Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 17, Issue 7, Pages 4480-4491Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.3016336
Keywords
Energy sharing; energy storage (ES); long short-term memory (LSTM) network; photovoltaic (PV) generation; pricing method; Q-learning algorithm; residential building cluster (RBC); Stackelberg game
Categories
Funding
- National Natural Science Foundation of China [71971183, 51907056]
- Singtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU) - Singapore Government through the Industry Alignment Fund -Industry Collaboration Projects Grant
Ask authors/readers for more resources
This article proposes a novel machine learning based data-driven pricing method for sharing rooftop photovoltaic generation and energy storage in an electrically interconnected residential building cluster. The energy sharing process is modeled by the leader-follower Stackelberg game, with the owner of the rooftop PV system responsible for pricing self-generated PV energy and operating ES devices. A long short-term memory network based rolling-horizon prediction function is developed to track stochastic PV panel outputs, and a Q-learning based decision-making process is used to find near-optimal pricing strategies. Simulation results confirm the effectiveness of the approach in solving energy sharing problems with partial or uncertain information.
In this article, a novel machine learning based data-driven pricing method is proposed for sharing rooftop photovoltaic (PV) generation and energy storage in an electrically interconnected residential building cluster (RBC). In the studied problem, the energy sharing process is modeled by the leader-follower Stackelberg game where the owner of the rooftop PV system is responsible for pricing self-generated PV energy and operating ES devices. Meanwhile, local electricity consumers in the RBC choose their energy consumption with the given internal electricity prices. To track the stochastic rooftop PV panel outputs, the long short-term memory network based rolling-horizon prediction function is developed to dynamically predict future trends of PV generation. With system information, the predicted information is fed into a Q-learning based decision-making process to find near-optimal pricing strategies. The simulation results verify the effectiveness of the proposed approach in solving energy sharing problems with partial or uncertain information.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available