Saima Aman

Cloud-Based Software Platform for Big Data Analytics in Smart Grids

This article focuses on a scalable software platform for the Smart Grid cyber-physical system using cloud technologies. Dynamic Demand Response (D2R) is a challenge-application to perform intelligent demand-side management and relieve peak load in Smart Power Grids. The platform offers an adaptive information integration pipeline for ingesting dynamic data; a secure repository for researchers to share knowledge; scalable machine-learning models trained over massive datasets for agile demand forecasting; and a portal for visualizing consumption patterns, and validated at the University of Southern Californias campus microgrid. The article examines the role of clouds and their tradeoffs for use in the Smart Grid Cyber-Physical Sagileystem.

Energy management systems: state of the art and emerging trends

The electric grid is radically evolving and transforming into the smart grid, which is characterized by improved energy efficiency and manageability of available resources. Energy management (EM) systems, often integrated with home automation systems, play an important role in the control of home energy consumption and enable increased consumer participation. These systems provide consumers with information about their energy consumption patterns and help them adopt energy-efficient behavior. The new generation EM systems leverage advanced analytics and communication technologies to offer consumers actionable information and control features, while ensuring ease of use, availability, security, and privacy. In this article, we present a survey of the state of the art in EM systems, applications, and frameworks. We define a set of requirements for EM systems and evaluate several EM systems in this context. We also discuss emerging trends in this area.

Improving Energy Use Forecast for Campus Micro-grids Using Indirect Indicators

The rising global demand for energy is best addressed by adopting and promoting sustainable methods of power consumption. We employ an informatics approach towards forecasting the energy consumption patterns in a university campus micro-grid which can be used for energy use planning and conservation. We use novel indirect indicators of energy that are commonly available to train regression tree models that can predict campus and building energy use for coarse (daily) and fine (15-min) time intervals, utilizing 3 years of sensor data collected at 15min intervals from 170 smart power meters. We analyze the impact of individual features used in the models to identify the ones best suited for the application. Our models show a high degree of accuracy with CV-RMSE errors ranging from 7.45% to 19.32%, and a reduction in error from baseline models by up to 53%.

Toward data-driven demand-response optimization in a campus microgrid

We describe and demonstrate a prototype software architecture to support data-driven demand response optimization (DR) in the USC campus microgrid, as part of the Los Angeles Smart Grid Demonstration Project. The architecture includes a semantic information repository that integrates diverse data sources to support DR, demand forecasting using scalable machine-learned models, and detection of load curtailment opportunities by matching complex event patterns.

Addressing data veracity in big data applications

Big data applications such as in smart electric grids, transportation, and remote environment monitoring involve geographically dispersed sensors that periodically send back information to central nodes. In many cases, data from sensors is not available at central nodes at a frequency that is required for real-time modeling and decision-making. This may be due to physical limitations of the transmission networks, or due to consumers limiting frequent transmission of data from sensors located at their premises for security and privacy concerns. Such scenarios lead to partial data problem and raise the issue of data veracity in big data applications. We describe a novel solution to the problem of making short term predictions (up to a few hours ahead) in absence of real-time data from sensors in Smart Grid. A key implication of our work is that by using real-time data from only a small subset of influential sensors, we are able to make predictions for all sensors. We thus reduce the communication complexity involved in transmitting sensory data in Smart Grids. We use real-world electricity consumption data from smart meters to empirically demonstrate the usefulness of our method. Our dataset consists of data collected at 15-min intervals from 170 smart meters in the USC Microgrid for 7 years, totaling 41,697,600 data points.

Enabling Automated Dynamic Demand Response: From Theory to Practice

Demand response (DR) is used in smart grids to shape customer load during peak hours. Automated DR offers utilities a fine grained control and a high degree of confidence in the outcome. However the impact on the customers comfort means this technique is more suited for industrial and commercial settings than for residential homes. In this paper we present a real-life system for achieving automated controlled DR in a heterogeneous environment. The system is integrated with the USC microgrid. Results show that while on a per building per event basis the accuracy of our prediction and customer selection techniques varies, it performs well on average when considering several events and buildings.