Please use this identifier to cite or link to this item:
Title: Hybrid gradient descent cuckoo search (HGDCS) algorithm for resource scheduling in IaaS cloud computing environment
Authors: Madni, Syed Hamid Hussain
Abd Latiff, Muhammad Shafie
Abdulhamid, Shafi’i Muhammad
Ali, Javed
Keywords: Gradient descent
Cloud computing
Meta-heuristic algorithms
Resource scheduling
Cuckoo search
Issue Date: 10-Jun-2018
Publisher: Cluster Computing Springer
Series/Report no.: 22:301–334;
Abstract: Resource scheduling is a procedure for the distribution of resources over time to perform a required task and a decision making process in cloud computing. Optimal resource scheduling is a great challenge and considered to be an NP-hard problem due to the fluctuating demand of cloud users and dynamic nature of resources. In this paper, we formulate a new hybrid gradient descent cuckoo search (HGDCS) algorithm based on gradient descent (GD) approach and cuckoo search (CS) algorithm for optimizing and resolving the problems related to resource scheduling in Infrastructure as a Service (IaaS) cloud computing. This work compares the makespan, throughput, load balancing and performance improvement rate of existing meta-heuristic algorithms with proposed HGDCS algorithm applicable for cloud computing. In comparison with existing meta-heuristic algorithms, proposed HGDCS algorithm performs well for almost in both cases (Case-I and Case-II) with all selected datasets and workload archives. HGDCS algorithm is comparatively and statistically more effective than ACO, ABC, GA, LCA, PSO, SA and original CS algorithms in term of problem solving ability in accordance with results obtained from simulation and statistical analysis.
ISSN: 1386-7857
Appears in Collections:Cyber Security Science

Files in This Item:
File Description SizeFormat 
14.pdf3.11 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.