Integrating Renewable Energy Using Data Analytics Systems: Challenges and Opportunities.

The variable and intermittent nature of many renewable energy sources makes integrating them into the electric grid challenging and limits their penetration. The current grid requires expensive, largescale energy storage and peaker plants to match such supplies to conventional loads. We present an alternative solution, in which supply-following loads adjust their power consumption to match the available renewable energy supply. We show Internet data centers running batched, data analytic workloads are well suited to be such supply-following loads. They are large energy consumers, highly instrumented, agile, and contain much scheduling slack in their workloads. We explore the problem of scheduling the workload to align with the time-varying available wind power. Using simulations driven by real life batch workloads and wind power traces, we demonstrate that simple, supply-following job schedulers yield 40-60% better renewable energy penetration than supply-oblivious schedulers.