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
 

Privacy-preserving federated learning: Application to behind-the-meter solar photovoltaic generation forecasting

Journal Article · · Energy Conversion and Management
 [1];  [2];  [3];  [2]
  1. Indiana Univ.-Purdue Univ. Indianapolis (IUPUI), Indianapolis, IN (United States); OSTI
  2. Indiana Univ.-Purdue Univ. Indianapolis (IUPUI), Indianapolis, IN (United States)
  3. Stevens Institute of Technology, Hoboken, NJ (United States)
+ Show Author Affiliations
Here, the growing usage of decentralized renewable energy sources has made accurate estimation of their aggregated generation crucial for maintaining grid flexibility and reliability. However, the majority of distributed photovoltaic (PV) systems are behind-the-meter (BTM) and invisible to utilities, leading to three challenges in obtaining an accurate forecast of their aggregated output. Firstly, traditional centralized prediction algorithms used in previous studies may not be appropriate due to privacy concerns. There is therefore a need for decentralized forecasting methods, such as federated learning (FL), to protect privacy. Secondly, there has been no comparison between localized, centralized, and decentralized forecasting methods for BTM PV production, and the trade-off between prediction accuracy and privacy has not been explored. Lastly, the computational time of data-driven prediction algorithms has not been examined. This article presents a FL power forecasting method for PVs, which uses federated learning as a decentralized collaborative modeling approach to train a single model on data from multiple BTM sites. The machine learning network used to design this FL-based BTM PV forecasting model is a multi-layered perceptron, which ensures privacy and security of the data. Comparing the suggested FL forecasting model to non-private centralized and entirely private localized models revealed that it has a high level of accuracy, with an RMSE that is 18.17% lower than localized models and 9.9% higher than centralized models.
Research Organization:
Indiana Univ., Bloomington, IN (United States)
Sponsoring Organization:
USDOE; USDOE Office of Energy Efficiency and Renewable Energy (EERE)
Grant/Contract Number:
EE0007711
OSTI ID:
2417657
Alternate ID(s):
OSTI ID: 1967513
Journal Information:
Energy Conversion and Management, Journal Name: Energy Conversion and Management Journal Issue: C Vol. 283; ISSN 0196-8904
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (28)

Regional PV power prediction for improved grid integration journal September 2010
Analysis of daily solar power prediction with data-driven approaches journal August 2014
Learning-based CO2 concentration prediction: Application to indoor air quality control using demand-controlled ventilation journal November 2021
Image-based dataset of artifact surfaces fabricated by additive manufacturing with applications in machine learning journal April 2022
Taxonomy research of artificial intelligence for deterministic solar power forecasting journal June 2020
Intermittent solar power hybrid forecasting system based on pattern recognition and feature extraction journal February 2023
Energy, exergy, and economic analysis of a centralized solar and biogas hybrid heating system for rural areas journal January 2023
Techno-economic analysis of solar aided liquid air energy storage system with a new air compression heat utilization method journal February 2023
High dimensional very short-term solar power forecasting based on a data-driven heuristic method journal March 2021
High-resolution net load forecasting for micro-neighbourhoods with high penetration of renewable energy sources journal May 2020
Distributed load forecasting using smart meter data: Federated learning with Recurrent Neural Networks journal May 2022
Model predictive control of heating, ventilation, and air conditioning (HVAC) systems: A state-of-the-art review journal November 2022
Solar radiation forecast based on fuzzy logic and neural networks journal December 2013
Online 24-h solar power forecasting based on weather type classification using artificial neural network journal November 2011
Analysis of the uncertainty in the estimates of regional PV power generation evaluated with the upscaling method journal October 2016
A power prediction model and its validation for a roof top photovoltaic power plant considering module degradation journal August 2021
Local energy markets design for integrated distribution energy systems based on the concept of transactive peer‐to‐peer market journal August 2021
Pandemic-Aware Day-Ahead Demand Forecasting Using Ensemble Learning journal January 2022
Irradiance Forecasting for the Power Prediction of Grid-Connected Photovoltaic Systems journal March 2009
Federated Learning: Challenges, Methods, and Future Directions journal May 2020
Federated Reinforcement Learning for Energy Management of Multiple Smart Homes With Distributed Energy Resources journal January 2022
Exploring Key Weather Factors From Analytical Modeling Toward Improved Solar Power Forecasting journal March 2019
A Privacy-Preserving Federated Learning Method for Probabilistic Community-Level Behind-the-Meter Solar Generation Disaggregation journal January 2022
A Weather-Based Hybrid Method for 1-Day Ahead Hourly Forecasting of PV Power Output journal July 2014
An Improved Photovoltaic Power Forecasting Model With the Assistance of Aerosol Index Data journal April 2015
High-Precision Forecasting Model of Solar Irradiance Based on Grid Point Value Data Analysis for an Efficient Photovoltaic System journal April 2015
Feature Selection Techniques for the Analysis of Discriminative Features in Temporal and Frontal Lobe Epilepsy: A Comparative Study journal June 2021
Carbon Footprint Assessment in the Life-Cycle Design of Concrete Structures in the Tropics: A Case Study of Residential Buildings in Malaysia journal August 2020

Figures / Tables (14)

Figure 1(p. 2)figure Figure 1
Table 1(p. 5)table Table 1
Figure 2(p. 7)figure Figure 2
Figure 3(p. 9)figure Figure 3
Figure 4(p. 10)figure Figure 4
Figure 5(p. 11)figure Figure 5
Figure 6(p. 12)figure Figure 6
Table 2(p. 13)table Table 2
Figure 7(p. 15)figure Figure 7
Table 3(p. 15)table Table 3
Figure 8(p. 16)figure Figure 8
Table 4(p. 16)table Table 4
Figure 9(p. 18)figure Figure 9
Table 5(p. 18)table Table 5

Similar Records

Privacy-Preserving Real-Time Action Detection in Intelligent Vehicles Using Federated Learning-Based Temporal Recurrent Network
Journal Article · Wed Jul 17 20:00:00 EDT 2024 · Electronics · OSTI ID:2438866
Federated Deep Reinforcement Learning for Decentralized VVO of BTM DERs
Conference · Tue Oct 01 00:00:00 EDT 2024 · OSTI ID:2477510

Related Subjects

14 SOLAR ENERGY
24 POWER TRANSMISSION AND DISTRIBUTION
Behind-the-meter
Energy & Fuels
Federated learning
Machine learning
Mechanics
Privacy-enhanced
Thermodynamics