Holistic Management of Sustainable Geo-Distributed Data Centers

Abstract

This paper designs a holistic global workload management solution which explores diversities of a set of geo-distributed data centers and energy buffering in order to minimize the electricity cost, reduce the peak power drawn from utilities while maintaining the carbon capping requirement of the data centers. The prior work often designed solutions to address each of the aforementioned energy and cost optimization separately, disregarding the possible conflicts between the solutions' objectives. We propose a holistic solution to concurrently optimize the aforementioned potentially competing objectives. The proposed solution combines the techniques from Lyapunov optimization and predictive solution in order to manage the tradeoffs of electricity cost and carbon footprint reduction, and electricity cost and peak power cost reduction, respectively. The predicted data center parameters, being a significant aid to near optimally manage energy buffering and smoothing data centers' peak power draw, adversely affect the peak power cost due to the parameters' prediction error. The proposed holistic solution adapts stochastic programing to take the predicted parameters' randomness into consideration for minimizing the harmful impact of the prediction error. Our trace-based study confirms our analytical result that our holistic solution balances all the tradeoffs towards achieving energy and cost sustainability. Also our solution removes up to 66% of the prediction error impact in increasing the cost.