SmartDPSS: Cost-Minimizing Multi-source Power Supply for Datacenters with Arbitrary Demand

Abstract

Abstract-To tackle soaring power costs, significant carbon emission and unexpected power outage, Cloud Service Providers (CSPs) typically equip their Datacenters with a Power Supply System (DPSS) nurtured by multiple sources: (1) smart grid with time-varying electricity prices, (2) uninterrupted power supply (UPS), and (3) renewable energy with intermittent and uncertain supply. It remains a significant challenge how to operate among multiple power supply sources in a complementary manner, to deliver reliable energy to datacenter users with arbitrary demand over time, while minimizing a CSP's operation cost over the long run. This paper proposes an efficient, online control algorithm for DPSS, SmartDPSS, based on the two-timescale Lyapunov optimization techniques. Without requiring a priori knowledge of system statistics, SmartDPSS allows CSPs to make online decisions on how much power demand, including delay-sensitive demand and delay-tolerant demand, to serve at each time, the amount of power to purchase from the long-term-ahead and realtime grid markets, and charging and discharging of UPS over time, in order to fully leverage the available renewable energy and time-varying prices from the grid markets, for minimum operational cost. We thoroughly analyze the performance of our online control algorithm with rigorous theoretical analysis. We also demonstrate its optimality in terms of operational cost, demand service delay, datacenter availability, system robustness and scalability, using extensive simulations based on one-month worth of traces from live power systems.

On Arbitrating the Power-Performance Tradeoff in SaaS Clouds

“…Second, though there exist alternative online control solutions [14], [15], [16], [17] in the literature for dynamic resource allocation and power management in datacenters, our work differs substantially in at least two important aspects. 1) We take an economic viewpoint to price application throughput with a nonlinear utility function based on the law of diminishing marginal utility (Section 3.2.3), rather than a simple linear utility function [14] that does not reflect reality in general.…”

Carbon-Aware Load Balancing for Geo-distributed Cloud Services

“…However, almost all of these works focused on reducing the power consumption or electricity bill [4]- [9], [25], [26]. Our work is different from those works in that we directly study the carbon emission aspect.…”

“…Taking an expectation for inequality (26) with respect to the distribution of Q j (t) and using iterative expectation law results in:…”

SGEESS: Smart green energy-efficient scheduling strategy with dynamic electricity price for data center

“…Goiri et al (2013) presented the Parasol, a prototype green data center built as a research platform, and the GreenSwitch, a model-based approach for dynamically scheduling the workload and selecting the source of energy to use. Deng et al (2013) applied the two-stage Lyapunov optimization to design an online control algorithm -SmartDPSS, which optimally schedules multi-source energy to power a data center with arbitrary demand in a cost minimizing fashion. Bird et al (2014) introduced a new conceptual approach to green data centers by using multiple, distributed networked data centers that are co-located with renewable energy.…”