaterial | None | |
dc.source.university | University | |
dc.type.degree | Ph.D. | |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 167.4 kB | Adobe PDF | View/Open |
02_prelimpages.pdf | 750.11 kB | Adobe PDF | View/Open | |
03_contents.pdf | 213 kB | Adobe PDF | View/Open | |
04_abstracts.pdf | 181.7 kB | Adobe PDF | View/Open | |
05_chapter1.pdf | 1.3 MB | Adobe PDF | View/Open | |
06_chapter2.pdf | 394.32 kB | Adobe PDF | View/Open | |
07_chapter3.pdf | 721.24 kB | Adobe PDF | View/Open | |
08_annexures.pdf | 93.55 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 54.15 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: