Real-time monitoring and control of distribution networks was traditionally deemed unnecessary because it had radial configuration, unidirectional power flows, and predictable load patterns. However, the fast growth of behind-the-meter generation, particularly solar photovoltaic, electric vehicles, and storage, is transitioning the distribution system from a passive load-serving entity to an active market-ready entity, whose reliable and secure operation necessitates real-time situational awareness. Synchrophasor measurement devices (SMDs) have been introduced in distribution systems to provide fast (sub-second) situational awareness by enabling time-synchronized state (voltage) estimation. However, due to the high cost of installation, the number of SMDs in a typical distribution network are not large enough to provide an independent assessment of the system state.
Modern distribution systems are being equipped with advanced metering infrastructure (AMI) in the form of smart meters. Hence, a combination of smart meter data with SMD data can be used to perform distribution system state estimation (DSSE). However, smart meters typically measure energy consumption from 15 minute to hourly time intervals and report their readings after a few hours or days. These two aspects make smart meter data unsuitable for real-time DSSE. Moreover, smart meter data is not time-synchronized by default which makes their direct integration with SMD data a statistical challenge.
Lastly, topology of a distribution network changes with time. This implies that impacts of changes in the configuration of the distribution system must be considered when performing DSSE. As such there is a need for a joint framework for identifying the topology and estimating the states at high-speeds in distribution systems that are unobservable by SMDs.
Researchers at Arizona State University and Cornell University have developed a deep learning-based approach for topology identification and distribution system state estimation (DSSE). Deep neural networks (DNNs) are trained for time-synchronized DNN-based topology identification and DSSE for systems that are incompletely observed by synchrophasor measurement devices (SMDs) in real-time.
Related publications:
State and Topology Estimation for Unobservable Distribution Systems Using Deep Neural Networks
Potential Applications:
- Distribution system monitoring
- Power utilities
Benefits and Advantages:
- Circumvents need for complete real-time observability for performing distribution system state estimation
- Performs topology identification in distribution systems at synchrophasor measurement device timescales (e.g., 30 samples per second)
- Numerical simulations indicate that this approach gives better DSSE accuracy with smaller number of SMDs in comparison to conventional linear state estimation