Energy management for data centre microgrids considering co‐optimisation of workloads and waste heat

Abstract

The high energy consumption of data centres (DCs) has recently become a significant problem with the rapid development of DCs worldwide. This work studies the daily energy management of a data centre microgrid (DCM). The energy management problem is formulated as a two-stage stochastic mixed-integer linear programing (MILP) model that accounts for workload schedules, cooling resources, uncertainties of onsite renewable generation, and electricity price. An energy management scheme that co-optimises workloads and waste heat is proposed to minimise the operating cost. Furthermore, the potential for waste heat recovery and reuse is also considered. The simulation results illustrate that the proposed model can reduce the operating cost of DCM by the cooptimisation of workloads and waste heat while meeting the temperature requirements for server clusters.

Data center integrated energy system for sustainability: Generalization, approaches, methods, techniques, and future perspectives

“…Consequently, many studies have focused on developing various configurations for DC-IES topology based on their research background. For example, for DCs with strict requirements on temperature and humidity, a DC-IES based on proton exchange membrane fuel cells (PEMFCs), integrating methanol-reforming and dehumidification was proposed, 47 where the adsorption chiller that utilizes waste heat from PEMFC and desiccant air conditioning system are used simultaneously. A combined heat and power (CHP) unit consisting of an absorption chiller was adopted in DC and effectively improving the system energy utilization.…”

“…These characteristics play a significant role in decision-making processes regarding resource allocation; 56 (4) Selecting appropriate energy conversion equipment is crucial for optimizing overall system performance. 47 This involves evaluating various options like electric conversion or thermoelectric conversion technologies based on their efficiency and compatibility with DC-IES requirements; (5) The variables in DC-IES optimization primarily encompass two aspects: the capacity configuration and the operation scheduling of system equipment, including the capacity of each equipment, the hourly cooling, storage charge/ discharge, 48 thermal and electrical output, 57 workload scheduling 58 and electricity interaction; 59 (6) The optimization of DC-IES typically involves solving a multi-objective optimization problem with multi-variable coupling and optimization objectives, the forthcoming text will provide further reviews on evaluation indices and optimization objectives; 60 (7) Establishing a comprehensive model that ensures conservation of mass and energy while accurately representing the energy conversion characteristics of DC-IES equipment; (8) Describing the equality and inequality constraints associated with each device involved in DC-IES. These constraints include capacity limits for efficient operation, and operational range limits for stability under different conditions, along with unique operational characteristics of each device.…”