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

Using spatio-temporal graph neural networks to estimate fleet-wide photovoltaic performance degradation patterns

Journal Article · · PLoS ONE
 [1];  [2];  [2];  [2];  [2];  [2]
  1. Case Western Reserve University, Cleveland, OH (United States); Case Western Reserve University
  2. Case Western Reserve University, Cleveland, OH (United States)
+ Show Author Affiliations

Accurate estimation of photovoltaic (PV) system performance is crucial for determining its feasibility as a power generation technology and financial asset. PV-based energy solutions offer a viable alternative to traditional energy resources due to their superior Levelized Cost of Energy (LCOE). A significant challenge in assessing the LCOE of PV systems lies in understanding the Performance Loss Rate (PLR) for large fleets of PV systems. Estimating the PLR of PV systems becomes increasingly important in the rapidly growing PV industry. Precise PLR estimation benefits PV users by providing real-time monitoring of PV module performance, while explainable PLR estimation assists PV manufacturers in studying and enhancing the performance of their products. However, traditional PLR estimation methods based on statistical models have notable drawbacks. Firstly, they require user knowledge and decision-making. Secondly, they fail to leverage spatial coherence for fleet-level analysis. Additionally, these methods inherently assume the linearity of degradation, which is not representative of real world degradation. To overcome these challenges, we propose a novel graph deep learning-based decomposition method called the Spatio-Temporal Graph Neural Network for fleet-level PLR estimation (PV-stGNN-PLR). PV-stGNN-PLR decomposes the power timeseries data into aging and fluctuation components, utilizing the aging component to estimate PLR. PV-stGNN-PLR exploits spatial and temporal coherence to derive PLR estimation for all systems in a fleet and imposes flatness and smoothness regularization in loss function to ensure the successful disentanglement between aging and fluctuation. We have evaluated PV-stGNN-PLR on three simulated PV datasets consisting of 100 inverters from 5 sites. Experimental results show that PV-stGNN-PLR obtains a reduction of 33.9% and 35.1% on average in Mean Absolute Percent Error (MAPE) and Euclidean Distance (ED) in PLR degradation pattern estimation compared to the state-of-the-art PLR estimation methods.

Research Organization:
Case Western Reserve University, Cleveland, OH (United States)
Sponsoring Organization:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Solar Energy Technologies Office
Grant/Contract Number:
EE0009353
OSTI ID:
2305501
Alternate ID(s):
OSTI ID: 2341612
OSTI ID: 2481545
Report Number(s):
DOE-CWRU-SETO--9353-230215-rxw497-1
Journal Information:
PLoS ONE, Journal Name: PLoS ONE Journal Issue: 2 Vol. 19; ISSN 1932-6203
Publisher:
Public Library of ScienceCopyright Statement
Country of Publication:
United States
Language:
English

References (19)

PV degradation curves: non-linearities and failure modes: PV degradation curves: non-linearities and failure modes journal September 2016
Photovoltaic lifetime forecast model based on degradation patterns journal July 2020
A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks journal May 2016
A correct validation of the National Solar Radiation Data Base (NSRDB) journal December 2018
A power-rating model for crystalline silicon PV modules journal December 2011
Best practices for photovoltaic performance loss rate calculations journal April 2022
Comparison of Statistical and Deterministic Smoothing Methods to Reduce the Uncertainty of Performance Loss Rate Estimates journal January 2018
Robust PV Degradation Methodology and Application journal March 2018
Review of Statistical and Analytical Degradation Models for Photovoltaic Modules and Systems as Well as Related Improvements journal November 2018
Modeling Outdoor Service Lifetime Prediction of PV Modules: Effects of Combined Climatic Stressors on PV Module Power Degradation journal July 2019
Nonlinear Photovoltaic Degradation Rates: Modeling and Comparison Against Conventional Methods journal July 2020
Spatio-temporal graph neural networks for multi-site PV power forecasting conference July 2022
Determining the Power Rate of Change of 353 Plant Inverters Time-Series Data Across Multiple Climate Zones, Using a Month-By-Month Data Science Analysis conference June 2017
Performance Loss Rate Consistency and Uncertainty Across Multiple Methods and Filtering Criteria conference June 2019
Efficient Long-Term Degradation Profiling in Time Series for Complex Physical Systems conference August 2015
Spatiotemporal Graph Neural Network for Performance Prediction of Photovoltaic Power Systems journal May 2021
pvlib python: a python package for modeling solar energy systems journal September 2018
Reducing Uncertainty of Fielded Photovoltaic Performance (Final Technical Report) report August 2022
Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification conference August 2021

Similar Records

Related Subjects

14 SOLAR ENERGY
Alternative energy
Cognitive science
Finance
Forecasting
Meteorology
Neural networks
Photovoltaic power
Simulation and modeling