Online Energy Budgeting for Cost Minimization in Virtualized Data Center

Abstract

The growing environmental and sustainability concerns have made energy efficiency a pressing issue for data center operation. Governments, as well as various organizations, are urging data centers to cap the increasing energy consumption. Naturally, achieving long term energy capping involves deciding the energy usage over a long timescale (without accurately foreseeing the far future) and hence, we call this process "energy budgeting". In this paper, we introduce an online resource management solution, called eBud (energy Budgeting), for a virtualized data center. eBud determines the number of servers, resource allocation to virtual machines and corresponding workload distribution to minimize data center operational cost while satisfying a long term energy cap. We theoretically prove that eBud achieves a close-to-minimum cost compared to the optimal offline algorithm with future information, while bounding the potential violation of energy budget constraint, in an almost arbitrarily random environment. We also perform a trace-based simulation study to complement the theoretical analysis. The simulation results show that eBud reduces the cost by more than 16% (compared to state-of-the-art prediction-based algorithm) while resulting in a zero energy budget deficit. We also perform an experimental study based on RUBiS benchmark application, demonstrating that, in real life scenario, eBud can achieve energy capping with a negligible increase in operational cost.

Dynamic switch-controller association and control devolution for SDN systems

“…When V is small, switches prefer controllers with shorter queues. 6 A switch's scheduling decision is independent of the others'. This will lead to arriving requests being intensively uploaded to just few controllers.…”

“…This will lead to arriving requests being intensively uploaded to just few controllers. In this way, controllers close to hot spots are 6 Note that JSQ is just a special case of Greedy with V = 0. more likely to get heavier loads, though Greedy would adjust the load spread in the next time slot. As V becomes larger, some switches would reach a tipping point and choose other controllers instead.…”

“…where f X (t) is defined by (4), g X (t) is defined by (6), and V > 0 is a constant that weights the penalty brought by f X (t) and g X (t).…”

“…Previous works have proposed a variety of solutions to related problems, such as ensemble routing [15], energy budgeting [6], workflow scheduling [10], virtual slice provisioning [14], VM placement [20], etc. Meanwhile, softwaredefined networking (SDN) provides an alternative perspective to manage the whole network.…”

optimization-Based Home Energy Management System Under Different Electricity Pricing Schemes

“…The significant penetration of Renewable Energy Resources (RERs) for supplying electricity demand, became an irrefutable fact around the world [1]. In addition to supplying energy, RERs such as Photovoltaic (PV), and wind turbines, can be mentioned as nature-friendly resources against to disadvantages of fossil fuels [2]. According to [3], many buildings were persuaded to install rooftop PV system for supplying a part of their consumption.…”