Analytical Model of Delayed Server System (DSS) for Energy Conservation

Abstract

This paper proposes a delayed server system (DSS) which regulates the number of servers in ON-state, and corresponding OFF-state servers, on the basis of queue occupancy for the sake of energy conservation. Upon arrival of demand, server allocation is delayed if predefined servers are already busy and, thus, customer is going to wait in the queue before it gets service. Hence, DSS allows us to keep some servers at least OFF for fraction of total operational, time resulting in energy conservation. We have developed the Markov chain models for DSS and M/M/n-s systems. Using the Markov chain models, the numerical evaluation has been carried out for the key performance metrics such as blocking probability and average energy conservation. Furthermore, our study has investigated and figured out the optimal configurations of delayed server system in order to maximize the energy conservation