Renewable Generation

Renewable energy generation, characterized by its intermittent and unpredictable nature, presents significant challenges for grid stability and efficient energy management. Current research focuses on improving forecasting accuracy using advanced machine learning models, such as deep neural networks, transformer architectures, and hybrid models combining machine learning with physical models, to predict solar and wind power output at various time scales (from nowcasting to long-term scenarios). These advancements are crucial for optimizing grid operations, integrating energy storage effectively, and reducing reliance on fossil fuels, ultimately contributing to a more sustainable and reliable energy system.

Papers

August 13, 2022

Feasibility Layer Aided Machine Learning Approach for Day-Ahead Operations
Arun Venkatesh Ramesh, Xingpeng Li
Machine Learning Renewable Generation Mixed Integer Linear Learning Feasibility Machine Scheduling Security Constrained Unit Commitment

August 1, 2022

Performance Comparison of Deep RL Algorithms for Energy Systems Optimal Scheduling
Hou Shengren, Edgar Mauricio Salazar, Pedro P. Vergara, Peter Palensky
Deep Reinforcement Learning Deep RL Performance Comparison Renewable Generation

July 15, 2022

A two-step machine learning approach to statistical post-processing of weather forecasts for power generation
Ágnes Baran, Sándor Baran
Constructive Approach Ensemble Method Post Processing Weather Forecasting Ensemble Forecast Renewable Generation Ensemble Weather Global Horizontal Irradiance

April 10, 2022

Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching
Xinhang Li, Zihao Li, Nan Yang, Zheng Yuan, Qinwen Wang, Yiying Yang, Yupeng Huang, Xuri Song, Lei Li, Lin Zhang
Renewable Energy Confidence Estimation Renewable Generation

February 8, 2022

Robust, Deep, and Reinforcement Learning for Management of Communication and Power Networks
Alireza Sadeghi
Reinforcement Learning Native Robustness Robust Version Timely Communication Cyber Physical Renewable Generation Power Network Distributional Uncertainty

Renewable Generation

Papers

Feasibility Layer Aided Machine Learning Approach for Day-Ahead Operations

Performance Comparison of Deep RL Algorithms for Energy Systems Optimal Scheduling

A two-step machine learning approach to statistical post-processing of weather forecasts for power generation

Confidence Estimation Transformer for Long-term Renewable Energy Forecasting in Reinforcement Learning-based Power Grid Dispatching

Robust, Deep, and Reinforcement Learning for Management of Communication and Power Networks