Track 2: Application of Machine Learning
in Power Systems
With the global transition to new power systems characterized by high renewable energy penetration and power electronics, traditional methods struggle to meet demands for real-time responsiveness and adaptability. Machine learning (ML) has become indispensable, offering data-driven solutions to overcome these bottlenecks.
This track showcases cutting-edge research on ML applications in power systems, covering reinforcement learning for dispatch/control, optimization theory integration, AI-based source/load forecasting, data-driven market clearing, detection/sensing/state estimation, large model-driven decision-making, and model-data hybrid methods. It aims to foster knowledge exchange between researchers and practitioners, advancing ML-enabled technologies for efficient, reliable, and resilient power system operation.
SCOPE & TOPICS
We seek original completed and unpublished work not currently under review by any other journal/magazine/conference.
- · Application of reinforcement learning in power system dispatch and control
- · Application of optimization theory in power system operation and control
- · Power system source and load forecasting technology based on artificial intelligence
- · Data-driven electricity market clearing technology
- · Data-driven detection, sensing, and state estimation technology for power systems
- · Decision-making technology for power systems driven by large models
- · Model-data hybrid decision-making method and its application in power systems
- · Other topics relevant to the application of machine learning in power systems