Deep Statistical Solver for Distribution System State Estimation
نویسندگان
چکیده
Implementing accurate Distribution System State Estimation (DSSE) faces several challenges, among which the lack of observability and high density distribution system. While data-driven alternatives based on Machine Learning models could be a choice, they suffer in DSSE because labeled data. In fact, measurements system are often noisy, corrupted, unavailable. To address these issues, we propose Deep Statistical Solver for (DSS 2 ), deep learning model graph neural networks (GNNs) that accounts network structure governing power flow equations problem. DSS is GNN leverages hypergraphs to as into deep-learning algorithm represent heterogeneous components systems. A weakly supervised approach put forth train : by enforcing output equations, force respect physics This strategy enables from noisy alleviates need ideal Extensive experiments with case studies IEEE 14-bus, 70-bus, 179-bus showed outperforms conventional Weighted Least Squares accuracy, convergence, computational time while being more robust erroneous, missing measurements. The achieves competing, yet lower, performance compared rely unrealistic assumption having all true labels.
منابع مشابه
Modified Weighted Least Squares Method to Improve Active Distribution System State Estimation
The development of communications and telecommunications infrastructure, followed by the extension of a new generation of smart distribution grids, has brought real-time control of distribution systems to electrical industry professionals’ attention. Also, the increasing use of distributed generation (DG) resources and the need for participation in the system voltage control, which is possible ...
متن کاملResilient Configuration of Distribution System versus False Data Injection Attacks Against State Estimation
State estimation is used in power systems to estimate grid variables based on meter measurements. Unfortunately, power grids are vulnerable to cyber-attacks. Reducing cyber-attacks against state estimation is necessary to ensure power system safe and reliable operation. False data injection (FDI) is a type of cyber-attack that tampers with measurements. This paper proposes network reconfigurati...
متن کاملMulti-objective Measurement Devices Allocation Using State Estimation in Distribution System
Allocation of measurement devices is a necessity of distribution system which is an application of state estimation. In this paper, the problem of active and reactive measurement devices is modeling using a multi-objective method. The objectives of the problem are to minimize the use of measurement devices, increase in state estimation output, improve the state estimation quality and reduce cos...
متن کاملMeter Placement Impact on Distribution System State Estimation
This paper discusses the criteria that must be considered for the placement of new measurements in distribution networks in order to obtain the best state estimation performances. A better network state monitoring will improve all the other network management tasks. The impacts of the measurement device placement on the state estimation accuracy and on the bad data detection capabilities are il...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Power Systems
سال: 2023
ISSN: ['0885-8950', '1558-0679']
DOI: https://doi.org/10.1109/tpwrs.2023.3290358