Controlling the power distribution network with a deep reinforcement learning-based agent (CROSBI ID 701182)
Prilog sa skupa u zborniku | sažetak izlaganja sa skupa
Podaci o odgovornosti
Brčić, Mario ; Jurić, Mislav ; Damjanović, Ivana ; Sudić, Ivan
engleski
Controlling the power distribution network with a deep reinforcement learning-based agent
Controlling power distribution networks is becoming increasingly complex due to globalization, growing network size, the addition of new sources of uncertainty, rising consumption, and concurrent limitations on capacity expansion. Similar considerations can be applied to power distribution networks, supply chains, and information networks. This paper specifies and implements a deep learning-based agent to operate a simple power distribution network in a secure manner that prevents power outages. The agent is first trained by imitation learning from a heuristic agent and it is then further improved by reinforcement learning using proximal policy optimization.
deep reinforcement learning ; imitation learning ; distribution network
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
52-53.
2020.
nije evidentirano
objavljeno
Podaci o matičnoj publikaciji
KOI 2020 Book of Abstracts
Podaci o skupu
18th International Conference on Operational Research (KOI 2020)
predavanje
23.09.2020-25.09.2020
Šibenik, Hrvatska