Artificial intelligence enabled smart control for advanced energy management systems in modern microgrids
Technical Outline of the Session and Topics:
Microgrid works as a vital building block in modern power system and plays an inevitable role to realize zero carbon emission. It is now experiencing a massive transition from its conventional form to a more complicated architecture which incorporates heterogenous renewable generations (PVs and wind turbines, etc.), various energy storage modules (supercapacitors, lithium-ion batteries, and flow batteries, etc.), synchronous generators, power electronic-based loads, and motor drives. Moreover, IOT appliances such as sensors and communication links allow for additional information flow hanging over the hardware layer. The information flow could be used to regulate any possible dynamic states determined in the physical layer, whereas the physical layer would reciprocally exert impacts over the control and optimization algorithms happening in the IOT layer. In this sense, the complex interactions between the energy flow in hardware layer and information flow in the communication layer would cause the overall energy management of microgrids more challenging. On the other hand, many of cosmopolitans, including Singapore, have been moving one step further to embrace artificial intelligence (AI) era. The powerful fitting capabilities have render AI to be ubiquitously applied to real-life engineering scenarios. But the benefits of extensive implementations of AI and its derivative technologies to microgrid energy management are still underplayed in many ways, which however should be more pointedly investigated. This special session will be led by researchers in EDF Lab Singapore and Newcastle University in Singapore (NUiS). The session encourages the creative ideas and cutting-edge research works from both academia and industry.
The topics of interest include but not are limited to the following:
- Advance dynamic control and learning based control for in DC microgrids, AC microgrids, hybrid AC/DC microgrids, and microgrid communities.
- Reinforcement learning driven controller designs and advanced optimization approaches for more economic energy management systems.
- Artificial intelligence framework and design for smart control of E-mobility involved regional microgrid systems.
- Supervised learning, unsupervised learning, and reinforcement learning for new feature developments in power electronics and power managements of microgrids.