Multi-Area Distribution System State Estimation Using Decentralized Physics-Aware Neural Networks

Abstract

The development of active distribution grids requires more accurate and lower computational cost state estimation. In this paper, the authors investigate a decentralized learning-based distribution system state estimation (DSSE) approach for large distribution grids. The proposed approach decomposes the feeder-level DSSE into subarea-level estimation problems that can be solved independently. The proposed method is decentralized pruned physics-aware neural network (D-P2N2). The physical grid topology is used to parsimoniously design the connections between different hidden layers of the D-P2N2. Monte Carlo simulations based on one-year of load consumption data collected from smart meters for a three-phase distribution system power flow are developed to generate the measurement and voltage state data. The IEEE 123-node system is selected as the test network to benchmark the proposed algorithm against the classic weighted least squares and state-of-the-art learning-based DSSE approaches. Numerical results show that the D-P2N2 outperforms the state-of-the-art methods in terms of estimation accuracy and computational efficiency.

Exploring regression models to enable monitoring capability of local energy communities for self‐management in low‐voltage distribution networks

“…Regression models mathematically formulate the correlation between one output variable and one or multiple input variables, afterwards allowing to estimate the output variable from the input variables. Regression models are widely employed for load forecasting [19,21,22], RES generation forecasting [23,24], power system state estimation [25,26], and supporting network operation [27,28]. However, to the authors' best knowledge, there have been no studies on regression models in transformer congestion monitoring that take into account the measurements from end-users' SMs.…”

Advanced and Complex Energy Systems Monitoring and Control: A Review on Available Technologies and Their Application Criteria

“…Measurement approaches and methodologies [34][35][36][37][38][39][40][41][42][43][44][45][46][47][48][49][50][51], such as sensor allocations and related protocols, mainly involve data processing techniques. Different data analysis tools can be applied to extract more information, optimizing energy systems such as predictions, parameter classifications, and possible unbalanced energy conditions.…”

Operation Orchestration of Local Energy Communities through Digital Twin: A Review on suitable Modeling and Simulation Approaches

“…The proposed approach unifies the consumption modeling for MV and LV networks, simulating active power consumption scenarios in flexible time horizons for a whole year. Based on a one-year smart meter data, the power flow analysis generates training data sets for a data-driven state estimation for LEC requiring more accurate and lower computational burden in [46]. The state estimation was designed based on the physical connections of the distribution network and the position of the phasor measurement unit (PMU).…”