Engineering Commons^™

Artificial Intelligence Method For The Forecast And Separation Of Total And Hvac Loads With Application To Energy Management Of Smart And Nze Homes, Rosemary E. Alden, Huangjie Gong, Evan S. Jones, Cristinel Ababei, Dan M. Ionel

Electrical and Computer Engineering Faculty Publications

Separating the HVAC energy use from the total residential load can be used to improve energy usage monitoring and to enhance the house energy management systems (HEMS) for existing houses that do not have dedicated HVAC circuits. In this paper, a novel method is proposed to separate the HVAC dominant load component from the house load. The proposed method utilizes deep learning techniques and the physical relationship between HVAC energy use and weather. It employs novel long short-term memory (LSTM) encoder-decoder machine learning (ML) models, which are developed based on future weather data input in place of weather forecasts. In …

Virtual Power Plant Control For Large Residential Communities Using Hvac Systems For Energy Storage, Huangjie Gong, Evan S. Jones, Rosemary E. Alden, Andrew G. Frye, Donald G. Colliver, Dan M. Ionel

Power and Energy Institute of Kentucky Faculty Publications

Heating, ventilation, and air-conditioning (HVAC) systems use the most electricity of any household appliance in residential communities. HVAC system modeling facilitates the study of demand response (DR) at both the residential and power system levels. In this article, the equivalent thermal model of a reference house is proposed. Parameters for the reference house were determined based on the systematic study of experimental data obtained from fully instrumented field demonstrators. Energy storage capacity of HVAC systems is calculated and an equivalent state-of-charge is defined. The uniformity between HVAC systems and battery energy storage system is demonstrated by DR control. The aggregated …

Generalized Energy Storage Model-In-The-Loop Suitable For Energy Star And Cta-2045 Control Types, Huangjie Gong, Evan S. Jones, A. H. M. Jakaria, Aminul Huque, Ajit Renjit, Dan M. Ionel

Power and Energy Institute of Kentucky Faculty Publications

The paper proposes a generalized energy storage (GES) model for battery energy storage systems (BESS), electric water heaters (EWH) and heating, ventilation, and air-conditioning (HVAC) systems. The analogies, including state of charge versus water temperature differential, are identified and explained, and models-in-the-loop (MIL) are introduced, which are compatible with the Energy Star and CTA-2045 general specifications and command types. Emphasis is placed on the proposed EWH model as it needfully fulfills a gap in present literature. The corresponding MIL has been implemented in the DER integration testbed, which was originally developed by EPRI, and satisfactorily validated against experimental results. A …

Power Factor And Reactive Power In Us Residences – Survey And Energyplus Modeling, Hope C. Anderson, Abdullah Al Hadi, Evan S. Jones, Dan M. Ionel

Power and Energy Institute of Kentucky Faculty Publications

Electric power systems are experiencing a growing number of electronic loads in the residential sector as modern appliance technology progresses, and it has become increasingly more important to consider the total power factor (PF) of residential communities. This paper provides a survey based on literature and publicly available information of typical appliance PF values and effects at the residential level as well as a discussion on appliance energy use and corresponding operation schedules. A procedure for the calculation of equivalent PF is proposed and exemplified with minutely experimental data at 15-minute and hourly time intervals, which correspond to smart metering …

Artificial Intelligence-Based Short-Term Electric Load Forecasts For Experimental Smart Homes Including Hvac And Pv Components, Rosemary E. Alden, Cristinel Ababei, Dan M. Ionel

Power and Energy Institute of Kentucky Presentations

Problem Formulation

• To predict electric load of the total average power as well as individual components for two residencies from experimental data
• Individual residential forecasting is difficult due to high variability of appliance usage and random human behavior influences
• Separate the HVAC load from total load as a desired profile using weather relationship and minimum HVAC load at night
• Data driven approach to reduce the amount of information about the home required

Peak Reduction And Long Term Load Forecasting For Large Residential Communities Including Smart Homes With Energy Storage, Huangjie Gong, Vandana Rallabandi, Michael L. Mcintyre, Eklas Hossain, Dan M. Ionel

Power and Energy Institute of Kentucky Faculty Publications

Domestic load profiles in the residential sectors are being modified with the adoption of smart home management systems and solar generation. In addition, houses with rooftop PV behave like local generators, contributing to the growth of the penetration of PV energy. Hence, the demand for power is declining day by day. However, the increasing PV penetration causes technical challenges for the power system, such as the “duck curve”. This can be addressed through home energy management (HEM) techniques including peak shaving, load shifting with smart home devices. In this regard, electric water heaters (EWH), with high thermal mass and being …