Distributed Real-Time Energy Management in Data Center Microgrids

In this paper, we investigate the problem of energy management in data center microgrids. Specifically, we intend to minimize the long-term operational cost (including the total electricity bill of data centers, battery depreciation cost, the total generation cost of conventional generators, and revenue loss incurred by workload allocation) of data center microgrids by taking into account the uncertainties in electricity prices, renewable outputs and data center workloads. We first formulate a stochastic programming problem to minimize the long-term operational cost of data center microgrids with the considerations of many factors, e.g., providing heterogeneous service delay guarantees for batch workloads, batch workload shedding, electricity buying/selling, battery charging/discharging efficiency, and the ramping constraints of backup generators. Since the formulated optimization problem is a large-scale nonlinear stochastic programming with time-coupling property, it is difficult to be solved. To overcome the above challenge, we design a distributed realtime algorithm for the formulated problem based on Lyapunov optimization technique and a variant of alternating direction method of multipliers (ADMM). Moreover, the performance guarantee of the proposed algorithm is analyzed. It is worth mentioning that the proposed algorithm does not require any prior knowledge of system parameters and has low computational complexity. Extensive simulation results show that the proposed algorithm could reduce the operational cost of data center microgrids effectively.