Research
Prof. Dipti Srinivasan's research focuses on the application of Artificial Intelligence, machine learning, and computational intelligence to complex challenges in modern power and energy systems. Her work addresses renewable energy integration, smart grid operation, demand-side management, microgrid coordination, electric vehicle integration, and uncertainty modelling for decision-making.
The emphasis on deployable, scalable, and data-driven solutions that bridge theory and practice. Her work has led to high-impact publications in leading IEEE journals and multiple best paper and algorithm awards at major international conferences.
Key Research Areas
- Artificial Intelligence for Smart Grids
- Renewable Energy Forecasting and Grid Integration
- Demand-Side Management and Energy Optimization
- Microgrid and Distributed Energy System Management
- Uncertainty Modelling and Decision-Making
- Evolutionary and Multi-Objective Optimization
Research Projects
Prof. Dipti Srinivasan leads and collaborates on interdisciplinary research projects that advance AI-enabled solutions for smart grids, renewable energy integration, and sustainable energy systems. Her projects span fundamental research, applied innovation, and real-world deployment, in close collaboration with industry and national agencies.
Current and Recently Completed Projects (Selected):
Lightning Fast Photonic Neural Processor for AI
Developing Critical Intelligent Modules for Large-Scale Vehicle-to-Grid (V2G) Implementation
AI-driven optimization and decision-making frameworks to enable scalable and reliable V2G integration.
AIoT-Enabled Smart Grid Applications for Sustainable and Resilient Digital Ports (ASGARD Project)
Intelligent sensing, forecasting, and energy management solutions for large-scale, mission-critical infrastructures.
AI-Based Automated Demand-Side Management for Commercial and Industrial Systems
Data-driven control and optimization methods for energy efficiency and cost-effective operation.
Advanced Solar Power Forecasting for Safe and Reliable Grid Integration
Uncertainty-aware forecasting models to support high-penetration photovoltaic systems.
Energy Storage System Testbed for Grid Applications (Redox Flow Battery)
Performance evaluation and operational strategies for grid-scale energy storage.
Data-Centric Transfer Optimization for High-Productivity Workforces in the Internet Era
AI-enabled optimization techniques for complex, data-intensive systems.