K. Pradeep

Bio: K. Pradeep is an academic researcher from St. Joseph's College of Engineering. The author has contributed to research in topics: Scheduling (computing) & Fixed-priority pre-emptive scheduling. The author has an hindex of 1, co-authored 1 publications receiving 25 citations.

CGSA scheduler: A multi-objective-based hybrid approach for task scheduling in cloud environment

Abstract: In cloud computing task scheduling is one of the important processes. The key problem of scheduling is how to allocate the entire task to a corresponding virtual machine while maximizing profit. Th...

A Multi-objective Optimal Task Scheduling in Cloud Environment Using Cuckoo Particle Swarm Optimization

Abstract: In cloud computing, varied demands are placed on the constantly changing resources. The task scheduling place very vital role in cloud computing environments, this scheduling process needs to schedule the tasks to virtual machine while reducing the makespan and cost. The task scheduling problem comes under NP hard category. Efficient scheduling method makes cloud computing services better and faster. In general, optimization algorithms are used to solve the scheduling issues in cloud. So, in this paper we combined two optimization algorithms namely called as Cuckoo Search (CS) and Particle Swarm Optimization (PSO).The new proposed hybrid algorithm is called as, CS and particle swarm optimization (CPSO). Our main purpose of the proposed paper is to reduce the makespan, cost and deadline violation rate. The performance of the proposed CPSO algorithm is evaluated using cloudsim toolkit. From the simulation results our proposed works minimize the makespan, cost, deadline violation rate, when compared to PBACO, ACO, MIN–MIN, and FCFS.

A Systematic Review on Image Processing and Machine Learning Techniques for Detecting Plant Diseases

Abstract: Techniques predicting the type of diseases affecting plants in their lifetime will be of immense help to agriculturists. This article throws light upon such techniques in the form of a survey that had been carried out comprehensively covering various image based plant leaf diseases. Such diseases are mostly grievous and they strike at any part of the plant. There are huge accumulated losses due to such diseases that bring down the productivity and increase the economic losses in the agricultural industry. Agriculture industry needs to sustain and evolve from such obstacles to be highly profitable. This can be done by precisely monitoring the health and detecting the diseases at appropriate stages of the plant’s life time. Technology has spread its wings in every field of day to day life but still its reach in the field of agriculture is not up to the mark. Agriculture industry is still thriving on outdated technical methodologies. Improper diagnosis of plant disease may lead to huge losses in terms of production, time, cost and product quality. The condition of the plant needs to be tracked throughout its growing stages leading to successful cultivation. As part of technological innovation, researchers had been applying the image processing techniques for monitoring as well as diagnosing the plant diseases in its various stages. Appropriate machine learning algorithms are being designed and applied for precisely identifying the various infections on plants throughout its life cycle and the type of treatment that can be afforded for overcoming loss.

Hybrid‐based novel approach for resource scheduling using MCFCM and PSO in cloud computing environment

Abstract: Cloud computing is a growing environment. Many of the users are interested to outsource their data in cloud; however, load balancing in cloud is still at risk. Resource allocation plays a major role in load balancing. In this scheduling problem, independent task in cloud computing can allocate resource by the summary of modified canopy fuzzy c‐means algorithm (MCFCMA). To allocate task to their corresponding resource, particle swarm‐based optimization algorithm (PSO) is used. In proposed scheme, first independent task selected based on load feed‐back, cluster the requested task using MCFCMA and schedule task to each virtual machine. VM selects parallel execution in virtual machine manager. Calculate feature value using PSO algorithm. Allocate resource to the task. Since our proposed system selects resource based on parallel execution, it reduces load balancing in Cloud Quantum Computation (CQC). The proposed system overcomes issues in load balancing and load scheduling; this can be proved by its precision and privacy calculation.

Multi-Objective Task Scheduling Using Hybrid Whale Genetic Optimization Algorithm in Heterogeneous Computing Environment

Abstract: The system of cloud computing comprises of several servers that are inter-connected in a datacenter, provisioned dynamically to cater on-demand services through the front-end interface for the clients. Improvement in virtualization technology has made cloud computing a viable option for various application services development. Cloud datacenters process the tasks on the basis of pay as you use manner. Task scheduling is one of the important research challenges in cloud computing. The formulation of task scheduling probes has been depicted to be NP-hard hence identifying the solution for a bigger problem is intractable. The dissimilar feature of cloud resources makes task scheduling non-trivial. NP-hard problem arises due to the dynamic behavior of the dissimilar resources identified in the cloud computing environment. Task scheduling can be optimized using a meta-heuristic algorithm. In this paper, we have combined two meta-heuristic techniques, namely Whale Optimization Algorithm (WOA) and Genetic Algorithm (GA) to devise a new hybridized algorithm called as Whale Genetic Optimization Algorithm. Our aim is to minimize the makespan and cost while scheduling the tasks. The simulation is done by using Cloudsim toolkit. The results obtained shows significant reduction in the execution time that was measured in terms of enactment amelioration rate. These results were compared with the classical WOA and standard GA. The results of the proposed technique provide higher quality solution for task scheduling.