ICIEA 2025 Special Session
SS22: Artificial Intelligence in Smart Grid: Renewable Energy Integration, Smart Grid Management, Demand Response and Market Dynamics and Storage Economics
Organized by:
Organizer 1: Juan Yan
Email: juanyan@ahu.edu.cn
Affiliation: Anhui University, China
Organizer 2: Xiandong Xu
Email: xux27@tju.edu.cn
Affiliation: Tianjin University, China
Organizer 3: Zhile Yang
Email: zl.yang@siat.ac.cn
Affiliation: University of Chinese Academy of Sciences, China
Organizer 4: Dajun Du
Email: ddj@i.shu.edu.cn
Affiliation: Shanghai University, China
Organizer 5: Bowen Zhou
Email: zhoubowen@ise.neu.edu.cn
Affiliation: North East University, China
Organizer 6: Ning Zhang
Email: zhangning@ahu.edu.cn
Affiliation: Anhui University, China
Session Abstract:
AI is a cornerstone of the transition to smart, sustainable electricity systems, offering solutions to many problems including: renewable energy integration, smart grid management, Electric Vehicles (EVs) and Microgrids, Market Dynamics and Regulation, Cybersecurity, Demand Response and Consumer Engagement etc. However, challenges persist such as:
- How to construct a hybrid data-physics-driven large-scale meteorological-electric model for power systems
- How to achieve security-certified and trusted applications of AI large models in critical domains of power systems
- How to ensure safe and stable operation of high-penetration renewable energy power systems under carbon neutrality goals
- How to leverage market mechanisms for integrated optimization of energy and power systems in terms of security, low-carbon, and economic balance
- How to achieve secure and reliable replacement of conventional energy with renewables under energy transition and market-oriented contexts
- How to enable economically reliable power transmission from large-scale renewable energy bases
- How to enhance high-end, intelligent, and green characteristics of power transmission and transformation equipment to meet the requirements of new-type power systems
This session targets AI innovations that harmonize technical advancements with socio-economic governance, enabling scalable decarbonization while ensuring grid reliability and fair market participation. We encourage contributions that highlight theoretical advancements, practical applications, and case studies demonstrating the potential of these technologies to enhance efficiency, reliability, and sustainability in modern power electronic systems.
Background and Justification:
This session aims to bridge technical gaps such as:
- Lack of multi-timescale optimization models integrating renewable forecasts with grid operations
- Limited AI methods addressing DER heterogeneity and communication latency,
- Lack of scalable AI models for multi-type storage (e.g., batteries, flywheels, hydrogen) coordination.
- Limited AI architectures balancing computational efficiency with interpretability (e.g., hybrid symbolic-AI) etc
- Lack of innovative hybrid AI architectures (e.g., digital twins + RL) for lifecycle management of storage assets
By integrating cutting-edge technologies, this session contributes to promoting the renewable energy transmission, storage and marketing by innovative AI models.
Information of papers
We invite original research and comprehensive reviews on, but not limited to, the following topics:
1 Renewable Energy Integration
- AI Forecasting: Probabilistic deep learning for solar/wind generation and net-load prediction.
- Dynamic Optimization: Hybrid physics-informed ML models for grid stability under high renewable penetration.
- Grid-Forming Control: Reinforcement learning (RL) for inverter-based resource coordination in hybrid AC/DC grids.
2 Smart Grid Management
- Resilient Operation: Explainable AI (XAI) for fault detection, islanding, and self-healing under cyberattacks.
- Resource Orchestration: Federated learning for privacy-preserving DER (distributed energy resource) coordination.
3 Demand Response & Consumer Engagement
- Behavioral AI: Nudging strategies for residential/commercial load flexibility via reinforcement learning.
- Personalized DR: Clustering and reinforcement learning for adaptive pricing and incentive design.
- Prosumer-Centric Models: Blockchain-AI platforms for peer-to-peer energy trading with dynamic contracts.
4 Market Dynamics, Regulation, and Storage Economics
- AI-Driven Storage Valuation: Multi-agent models for ESS participation in energy, capacity, and ancillary markets.
- Policy-AI Alignment: Regulatory sandbox designs for AI-managed storage-as-a-service (STaaS) business models.
- Cross-Sector Coupling: Storage-enabled carbon-aware pricing using AI-powered grid-to-X (G2X) frameworks.