Climate change is a major challenge facing mankind and many countries worldwide have committed to reduce carbon emissions significantly in the following decades. The energy sector plays a major role to achieve the low carbon energy transition.
Within this context, it is necessary to develop a systematic approach to quantitatively evaluate carbon intensity and trace carbon flow from generation to consumption. Moreover, with the significant penetration of renewable energies at all voltage levels, it is vital to effectively handle the impact of the stochastic and intermittent nature of renewable energies on the power grid operations. As enabling technologies to achieve decarbonization, machine learning in modelling, planning, operation, and control of the whole energy chain from different energy mixes of electricity, thermal, and natural gas to end-users such as buildings, transportation, and manufacturing has become increasingly important. Meanwhile, the emerging carbon trading market and the local energy sharing have strong interaction with the conventional electricity market. It is therefore also essential to consider how to design the trading mechanism that can transfer carbon emission cost to end-users who is the underlying driver of the carbon emission; how to motivate the demand side prosumers to participate in carbon reduction. In addition, with the digitalization of the energy systems, huge amounts of data from various sources are available and enable machine learning applications in the energy industry. This may include carbon emission estimation, renewable energy output, and load forecasting, economic dispatch, demand-side management, cybersecurity, etc. Combining these data-driven technologies with model-based methods can achieve powerful performance to support low carbon energy transition.
This research topic aims to attract innovative ideas and interdisciplinary research to support low carbon energy transition assisted with machine learning. Topics of interest for this research topic include, but are not limited to, the following aspects:
• Novel measuring and computing methods for carbon emissions of multi-energy networks.
• Analysis and evaluation of low-carbon networks in all aspects of the energy chain from top to tail, including telecommunication, transportation network, etc.
• Intelligent modelling and optimization for low-carbon energy system planning, operation, and control.
• Data-driven customer behavior analysis and demand-side management.
• Data analytics of cyber-physical system security for low-carbon energy systems.
• Market mechanism design for supporting net-zero emissions transactive energy networks and future energy markets.
• Market design and emission trading for carbon and green hydrogen.
• Data-driven modelling, simulation, and forecasting technology for low-carbon energy systems.
Climate change is a major challenge facing mankind and many countries worldwide have committed to reduce carbon emissions significantly in the following decades. The energy sector plays a major role to achieve the low carbon energy transition.
Within this context, it is necessary to develop a systematic approach to quantitatively evaluate carbon intensity and trace carbon flow from generation to consumption. Moreover, with the significant penetration of renewable energies at all voltage levels, it is vital to effectively handle the impact of the stochastic and intermittent nature of renewable energies on the power grid operations. As enabling technologies to achieve decarbonization, machine learning in modelling, planning, operation, and control of the whole energy chain from different energy mixes of electricity, thermal, and natural gas to end-users such as buildings, transportation, and manufacturing has become increasingly important. Meanwhile, the emerging carbon trading market and the local energy sharing have strong interaction with the conventional electricity market. It is therefore also essential to consider how to design the trading mechanism that can transfer carbon emission cost to end-users who is the underlying driver of the carbon emission; how to motivate the demand side prosumers to participate in carbon reduction. In addition, with the digitalization of the energy systems, huge amounts of data from various sources are available and enable machine learning applications in the energy industry. This may include carbon emission estimation, renewable energy output, and load forecasting, economic dispatch, demand-side management, cybersecurity, etc. Combining these data-driven technologies with model-based methods can achieve powerful performance to support low carbon energy transition.
This research topic aims to attract innovative ideas and interdisciplinary research to support low carbon energy transition assisted with machine learning. Topics of interest for this research topic include, but are not limited to, the following aspects:
• Novel measuring and computing methods for carbon emissions of multi-energy networks.
• Analysis and evaluation of low-carbon networks in all aspects of the energy chain from top to tail, including telecommunication, transportation network, etc.
• Intelligent modelling and optimization for low-carbon energy system planning, operation, and control.
• Data-driven customer behavior analysis and demand-side management.
• Data analytics of cyber-physical system security for low-carbon energy systems.
• Market mechanism design for supporting net-zero emissions transactive energy networks and future energy markets.
• Market design and emission trading for carbon and green hydrogen.
• Data-driven modelling, simulation, and forecasting technology for low-carbon energy systems.
