This paper puts forward a systematic approach to designing energy-aware traffic-efficient geographical load balancing schemes for data-center networks that are not only optimal, but also computationally efficient and amenable to distributed implementation. Under a stochastic optimization approach, we rely on decomposition techniques and develop a two-timescale algorithm that optimizes jointly workload and power balancing schemes across the network. Both delay-tolerant and interactive workloads are accommodated, and novel smart-grid features are incorporated to cope with renewables and energy storage units.
|Original language||English (US)|
|Title of host publication||Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016|
|Editors||Michael B. Matthews|
|Publisher||IEEE Computer Society|
|Number of pages||5|
|State||Published - Mar 1 2017|
|Event||50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 - Pacific Grove, United States|
Duration: Nov 6 2016 → Nov 9 2016
|Name||Conference Record - Asilomar Conference on Signals, Systems and Computers|
|Other||50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016|
|Period||11/6/16 → 11/9/16|
Bibliographical noteFunding Information:
Work in this paper was supported by NSF grants 1509040, 1508993, 1423316, 1442686, by Spanish MINECO Grant TEC2013-41604-R and CAM Grant S2013/ICE-2933.