AMI Data for Decision Makers and the Use of Data Analytics Approach

Abstract

The Advanced Metering Infrastructure (AMI) analytics provide a source of real-time information not only about energy usage, but also as an indicator of various social, demographic, and economic phenomena inside a city, according to the National Electricity Information Administration. As a tool for leveraging the potential of AMI data within the applications in a Smart City, this article proposes a Data Analytics/Big Data framework applied to AMI data as presented in this study. The framework is comprised of three main components. First and foremost, the architectural perspective sets AMI within the context of the Smart Grids Architecture Model-SGAM. Second, the methodological view describes the translation of raw data into knowledge, which is represented by the DIKW hierarchy and the NIST Big Data interoperability model, among other things. The final factor that connects the two perspectives is human expertise and talents, which enable us to gain a better comprehension of the results and translate knowledge into wisdom. Our novel perspective responds to the issues that are emerging in the energy markets by including a binding element that provides assistance for the most optimal and efficient decision-making possible. We created a case study to demonstrate the functionality of our framework. It illustrates how each component of the framework for a load forecasting application at a retail electricity provider is implemented in the instance described here (REP). According to the company, the Mean Absolute Percentage Error (MAPE) for certain of the REP's markets was less than 5 percent. Aside from that, the instance illustrates what happens when the binding element is introduced, since it generates fresh development possibilities and serves as a feedback mechanism for more forceful decision-making.