Deep Learning Based Forecasting-Aided State Estimation in Active Distribution Networks

Operating an active distribution network (ADN) in the absence of enough measurements, the presence of distributed energy resources, and poor knowledge of responsive demand behaviour is a huge challenge. This paper introduces systematic modelling of demand response behaviour which is then included in Forecasting Aided State Estimation (FASE) for better control of the network. There are several innovative elements in tuning parameters of FASE-based, demand profiling, and aggregation. The comprehensive case studies for three UK representative demand scenarios in 2023, 2035, and 2050 demonstrated the effectiveness of the proposed approach.