| NSF Org: |
ECCS Division of Electrical, Communications and Cyber Systems |
| Recipient: |
|
| Initial Amendment Date: | August 20, 2019 |
| Latest Amendment Date: | August 11, 2021 |
| Award Number: | 1936131 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Aranya Chakrabortty
ECCS Division of Electrical, Communications and Cyber Systems ENG Directorate for Engineering |
| Start Date: | September 15, 2019 |
| End Date: | August 31, 2024 (Estimated) |
| Total Intended Award Amount: | $333,340.00 |
| Total Awarded Amount to Date: | $364,340.00 |
| Funds Obligated to Date: |
FY 2020 = $16,000.00 FY 2021 = $15,000.00 |
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
500 S LIMESTONE LEXINGTON KY US 40526-0001 (859)257-9420 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
500 S. Limestone Lexington KY US 40526-0001 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | EPCN-Energy-Power-Ctrl-Netwrks |
| Primary Program Source: |
01002021DB NSF RESEARCH & RELATED ACTIVIT 01002122DB NSF RESEARCH & RELATED ACTIVIT |
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.041 |
ABSTRACT
The building sector is the largest energy consumer in the world, and in the United States it accounts for more than 40 percent of the total energy consumption and greenhouse gas emissions. Therefore, it is economically, socially, and environmentally important to reduce the energy consumption of this sector. The goal of this collaborative proposal is to develop novel machine learning based algorithms to address the problem of energy optimization at the building and district levels. These algorithms are integrated within a simulation framework that combines user behavior with the collaboration between buildings equipped with photovoltaic arrays, energy storage systems, and smart grid meters. The proposed research is expected to lay the foundation for robust multi-objective optimization for next generation district level distribution systems. The proposed research is closely integrated with a broad and diverse education and outreach plan aimed at inspiring young women to pursue careers in STEM through summer programs for middle school. Additionally, the project will train the next generation of engineers and researchers by involving graduate and undergraduate students through the proposed research as well as through classes taught by the PIs encompassing the proposed research methodologies. Overall, the outcomes of this proposal are expected to significantly advance the areas of energy optimization, electric power systems, and smart grid design, as well as to have a positive impact on the academic and industrial communities and society.
The project proposes and integrates, within the same software tool, novel machine learning models for complex user behavior at the individual building level, for energy load prediction and energy storage systems scheduling at the district level, and for cost reduction via energy peak spreading. These models are used to formulate and construct algorithmic solutions based on reinforcement learning, recurrent and deep neural networks, and deep reinforcement learning suitable for implementation in the future generation Virtual Power Plants. The methodologies employed for energy reduction and cost minimization include: 1) alter user behavior through personalized recommendations regarding changes in the appliance states (e.g., heating and air conditioning settings), 2) district-level scheduling of energy storage systems among buildings equipped with photovoltaic arrays and smart grid meters, and 3) building-level scheduling of energy consumption events for smart appliances equipped with smart Internet-of-Things controllers to take benefit of different energy prices.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
The primary outcomes of this project include the following:
1) The development of several machine learning (ML) models for hourly 24-hour ahead prediction of energy usage in heating, ventilation and air conditioning (HVAC) systems. These models were integrated within a custom co-simulation framework of buildings and distribution network and utilized to develop optimization algorithms for reducing the energy costs and usage of HVAC systems. These demand side management algorithms employed techniques based on game theory as well as on model predictive optimal control combined with Q-Learning reinforcement learning.
2) The development of several frameworks for i) optimization of energy sharing among prosumers; ii) incentive-based demand response with human-in-the-loop; and iii) appliance recognition through smart outlets with user-oriented stream-based learning.
3) The development of models and algorithms for HVAC energy component disaggregation and HVAC controls. Long short-term memory (LSTM) models were investigated for prediction of total and HVAC energy consumption as well as photovoltaic (PV) generation in buildings. The prediction models were used to develop combined control home energy management systems (HEMS) for HVAC, PV, and battery storage systems for behind-the-meter (BTM) demand response. Novel methods were developed to separate the HVAC dominant load component from the house load. The proposed algorithms are based on deep learning techniques and on the physical relationship between HVAC energy use and weather.
Research Publications
[1] R. Heidarykiany and C. Ababei, HVAC energy cost minimization via demand side management based on game theory optimization and deep learning based prediction, Elsevier Energy and AI, 2024.
[2] R. Heidarykiany and C. Ababei, Minimalistic LSTM models for next day hourly residential HVAC energy usage forecasting, IEEE EPEC, 2022.
[3] Rahman Heidarykiany, Deep machine learning algorithms for HVAC energy usage and cost optimization in smart grids, PhD Dissertation, July 2024, Doctor of Philosophy in Electrical and Computer Engineering, Marquette University.
[4] E. Casella, S. Silvestri, D. A. Baker, S. K. Das, A Human-Centered Power Conservation Framework based on Reverse Auction Theory and Machine Learning, ACM Transactions on Cyber-Physical Systems, 2024.
[5] A. Timilsina, S. Silvestri, P2P Energy Trading through Prospect Theory, Differential Evolution, and Reinforcement Learning, ACM Transactions on Evolutionary Learning and Optimization, 2023.
[6] J. Codispoti, A. R. Khamesi, N. Penn, S. Silvestri, E. Shin, Learning from Non-Experts: An Interactive and Adaptive Learning Approach for Appliance Recognition in Smart Homes, ACM Transactions on Cyber-Physical Systems, 2022.
[7] A. Timilsina, A. R. Khamesi, V. Agate, S. Silvestri, A Reinforcement Learning Approach for User Preference-aware Energy Sharing Systems, IEEE Transactions on Green Communications and Networking, 2021.
[8] A. Khamesi, S. Silvestri, D. Baker, A. De Paola, Perceived-Value Driven Optimization of Energy Consumption in Smart Homes, ACM Transactions on Internet of Things, 2020.
[9] R. Alden, A. Timilsina, S. Silvestri, D. Ionel, V2G Optimization for Dispatchable Residential Load Operation and Minimal Utility Cost, IEEE ITEC, 2023.
[10] E. Casella, A. R. Khamesi, S. Silvestri, D. A. Baker, S. K. Das, HVAC Power Conservation through Reverse Auctions and Machine Learning, IEEE PerCom, 2022.
[11] Alden, R. E., Gong, H., Ababei, C., and Ionel,D. M., LSTM Forecasts for Smart Home Electricity Usage, IEEE ICRERA 2020.
[12] Jones, E. S., Alden, R. E., Gong, H., Frye, A. G., Colliver, D., and Ionel, D. M., The Effect of High Efficiency Building Technologies and PV Generation on the Energy Profiles for Typical US Residences, IEEE ICRERA 2020.
[13] Alden, R. E., Gong, H., Jones., E. S., Ababei, C., and Ionel, D. M, Artificial Intelligence Method for the Forecast and Separation of Total and HVAC Loads with Application to Energy Management of Smart and NZE Homes, IEEE Access, 2021.
[14] Gong, H., Alden, R. E., Patrick, A., and Ionel, D. M., Forecast of Community Total Electric Load and HVAC Component Disaggregation through a New LSTM-Based Method, Energies, 2022.
[15] Gong, H., Alden, R. E., and Ionel, D. M., Stochastic Battery SOC Model of EV Community for V2G Operations Using CTA-2045 Standards, IEEE Transportation Electrification Conference and Expo (ITEC), 2022.
[16] Alden, R. E., Jones, E. S., Poore, S., Gong, H., Hadi, A. and Ionel, D. M., Digital Twin for HVAC Load and Energy Storage based on a Hybrid ML Model with CTA-2045 Controls Capability, IEEE ECCE 2022.
[17] Jones, E. S., Alden, R. E., Gong, H., and Ionel, D. M., Co-Simulation of Electric Power Distribution Systems and Buildings including Ultra-Fast HVAC Models and Optimal DER Control, Sustainability, 2023.
[18] Poore, S., Alden, R., Jones, E., and Ionel, D. M., Distribution System Optimal Operation of Smart Homes with Battery and Equivalent HVAC Energy Storage for Virtual Power Plant Controls, IEEE ECCE, 2023.
Last Modified: 09/30/2024
Modified by: Simone Silvestri
Please report errors in award information by writing to: awardsearch@nsf.gov.
