Project title: Translating grid substations data into actionable information via unsupervised load monitoring
PI: Malcolm McCulloch
Extracting useful knowledge from the aggregated load at substations level plays an important role in the planning and operation of the distribution grid – enabling smart solutions for demand-side energy management as well as fault detection and recovery. This research aims to develop a learning-based method to extract information from existing grid measurements (active and reactive power, voltage and current). The novelty is in utilizing unsupervised pattern recognition and clustering techniques, thus easing the sensing and communication infrastructure requirements. Moreover, the correlation between different measurements will be leveraged to increase the accuracy of information extraction. The methodology will be applied to real substations’ load datasets from the Oxfordshire distribution system and tested in different simulated scenarios.
