TY - GEN
T1 - Optimization of Aggregated Energy Resources using Sequential Decision Making
AU - Roy, Trishant
AU - Jana, Aryyama K.
AU - Hedman, Kory W.
N1 - Funding Information: ACKNOWLEDGMENT This work was funded by the Power Systems Engineering Research Center (PSERC), an Industry-University Cooperative Research Center focusing on innovations in modern electric energy infrastructure. The project ID associated with this work is M-44. Publisher Copyright: © 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Due to the limited non-renewable sources and focus on clean energy in the contemporary world, most governments are focusing more on renewable energy sources for electrical power. However, the unpredictable variations in the renewable energy source itself can pose serious threats to the grid's operation unless managed. A plausible solution is to manage a combination of resources that can complement each other's generation to meet the total demand reliably. In this paper, we consider a utility with solar energy as a renewable resource, battery for storage, and interaction with the electrical grid. The objective is to develop a decision-making approach to help the utilities better manage their resources to decide when and how to dispatch battery, solar power, and how much electricity to buy/sell from the grid. Here, the management problem has been formulated as Markov Decision Process. We have implemented and compared the performance of a conventional approach of dynamic programming and a Q-learning approach to solve the optimization problem. The advantages and disadvantages of these approaches are also highlighted in this paper.
AB - Due to the limited non-renewable sources and focus on clean energy in the contemporary world, most governments are focusing more on renewable energy sources for electrical power. However, the unpredictable variations in the renewable energy source itself can pose serious threats to the grid's operation unless managed. A plausible solution is to manage a combination of resources that can complement each other's generation to meet the total demand reliably. In this paper, we consider a utility with solar energy as a renewable resource, battery for storage, and interaction with the electrical grid. The objective is to develop a decision-making approach to help the utilities better manage their resources to decide when and how to dispatch battery, solar power, and how much electricity to buy/sell from the grid. Here, the management problem has been formulated as Markov Decision Process. We have implemented and compared the performance of a conventional approach of dynamic programming and a Q-learning approach to solve the optimization problem. The advantages and disadvantages of these approaches are also highlighted in this paper.
KW - Battery storage
KW - Q-learning
KW - dynamic programming
KW - sequential decision making
UR - http://www.scopus.com/inward/record.url?scp=85147246368&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85147246368&partnerID=8YFLogxK
U2 - 10.1109/NAPS56150.2022.10012186
DO - 10.1109/NAPS56150.2022.10012186
M3 - Conference contribution
T3 - 2022 North American Power Symposium, NAPS 2022
BT - 2022 North American Power Symposium, NAPS 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 North American Power Symposium, NAPS 2022
Y2 - 9 October 2022 through 11 October 2022
ER -