Cucumber: Renewable-Aware Admission Control for Delay-Tolerant Cloud and Edge Workloads

Abstract

The growing electricity demand of cloud and edge computing increases operational costs and will soon have a considerable impact on the environment. A possible countermeasure is equipping IT infrastructure directly with on-site renewable energy sources. Yet, particularly smaller data centers may not be able to use all generated power directly at all times, while feeding it into the public grid or energy storage is often not an option. To maximize the usage of renewable excess energy, we propose Cucumber, an admission control policy that accepts delaytolerant workloads only if they can be computed within their deadlines without the use of grid energy. Using probabilistic forecasting of computational load, energy consumption, and energy production, Cucumber can be configured towards more optimistic or conservative admission. We evaluate our approach on two scenarios using real solar production forecasts for Berlin, Mexico City, and Cape Town in a simulation environment. For scenarios where excess energy was actually available, our results show that Cucumber's default configuration achieves acceptance rates close to the optimal case and causes 97.0 % of accepted workloads to be powered using excess energy, while more conservative admission results in 18.5 % reduced acceptance at almost zero grid power usage.

BEASY: Making EASY Backfilling Renewable-Only

“…Their work has integration with the grid to buy/sell energy. [10] proposes an admission control policy, named Cucumber, that accepts jobs only if they can be computed within their deadlines without the use of grid energy. They estimate the power production and consumption, using the remainder of both (production minus consumption) to accept new jobs.…”

“…It is possible to notice that the majority of the works consider only online [7], [8], [11], [12], [15] or offline decisions [9], [10], [13], [16]. Therefore, to the best of our knowledge, only work [17] proposes a mix between offline and online decisions, for a renewable-only data center and considering battery awareness.…”

Migrating from microservices to serverless

“…For instance, datacenters worldwide consumed 205 TWh of electricity in 2018 [41], exceeding the annual electricity consumption of countries such as Ireland and Luxembourg [44]. With the increasing migration rate of software to the cloud and the additional demand from novel domains such as Internet of Things (IoT) [24,50], these datacenters are forecasted to consume between 3% to 13% of the world's total electricity by 2030 [23].…”