Hybrid gradient descent cuckoo search (HGDCS) algorithm for resource scheduling in IaaS cloud computing environment

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 dynami...

Full description

Saved in:
Bibliographic Details
Published in:Cluster computing 2019-03, Vol.22 (1), p.301-334
Main Authors: Madni, Syed Hamid Hussain, Abd Latiff, Muhammad Shafie, Abdulhamid, Shafi’i Muhammad, Ali, Javed
Format: Article
Language:English
Subjects:
Algorithms
Cloud computing
Computer Communication Networks
Computer Science
Energy consumption
Heuristic
Heuristic methods
Hybridization
Operating Systems
Optimization
Performance evaluation
Problem solving
Processor Architectures
Resource scheduling
Scheduling
Search algorithms
Simulation
Software
Statistical analysis
Task scheduling
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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
1573-7543
DOI:10.1007/s10586-018-2856-x