IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids
11-13 November 2020 // Virtual Conference

WS-1: Machine Learning and Big Data Analytics in Power Distribution Systems

WS-1: Machine Learning and Big Data Analytics in Power Distribution Systems

Aim and Scope

The recent decade has seen a paradigm shift in the planning and operation of power distribution grid, thanks to greater inclusion of household solar, electric vehicles as well as smart devices. The distribution grid is now considered as an ‘active’ participant of the smart grid ecosystem. The optimal coordination and control of distribution grid resources are enabled by the advanced metering and communication infrastructure that are deployed at the edge of the grid. The value of global energy big data analytics is pegged at a cumulative $20 billion by 2020. Indeed, the data-rich distribution grids provide incentives to develop novel physics-guided artificial intelligence (AI) techniques for diverse problems in grid control, optimization, event detection and hazard mitigation. Given the critical nature of power grid operations, new AI approaches for distribution networks must be cognizant of cyber-security risks associated with data curation and usage.

The proposed workshop aims at soliciting high-quality research articles that develop novel machine learning techniques to advance distribution grid efficiency, resilience and security. Original ideas bridging cross-disciplinary fields of signal processing, optimization, statistics, AI and energy systems are sought from prospective authors for presentations and publications in the workshop.

Potential topics of this workshop include but are not limited to the following:

  • Reinforcement learning and deep learning for cyber-physical distribution systems
  • Distributed and robust monitoring and optimization in distribution grids
  • Robust and data-driven control in distribution grids
  • Building automation and control
  • Fault diagnosis, localization and prognosis
  • Micro-PMU and smart meter big data analysis
  • Topology identification in distribution networks
  • Power restoration for smart distribution systems using machine learning
  • Utility and residential level load and renewable energy forecasting
  • Condition monitoring and asset management in distribution grids
  • Intelligent wide area monitoring, protection, control, and management
  • Privacy and security for machine learning in distribution grids