Bi-level Uncertainty-aware DER Aggregation Planning including Multi-period Load Forecasting with Electrical Transportation, Renewable Resources, and Community Batteries

We propose a new bi-level uncertainty-aware DER aggregation planning model to fill the existing gaps. It encompasses the trading of the aggregator in the electricity market at the upper level and the trading of end users (both Peer-to-Peer and Peer-to-Grid) at the lower level. Furthermore, the model incorporates a Blockchain-based energy trading ecosystem. Additionally, state-of-the-art deep learning and data mining methodologies will be used to develop innovative multi-step-ahead load forecasting models. These models will capture load temporal behaviors, including trends, seasonalities, and the electric vehicle component, while leveraging renewable generations like PV to represent the net load accurately. Our AI-based forecasting model and energy trading platform will undergo comprehensive testing with real-world data, showcasing their superiority over existing DER aggregation planning models. Furthermore, we aim to assess the technology readiness level for the industry by using GPS time-stamped real-time data from a testbed comprising a Real-Time Digital Simulator (RTDS) and dSPACE. Due to the anticipated significant impact on operational efficiency and business planning, the project receives direct support from KAHRAMAA through $45,000 USD in-kind support and the active participation of a KAHRAMAA Engineer as a PI with 45 effort days.

Qatar University