Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Semi-Supervised, Non-Intrusive Disaggregation of Nodal Load Profiles With Significant Behind-the-Meter Solar Generation

Journal Article · · IEEE Transactions on Power Systems
It is of imperative interests for regional transmission organizations (RTOs) to effectively extract actual load profiles at transmission nodes with significant behind-the-meter solar generation, which remains a gap in the existing technology paradigm. This paper proposes an explicit yet efficient linear estimator to disaggregate actual load profiles at transmission buses with significant behind-the-meter (BTM) solar generations. The proposed estimator is based on disaggregating (i.e., extracting) at locations close to transmission buses under consideration. Further, to overcome the lack of “ground truth” and validate the performance of the proposed algorithms, we first propose semi-supervised mechanisms with parameter tuning as well as unsupervised clustering and leverage the unique characteristics of zero-crossing points in BTM solar peaking behaviors, which we refer to as “Zone-to-Node (Z2N)” methods. Next, we further propose a bi-level Node-to-Node (N2N) framework that improves the overall disaggregation performances compared to Z2N. Numerical results are presented using real-world data at PJM Interconnection.
Research Organization:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Sponsoring Organization:
USDOE
Grant/Contract Number:
AC05-76RL01830
OSTI ID:
2339614
Report Number(s):
PNNL-SA--191770
Journal Information:
IEEE Transactions on Power Systems, Journal Name: IEEE Transactions on Power Systems Journal Issue: 3 Vol. 39; ISSN 0885-8950
Publisher:
IEEECopyright Statement
Country of Publication:
United States
Language:
English

References (29)

A survey on semi-supervised learning journal November 2019
A Practical Approach to Feature Selection book January 1992
An area-based shape distance measure of time series journal November 2016
Forecasting day-ahead electricity load using a multiple equation time series approach journal June 2016
Disaggregating solar generation from feeder-level measurements journal March 2018
A Fast Estimation Method for the Vector Autoregressive Moving Average Model with Exogenous Variables journal December 1983
The self-organizing map journal January 1990
A review of identification and monitoring methods for electric loads in commercial and residential buildings conference September 2010
A Data-Driven Democratized Control Architecture for Regional Transmission Operators conference April 2022
Self-organizing classification and identification of miscellaneous electric loads
  • Du, L.; He, D.; Yang, Y.
  • 2012 IEEE Power & Energy Society General Meeting. New Energy Horizons - Opportunities and Challenges, 2012 IEEE Power and Energy Society General Meeting https://doi.org/10.1109/PESGM.2012.6343927
conference July 2012
Solar forecasting as an enablement tool for the distribution system operator (DSO) conference June 2019
Unsupervised Disaggregation of Photovoltaic Production From Composite Power Flow Measurements of Heterogeneous Prosumers journal September 2018
An Adaptive Machine Learning Framework for Behind-the-Meter Load/PV Disaggregation journal October 2021
A New Distance Measure for Model-Based Sequence Clustering journal July 2009
Clustering Technique Applied to Nodal Reliability Indices for Optimal Planning of Energy Resources journal November 2016
A Data-Driven Game-Theoretic Approach for Behind-the-Meter PV Generation Disaggregation journal July 2020
A Linear Programming Approximation of Distributionally Robust Chance-Constrained Dispatch With Wasserstein Distance journal September 2020
Data-Driven Distributionally Robust Unit Commitment With Wasserstein Metric: Tractable Formulation and Efficient Solution Method journal November 2020
Disaggregating Customer-Level Behind-the-Meter PV Generation Using Smart Meter Data and Solar Exemplars journal November 2021
Bayesian Energy Disaggregation At Substations With Uncertainty Modeling journal January 2022
Nonintrusive, Self-Organizing, and Probabilistic Classification and Identification of Plugged-In Electric Loads journal September 2013
Separating Feeder Demand Into Components Using Substation, Feeder, and Smart Meter Measurements journal July 2020
A Deep Generative Model for Non-Intrusive Identification of EV Charging Profiles journal November 2020
Unsupervised Clustering-Based Short-Term Solar Forecasting journal October 2019
Joint Estimation of Behind-the-Meter Solar Generation in a Community journal January 2021
Least Absolute Deviations Curve-Fitting journal June 1980
Disaggregating solar generation behind individual meters in real time conference November 2018
Quantile Regression journal November 2001
Queued Up: Characteristics of Power Plants Seeking Transmission Interconnection As of the End of 2022 [Slides] report April 2023