A Performance Analysis of Task Scheduling Algorithms using Qualitative Parameters

Abstract

A CPU is the very important part of the computer system; hence it must be utilized efficiently. When the demand for computing power increases, then scheduling problem becomes very important. The problem of task scheduling and load balancing are most important and challenging area of research in computer engineering. Task scheduling can be defined as allocating processes to processor so that total execution time will be minimized, utilization of processors will be optimized. Load balancing is the process of improving the performance of system through a redistribution of load among processor. In this paper, the performance analysis of various task scheduling algorithms based on different qualitative parameters is presented. The analysis indicates that task scheduling algorithms have some advantages as well as disadvantages. The main purpose of this paper is to help in design of new scheduling algorithms in future by studying existing task scheduling algorithms.

A State-of-the-Art Survey and Taxonomy of Classification, Algorithms, and Techniques for Load Balancing in SDN

“…So, the main problem with static load-balancing algorithms is that they need to consider the system's current state. This type makes them unsuitable for plans whose load status can't be predicted in advance [42]. It includes the following algorithms: 1.…”

Improved time quantum length estimation for round robin scheduling algorithm using neural network

“…For long-term scheduler, it loads processes in memory for execution after selecting them from the job pool. Concerning the short-term scheduler, it allocates the CPU to one process from those ready to be executed [12], [15]. For medium-term scheduler, it takes off processes from main memory and place them on secondary memory (such as a disk drive) or vice versa.…”