Search

Electrification for commercial vehicle fleets presents opportunity to cut emissions, reduce fuel costs, and improve operational metrics. However, infrastructure limitations in urban areas often inhibit the ability to charge a significant number of electric vehicles, especially under one roof. This paper highlights a novel controls approach developed at GE Global Research in conjunction with Columbia University to fulfill the stated needs for intelligent charging of a commercial fleet of electric vehicles. This novel approach combines traditional control techniques with machine learning algorithms to adapt to customer behavior over time. The stated controls system is designed to regulate the charging rate of multiple electric vehicle supply equipment devices (EVSEs) to facilitate cost-optimal charging subject to past and predicted building load, vehicle energy requirements, and current conditions. In this embodiment, the system is primarily designed to mitigate electric demand charges that may otherwise occur due to charging at inopportune times. The system will be deployed at a New York City FedEx Express delivery depot in partnership with the local utility, Consolidated Edison Company of New York.

A high percentage of newly-constructed commercial office buildings experience energy consumption that exceeds specifications and system failures after being put into use. This problem is even worse for older buildings. We present a new approach, ‘predictive building energy optimization’, which uses machine learning (ML) and automated online evaluation of historical and real-time building data to improve efficiency and reliability of building operations without requiring large amounts of additional capital investment. Our ML approach uses a predictive model to generate accurate energy demand forecasts and automated analyses that can guide optimization of building operations. In parallel, an automated online evaluation system monitors efficiency at multiple stages in the system workflow and provides building operators with continuous feedback. We implemented a prototype of this application in a large commercial building in Manhattan. Our predictive machine learning model applies Support Vector Regression (SVR) to the building's historical energy use and temperature and wet-bulb humidity data from the building's interior and exterior in order to model performance for each day. This predictive model closely approximates actual energy usage values, with some seasonal and occupant-specific variability, and the dependence of the data on day-of-the-week makes the model easily applicable to different types of buildings with minimal adjustment. In parallel, an automated online evaluator monitors the building's internal and external conditions, control actions and the results of those actions. Intelligent real-time data quality analysis components quickly detect anomalies and automatically transmit feedback to building management, who can then take necessary preventive or corrective actions. Our experiments show that this evaluator is responsive and effective in further ensuring reliable and energy-efficient operation of building systems.

Power companies can benefit from the use of knowledge discovery methods and statistical machine learning for preventive maintenance. We introduce a general process for transforming historical electrical grid data into models that aim to predict the risk of failures for components and systems. These models can be used directly by power companies to assist with prioritization of maintenance and repair work. Specialized versions of this process are used to produce (1) feeder failure rankings, (2) cable, joint, terminator, and transformer rankings, (3) feeder Mean Time Between Failure (MTBF) estimates, and (4) manhole events vulnerability rankings. The process in its most general form can handle diverse, noisy, sources that are historical (static), semi-real-time, or real-time, incorporates state-of-the-art machine learning algorithms for prioritization (supervised ranking or MTBF), and includes an evaluation of results via cross-validation and blind test. Above and beyond the ranked lists and MTBF estimates are business management interfaces that allow the prediction capability to be integrated directly into corporate planning and decision support; such interfaces rely on several important properties of our general modeling approach: that machine learning features are meaningful to domain experts, that the processing of data is transparent, and that prediction results are accurate enough to support sound decision making. We discuss the challenges in working with historical electrical grid data that were not designed for predictive purposes. The “rawness” of these data contrasts with the accuracy of the statistical models that can be obtained from the process; these models are sufficiently accurate to assist in maintaining New York City's electrical grid.

Ranking problems arise in a wide range of real world applications where an ordering on a set of examples is preferred to a classification model. These applications include collaborative filtering, information retrieval and ranking components of a system by susceptibility to failure. In this paper, we present an ongoing project to rank the underground primary feeders of New York City's electrical grid according to their susceptibility to outages. We describe our framework and the application of machine learning ranking methods, using scores from Support Vector Machines (SVM), RankBoost and Martingale Boosting. Finally, we present our experimental results and the lessons learned from this challenging real-world application.

Electric vehicles are not penetrating the market as quickly as expected. This is due to limited driving range, time required to recharge a battery, and lack of charging infrastructure in most metropolitan cities. We propose a charge sharing network in which we use inductive power transfer to wirelessly exchange charge between vehicles. In our network, vehicles that have excess charge to share, can sell charge to vehicles needing charge to reach their destination. In this paper, we describe a game theoretic approach to offering incentives for electric vehicles to participate in the charge sharing network. We utilize Nash Bargaining theory to show that participation in the network can yield profits for the seller driving to their destination and that we can increase the number of cars reaching their destination without needing to stop for recharging.