Statistical Machine Learning for Uncertainty Modelling in Energy Systems
1China Agricultural University, Beijing, China
2Concordia University, Montreal, Canada
3Zhejiang University, Hangzhou, China
Statistical Machine Learning for Uncertainty Modelling in Energy Systems
Description
The development of distributed renewable energy, such as photovoltaic power generation and wind power generation, makes traditional energy systems cleaner and is of great significance for reducing carbon emissions. However, variations in weather can affect distributed renewable energy power generation and the uncertainty of output creates uncertainty in energy systems. Photovoltaic and wind power output fluctuates greatly and has strong randomness, which brings a series of problems in control, scheduling, and planning. The energy systems with high permeability distributed renewable energy are high-dimensional, have nonlinear dynamics of large-scale complex systems, and finding the optimal solution to the uncertainty model is a difficult problem. Statistical learning, also known as statistical machine learning, involves probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, machine learning, and other disciplines. It is a science that focuses on probabilistic statistical models constructed by computers. To address the uncertainty of distributed renewable energy, statistical machine learning has moved to the mainstream of uncertainty modeling in energy systems.
This Special Issue aims to bring together research that discusses and highlights the statistical machine learning technologies for uncertainty modeling in energy systems, which enables the functions of planning, operation, and control in uncertain environments.
Potential topics include but are not limited to the following:
- Probabilistic photovoltaic generation forecasting
- Probabilistic modeling of photovoltaic systems
- Planning of photovoltaic power generation
- Uncertainty quantification and scenario generation of photovoltaic
- Probabilistic power flow calculation considering uncertainty
- Probabilistic scheduling of new energy systems
- Probabilistic load modeling for power system expansion planning
- Stochastic weather simulation and climate models
- Deep learning for power system data analysis
- Applications of reinforcement learning in energy systems
- Machine learning in agriculture and rural microgrid
- Optimization and machine learning in energy harvesting system