Multi-Fidelity Gaussian Process for Distribution System Voltage Probabilistic Estimation with PVs
The increasing penetration of behind-the-meter PVs causes challenges to maintain voltage security due to the lack of distribution system visibility. This paper proposes a nonlinear autoregressive Gaussian process (NARGP) approach to fuse limited number of SCADA/AMI data together with historical pseudo measurements for distribution node voltage probabilistic estimation. The high-fidelity SCADA data are fused with the low-fidelity AMI and pseudo measurements by the autoregressive algorithm embedded in the Gaussian process. This allows us to use multi-fidelity data to achieve entire distribution system voltage visibility. Numerical results carried out on the IEEE 123node system demonstrate that the NARGP method is able to obtain high accuracy in estimating bus voltage and quantifying estimation uncertainties as compared to other approaches.
- Research Organization:
- National Renewable Energy Laboratory (NREL), Golden, CO (United States)
- Sponsoring Organization:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE)
- DOE Contract Number:
- AC36-08GO28308
- OSTI ID:
- 1985636
- Report Number(s):
- NREL/CP-5D00-86597; MainId:87370; UUID:f01ed899-c7ec-4801-9f1f-4829ecb18b89; MainAdminID:69793
- Resource Relation:
- Conference: Presented at the 2022 IEEE 6th Conference on Energy Internet and Energy System Integration (EI2), 11-13 November 2022, Chengdu, China
- Country of Publication:
- United States
- Language:
- English
Similar Records
Physics-Informed Sparse Gaussian Process for Probabilistic Stability Analysis of Large-Scale Power System with Dynamic PVs and Loads
A Multi-Fidelity Gaussian Process Regression Method for Probabilistic Wind Farm Power Curve Estimation