Data center and load aggregator coordination towards electricity demand response

Yijia Zhang, Athanasios Tsiligkaridis, Ioannis Ch. Paschalidis, Ayse K. Coskun

Abstract: Highlights•DCAopt, a joint data center and aggregator optimization framework, optimizes quality-of-service of jobs, coordinates workload sharing, and assigns electricity prices that incentivize demand response.•DCAopt employs a realistic data center model, accepting heterogenous workloads composed of jobs with different properties (arrival rate, execution time, time constraint).•A queueing-theoretic approach in DCAopt quantifies and optimizes the quality-of-service of jobs.•DCAopt is evaluated using an event-based data center job scheduling simulator, which captures job events (arrival / start / finish) on the timescale of seconds.