A New Method to Improve Round Robin Scheduling Algorithm with Quantum Time Based on Harmonic-Arithmetic Mean (HARM)
Ashkan Emami Ale Agha, Somayyeh Jafarali Jassbi · International Journal of Information Technology and Computer Science · 2013
One of the most important concepts in multi programming Operat ing Systems is scheduling.It helps in choosing the processes for execution.Round robin method is one of the most important algorithms in scheduling.It is the most popular algorith m due to its fairness and starvation free nature towards the process es, which is achieved by using proper quantum time .The main challenge in this algorithm is selection of quantum time.Th is parameter affects on average Waiting Time and average Turnaround Time in execution queue.As the quantum time is static, it causes less context switching in case of h igh quantum time and high context switching in case of less quantum time.Increasing context switch leads to high average waiting time, h igh average turnaround time wh ich is an overhead and degrades the system performance.With respect to these points, the algorith ms should calculate proper value fo r the quantum t ime.Two main classes of algorith ms that are proposed to calculate the quantum time include static and dynamic methods.In static methods quantum time is fixed during the scheduling.Dynamic algorith ms are one of these methods that change the value of quantum time in each cycle.For example in one method the value of quantum time in each cycle is equal to the median o f burst times of processes in ready queue and for another method this value is equal to arithmet ic mean o f burst times of ready processes.In this paper we proposed a new method to obtaining quantum t ime in each cycle based on arith meticharmonic mean (HARM).Harmonic mean is calculated by dividing the number of observations by the reciprocal of each number in the series .With examples we show that in some cases it can p rovides better scheduling criteria and imp roves the average Turnaround Time and average Waiting Time.