Call for Papers

The global transition towards carbon neutrality is driving the massive integration of renewable energy sources, which are predominantly interfaced with the grid through power electronic converters. This shift creates a paradigm of power-electronic-based power systems, presenting both opportunities and significant challenges. The inherent intermittency of renewables and the low-inertia characteristics of power electronics pose critical threats to system stability and power quality. This track aims to explore cutting-edge solutions at the intersection of power-electronic-based power systems and intelligent control technologies. We will focus on how advanced sensing technologies, robust communication and AI-driven control strategies can collectively address these challenges. Topics of interest include but are not limited to: AI-enabled stability assessment and forecasting; wide-bandgap semiconductor devices for high-efficiency power conversion; cyber-physical system security and communication protocols for grid control; intelligent fault detection and resilience enhancement; and real-time optimization of hybrid AC/DC microgrids. This track seeks to foster interdisciplinary dialogue among researchers in power electronics, communications, and artificial intelligence to pave the way for a smarter, more resilient, and sustainable power grid.

1. AI and Machine Learning for Power System Stability and Security Control;
2. Advanced Power Electronics and Intelligent Control with Wide-Bandgap Devices;
3. Communication Networks and Cybersecurity for Automated Grid Operations;
4. Intelligent Sensing, State Estimation, and Automated Diagnostics for Power Systems;
5. Grid-Following and Grid-Forming Control Strategies for Automated Grid Support;
6. Intelligent and Autonomous Control of AC/DC Microgrids with High Penetration of Renewables.

This track focuses on the applications of AI in climate change analysis, projection, and climate disaster prevention and mitigation. It covers the application of AI in both long-term climate change research and short-term micrometeorological forecasting. Topics of interest include, but are not limited to: AI and data-driven analysis of climate change trends and attributions, forecasting of micrometeorological disasters, early warning and prevention of extreme weather events, impact assessment of meteorological hazards, and interdisciplinary applications of atmospheric sciences. The column welcomes high-quality original research papers, case studies, and technical review articles from global researchers and engineers. It aims to advance the application of artificial intelligence in addressing climate change, foster interdisciplinary integration between meteorological science and other disciplines, and support the development of cross-disciplinary research.

1. Analysis of climate change trend based on AI for renewable energy forecasting and grid integration;
2. Climate change modeling based on AI;
3. Forecasting of micrometeorological disasters;
4. Early warning and prevention of extreme weather events;
5. Impact assessment of meteorological hazards;
6. Interdisciplinary applications of atmospheric sciences.

In recent years, the rapid advancement of machine learning (ML) has revolutionized numerous fields, from healthcare and finance to autonomous systems and power systems. However, the increasing complexity and black-box nature of many ML models have raised significant concerns regarding transparency, fairness, accountability, and trustworthiness. The lack of interpretability hinders the deployment of ML in high-stakes domains such as medical diagnosis and power system optimization, where understanding model decisions is critical. Interpretable machine learning aims to bridge this gap by developing methods that provide human-understandable explanations of model predictions and behaviors. Despite recent progress, challenges remain in balancing accuracy and interpretability, ensuring explanation fidelity, and meeting regulatory requirements. This special session focuses on the latest advances in machine learning interpretability, including novel explanation techniques, evaluation metrics, and applications in real-world scenarios. The purpose of this session is to bring together researchers and practitioners to share cutting-edge methodologies, discuss open problems, and foster collaboration toward building more transparent and reliable AI systems.

1. Interpretable model design for balancing transparency with predictive performance;
2. Post-hoc explanation techniques for black-box models after training;
3. Evaluation and benchmarking of explanations across different tasks and domains;
4. Integrating Causal Inference and Counterfactual Reasoning for Enhanced Interpretability;
5. Application of Explainable Machine learning in the Operation and Control of Modern Power Systems.

This track focuses on AI Applications in Power and Energy Systems, aiming to gather cutting-edge research, engineering practices and innovative solutions at the intersection of artificial intelligence and energy transformation. It covers intelligent decision-making, data-driven operation and maintenance, renewable energy prediction, smart grid optimization, carbon neutrality path planning and other key scenarios. The track welcomes high-quality papers, case studies and technical reviews, providing an academic exchange platform for global researchers and engineers to promote the deep integration of AI and power energy, and support the safe, efficient and low-carbon development of the energy industry.

1. AI for renewable energy forecasting and grid integration;
2. Advanced machine learning for energy modeling;
3. Large language model for smart energy systems;
4. AI for smart energy system control and operation;
5. Intelligent fault diagnosis, condition assessment and predictive maintenance;
6. AI for carbon neutrality, energy efficiency and low-carbon transition.