Show simple item record

dc.contributor.advisorChakrabarty, Amitabha
dc.contributor.advisorMostakim, Moin
dc.contributor.authorNiloy, Maharshi
dc.contributor.authorMoni, Md. Moynul Asik
dc.contributor.authorKhan, Farah Jasmin
dc.contributor.authorChowdhury, Aquibul Haq
dc.contributor.authorJuboraj, Md. Fahmid-Ul-Alam
dc.date.accessioned2023-10-16T05:33:25Z
dc.date.available2023-10-16T05:33:25Z
dc.date.copyright©2022
dc.date.issued2022-09-28
dc.identifier.otherID 19101117
dc.identifier.otherID 19101189
dc.identifier.otherID 19101239
dc.identifier.otherID 19101290
dc.identifier.otherID 19101618
dc.identifier.urihttp://hdl.handle.net/10361/21838
dc.descriptionThis thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2022.en_US
dc.descriptionCataloged from PDF version of thesis.
dc.descriptionIncludes bibliographical references (pages 36-39).
dc.description.abstractProcess scheduling is an integral part of operating systems. The most widely used scheduling algorithm in operating systems is round-robin (RR), but the average waiting time in RR is often quite long. The purpose of this study is to propose a new algorithm to minimize waiting time and process starvation by determining the optimal time quantum by predicting CPU burst time. For burst time prediction, we are using the machine learning algorithms decision tree (DT), k-nearest neighbors (KNN), linear regression (LR) and Neural Network Model Multi-Layer perceptron-MLP. Finally, the obtained accuracy for burst time prediction of DT is 98.64%, KNN is 17.1%, LR is 97.96% and using MLP is 26.01%. Moreover, for 10000 predicted(burst time) processes with the same configuration the average turnaround time (avg TT), the average wait time (avg WT) and the number of context switches (CS) of the proposed algorithm are consecutively 40331930.48, 40312117.96 and 20002, whereas Traditional Round Robin (RR) has 87194390.98 (avg TT), 87174578.46 (avg WT) and 28964 (CS). Self-Adjustment Round Robin (SARR) has 72398064.70 (avg TT), 72378252.18 (avg WT) and 39956 (CS). Modi- fied Round Robin Algorithm (MRRA) has 84924105.36 (avg TT), 84904292.84 (avg WT) and 5208 (CS) and Optimized Round Robin (ORR) has 78508779.73 (avg TT), 78488967.20 (avg WT) and 22470 (CS). Therefore, it is clear that the proposed algo- rithm is almost 2 times faster than the other algorithm in terms of process scheduling under a huge load of processes.en_US
dc.description.statementofresponsibilityMaharshi Niloy
dc.description.statementofresponsibilityMd. Moynul Asik Moni
dc.description.statementofresponsibilityFarah Jasmin Khan
dc.description.statementofresponsibilityAquibul Haq Chowdhury
dc.description.statementofresponsibilityMd. Fahmid-Ul-Alam Juboraj
dc.format.extent51 pages
dc.language.isoenen_US
dc.publisherBrac Universityen_US
dc.rightsBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.
dc.subjectDecision tree (DT)en_US
dc.subjectKNNen_US
dc.subjectLinear regression (LR)en_US
dc.subjectNeural network (NN)en_US
dc.subjectMLPen_US
dc.subjectAverage turnaround time (avg TT)en_US
dc.subjectOptimized round robin (ORR)en_US
dc.subjectModified round robin algorithm (MRRA)en_US
dc.subjectSelf-adjustment round robin (SARR)en_US
dc.subjectRound robin (RR)en_US
dc.subjectAverage waiting time (avg WT)en_US
dc.subjectContext switch (CS)en_US
dc.subjectProposed algorithmen_US
dc.subjectBurst timeen_US
dc.subject.lcshArtificial intelligence
dc.subject.lcshAlgorithms
dc.titleComparative analysis and implementation of AI algorithms and NN model in process scheduling algorithmen_US
dc.typeThesisen_US
dc.contributor.departmentDepartment of Computer Science and Engineering, Brac University
dc.description.degreeB.Sc. in Computer Science


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record