Projektdetaljer
Beskrivelse
Abstract:
Compared with a single microgrid, although multi-microgrids has high energy resilience and stability, it is more sophisticated and facing more uncertainties for energy management, which is caused by coupled energy between MGs, multi-energy coupling, privacy of information as well as time-varying renewable source, loads and electricity price. Traditional model-based methods cannot fully satisfy the multi-microgrids energy management requirements due to a variety of reasons. As one of the data-driven approaches, multi-agent deep reinforcement learning technology shows state-of-the-art performance in many fields compared with data-driven methods. The project aims to achieve multi-objective optimization of multi-microgrids by investigating multi-microgrids energy management based on multi-agent deep reinforcement learning.
Funding:
China Scholarship Council
Compared with a single microgrid, although multi-microgrids has high energy resilience and stability, it is more sophisticated and facing more uncertainties for energy management, which is caused by coupled energy between MGs, multi-energy coupling, privacy of information as well as time-varying renewable source, loads and electricity price. Traditional model-based methods cannot fully satisfy the multi-microgrids energy management requirements due to a variety of reasons. As one of the data-driven approaches, multi-agent deep reinforcement learning technology shows state-of-the-art performance in many fields compared with data-driven methods. The project aims to achieve multi-objective optimization of multi-microgrids by investigating multi-microgrids energy management based on multi-agent deep reinforcement learning.
Funding:
China Scholarship Council
Status | Igangværende |
---|---|
Effektiv start/slut dato | 01/06/2021 → 31/05/2024 |
Fingerprint
Udforsk forskningsemnerne, som dette projekt berører. Disse etiketter er oprettet på grundlag af de underliggende bevillinger/legater. Sammen danner de et unikt fingerprint.