My motivation to pursuedoctoral studies comes from my deep-rooted interest for energy systems coupledwith the desire to address the challenges arising with building energy systemsof the future. From the traditional hub and spoke architecture, power systems oftoday have evolved into a complex cyber-physical system with heavy reliance onintermittent distributed energy sources. Such changes necessitate developmentof new intricate control & operational methodologies to ensure efficient,reliable and resilient operation of this system. I amapplying to the Ph.D.
program at Stanford University to address thesechallenges using an interdisciplinary approach of data analytics, optimizationand energy system engineering. The need for sustainablepower generation and distribution was the cornerstone for my career inElectrical Engineering. My undergraduate studies equipped me with themathematical and electrical engineering fundamentals vital for building astrong foundation. Research and internships done during undergraduate careerfueled my interest in energy systems that brought me to Georgia Tech to pursuea Master’s degree in Electrical Engineering. In the first year ofMaster’s program, I focused my coursework and research in the areas of smartgrids, power electronics applications for power systems, control system designand optimization. I worked with Professor Santiago Grijalva to build a smart homeenergy management system that based its operations on real time electricityprices. The purpose of this project was to schedule the consumption from thegrid, solar PV and battery storage in a pattern that minimized the total costof electricity consumption from the grid.
I proposed that data processing andoptimization be done on a cloud server to help increase the system scalabilitywhile expanding it to accommodate several houses supplied by an electricutility. Working on this project gave me experience in hardware implementationof the smart grid layers in real time, along with formulation & executionof optimization problem using mixed integer linear programing. I worked on a researchproject on grid connected smart inverters with Professor Deepak Divan atGeorgia Tech’s Center for Distributed Energy (CDE). The goal of this projectwas to understand the drawbacks of traditional inverters in smooth operation ofa grid with heavy inverter interfaced generation and address this issue byadding smart functionalities to the traditional inverter. For this, I designed agrid connected H-Bridge inverter and implemented various control layers to addsmart inverter functionality of voltage ride through and dynamic voltagesupport. This entire system was then simulated for different types of gridfaults.
Based on the observations, I further tuned the control loop to ensureoptimal system performance under any condition. Such smart functionalitiesequipped the inverter to provide grid support by staying connected to the gridduring faults, thus speeding up the fault recovery process. This research helped unearth the shortcomings of smartinverters based on the nature of the system they are connected to and theirasynchronized behavior in systems connected to multiple inverter interfaceddistributed energy resources. My interest towardsleveraging data analytics for advancing energy systems stems from my graduateinternship with the Advanced Grid Analytics (AGA) group at Landis+Gyr (L+G), aleading smart grids solutions company. My projects at L+G were focused on distributionsystem data analytics, an emerging area under the smart grids domain. I worked on designing and implementing a robust algorithmthat processed the myriad of data available from smart meters for mappingmeters to their corresponding transformers. The algorithm was tested foreffectiveness on different distribution systems belonging to differentutilities and produced visible results.
Distribution systemsare equipped with multiple Volt/VAR devices to ensure voltages at every pointin the network lie within the limits specified by American National StandardsInstitute (ANSI). One of the pressing problems faced by the electric utilitiesis the lack of knowledge on the operational performance of these devices. Tomitigate this issue, I designed a novel tool that utilized the AMI and systemtopology data to closely monitor the device performance on a daily basis. Thealgorithm factors in the physics that underlie the asset operation and iscomputationally efficient, can seamlessly handle frequent system topologyreconfigurations and does not require installation of any additional sensors.This asset health monitoring algorithm will be the first of its kind and willbe offered to the utilities as a software service or will be integrated as anew module within L+G’s proprietary AGA platform. As of today, this tool is under development and testing phase byvalidating its results on data pertaining to different utilities and apreliminary patent application is under review.
Interning at L+G was a steep learning curve in the distribution system dataanalytics, utilizing various statistical techniques for analyzing data anddesigning algorithms to efficiently process big data. Working on data analytics piqued my curiosity to explore MachineLearning. To familiarize myself with machine learning concepts and algorithms, I took few onlinecourses. I found the decision tree algorithm most suitable for enhancing thetransformer-meter mapping tool and am currently working towards implementingit. I look forward towards integrating machine learning in my doctoralresearch. Electrification, decentralization and digitization are mergingtogether to build the next generation electric grid.
Some of the challengesposed by such distributed system architecture are maintaining system stabilityalong with regulating voltage appropriately in the presence of intermittentrenewable energy sources, smoothly handling bidirectional power flow anddesigning a robust distributed control algorithm implementation with minimalcommunication infrastructure. With the rise of the age of Internet of Things(IoT), sensors transmitting vital system data are being placed at differentpoints in the system. We still lack a systematic data-driven approach toleverage this information for monitoring, operating and providing diagnostic& prognostic evaluation of the grid. As a doctoral student, I wish to be in an institution wherein Ican incubate an idea, dedicatedly work to bring it into reality usingscientific integrity and communicate it to all.Stanford’s wide array of exceptional engineering programs and faculty are aperfect match for my multidisciplinary research in Electrical Engineering, Statisticsand Computer Science. I find the work of Prof.
Ram Rajagopal (Data driven energy systemmodeling) and Prof. Dimitry Gorinevsky (Industrial IoT) interesting andexceedingly aligned with my research interests. Stanford’s commitment towardsenergy & sustainability, eminent faculty, multiple centers/labs forinterdisciplinary research and industrial collaboration makes it the most idealplace to pursue my graduate career. I am confident that myunswerving dedication and strong academic background strengthened by relevantindustrial exposure will help me achieve my goals. After completing my Ph.
D.studies, I hope to pursue a career in industrial Research & Developmentsector to contribute towards developing innovative solutions for sustainableand efficient power generation and distribution.