Abstract Commercial buildings have been identified as a major contributor of total global energy consumption. Mechanisms for collecting data about energy consumption patterns within buildings, and their subsequent analysis to support demand estimation (and reduction) remain important research challenges, which have already attracted considerable work. We propose a cloud based energy management system that enables such analysis to scale to both increasing data volumes and number of buildings. We consider both energy consumption and storage to support: (i) flattening the peak demand of commercial building(s); (ii) enable a “cost reduction” mode where the demand of a commercial building is reduced for those hours when a “triad peak” is expected; and (iii) enables a building manager to participate in grid balancing services market by means of demand response. The energy management system is deployed on a cloud infrastructure that adapts the number of computational resources needed to estimate potential demand, and to adaptively run multiple what-if scenarios to choose the most optimum configuration to reduce building energy demand.
[1]
Manish Parashar,et al.
CometCloud: Enabling Software-Defined Federations for End-to-End Application Workflows
,
2015,
IEEE Internet Computing.
[2]
Omer F. Rana,et al.
Predicting the energy demand of buildings during triad peaks in GB
,
2017
.
[3]
Yogesh L. Simmhan,et al.
Cloud-Based Software Platform for Big Data Analytics in Smart Grids
,
2013,
Computing in Science & Engineering.
[4]
Omer Rana,et al.
Fog Paradigm for Local Energy Management Systems
,
2017,
IISSC/CN4IoT.
[5]
T. Rajeev,et al.
A cloud computing approach for power management of microgrids
,
2011
.