Smart grid data analytics framework for increasing energy savings in residential buildings

• Published in: Automation in construction Vol. 72; pp. 247 - 257
• Main Authors: Chou, Jui-Sheng, Ngo, Ngoc-Tri
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.12.2016; Elsevier BV
• Subjects: Air pollution; Analytics; Architecture; Big data; Cost engineering; Data acquisition; Data analysis; Data management; Decision analysis; Decision support systems; Electric appliances; Electricity consumption; Electricity pricing; End users; Energy conservation; Energy consumption; Energy costs; Energy saving; Global warming; Heuristic methods; Home appliance; Household appliances; Mathematical analysis; Optimization; Power efficiency; Residential buildings; Residential energy; Schedules; Smart grid; Time series data analytics; Web-based portal; World Wide Web; Time series data analytics; Home appliance; Web-based portal; Big data; Energy saving; Smart grid; Optimization
• ISSN: 0926-5805; 1872-7891
• DOI: 10.1016/j.autcon.2016.01.002

Human energy consumption has gradually increased greenhouse gas concentrations and is considered the main cause of global warming. Currently, the building sector is a major energy consumer, and its share of energy consumption is increasing because of urbanization. This paper presents a framework for smart grid big data analytics and components required for an energy-saving decision-support system. The proposed system has a layered architecture that includes a smart grid, a data collection layer, an analytics bench, and a web-based portal. A smart metering infrastructure was installed in a residential building to conduct an experiment for evaluating the effectiveness of the proposed framework. Furthermore, a novel hybrid nature-inspired metaheuristic forecast system and a dynamic optimization algorithm are designed behind the analytics bench for achieving accurate prediction and optimization of future energy consumption. The main contribution of this study is that an innovative framework for the energy-saving decision process is presented; the framework can serve as a basis for the future development of a full-scale smart decision support system (SDSS). Through the identification of consumer usage patterns, the SDSS is expected to enhance energy use efficiency and improve the accuracy of future energy demand estimates. End users can reduce their electricity costs by implementing the optimal operating schedules for appliances, which are provided by the SDSS. [Display omitted] •This study presents a smart grid big data analytics framework.•The framework consists of data layer, analytics bench, and web-based portal.•Smart grid infrastructure is installed in a residential building for experiments.•A novel time-series metaheuristic algorithm is designed to forecast energy consumption.•A decision-support system is proposed to optimize and allocate energy usage.