Revenue prediction for integrated renewable energy and energy storage system using machine learning techniques

Lin, Yingqian; Li, Binghui; Moiser, Thomas M.; Griffel, L. Michael; Mahalik, Matthew R.; Kwon, Jonghwan; Shafiul Alam, S. M.

doi:10.1016/j.est.2022.104123

Revenue prediction for integrated renewable energy and energy storage system using machine learning techniques

Journal Article · Thu Feb 17 00:00:00 EST 2022 · Journal of Energy Storage

DOI:https://doi.org/10.1016/j.est.2022.104123· OSTI ID:1903574

^[1]; ^[1]; Moiser, Thomas M. ^[1]; Griffel, L. Michael ^[2]; Mahalik, Matthew R. ^[3]; Kwon, Jonghwan ^[3]; ^[1]

Idaho National Lab. (INL), Idaho Falls, ID (United States)
Idaho State Univ., Pocatello, ID (United States)
Argonne National Lab. (ANL), Lemont, IL (United States)

Revenue estimation for integrated renewable energy and energy storage systems is important to support plant owners or operators’ decisions in battery sizing selection that leads to maximized financial performances. A common approach to optimizing revenues of a hybrid hydro and energy storage system is using mixed-integer linear programming (MILP). Although MILP models can provide accurate production cost estimations, they are typically very computationally expensive. To provide a fast yet accurate first-step information to hydropower plant owners or operators who consider integrating energy storage systems, we propose an innovative approach to predicting optimal revenues of an integrated energy generation and storage system. In this study, we examined the performance of two prediction techniques: Generalized Additive Models (GAMs) and machine learning (ML) models developed based on artificial neural networks (ANN). Predictive equations and models are generated based on optimized solutions from a market participation optimization model, the Conventional Hydropower Energy and Environmental Resource System (CHEERS) model. The two predicting techniques reduce the computational time to evaluate annual revenue for one set of battery configurations from 3 h to 1 to 4 min per run while also being implementable with significantly less data. The model validation prediction errors of developed GAMs and ML models are generally below 5%; for model testing predictions, the ML models consistently outperform the regression equations in terms of root mean square errors. This new approach allows plant owners, operators, or potential investors to quickly access multiple battery configurations under different energy generation and market scenarios. This new revenue prediction method will therefore help reduce the barriers, and thereby promoting the deployment of battery hybridization with existing renewable energy sources.

View Accepted Manuscript (DOE)

Research Organization:: Idaho National Laboratory (INL), Idaho Falls, ID (United States)

Sponsoring Organization:: USDOE Office of Nuclear Energy (NE)

Grant/Contract Number:: AC07-05ID14517

OSTI ID:: 1903574

Report Number(s):: INL/JOU-21-64535-Rev001

Journal Information:: Journal of Energy Storage, Journal Name: Journal of Energy Storage Vol. 50; ISSN 2352-152X

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (16)

Logistic regression and artificial neural network classification models: a methodology review Dreiseitl, Stephan; Ohno-Machado, Lucila Journal of Biomedical Informatics, Vol. 35, Issue 5-6 https://doi.org/10.1016/S1532-0464(03)00034-0	journal	October 2002
A survey of artificial neural network in wind energy systems Marugán, Alberto Pliego; Márquez, Fausto Pedro García; Perez, Jesus María Pinar Applied Energy, Vol. 228 https://doi.org/10.1016/j.apenergy.2018.07.084	journal	October 2018
Auction optimization using regression trees and linear models as integer programs Verwer, Sicco; Zhang, Yingqian; Ye, Qing Chuan Artificial Intelligence, Vol. 244 https://doi.org/10.1016/j.artint.2015.05.004	journal	March 2017
Empirical decision model learning Lombardi, Michele; Milano, Michela; Bartolini, Andrea Artificial Intelligence, Vol. 244 https://doi.org/10.1016/j.artint.2016.01.005	journal	March 2017
Real time power management strategy for hybrid energy storage systems coupled with variable energy sources in power smoothing applications Barelli, L.; Bidini, G.; Ciupageanu, D. A. Energy Reports, Vol. 7 https://doi.org/10.1016/j.egyr.2021.05.018	journal	November 2021
Distributional modeling and short-term forecasting of electricity prices by Generalized Additive Models for Location, Scale and Shape Serinaldi, Francesco Energy Economics, Vol. 33, Issue 6 https://doi.org/10.1016/j.eneco.2011.05.001	journal	November 2011
Intelligent control strategy for a grid connected PV/SOFC/BESS energy generation system Chettibi, N.; Mellit, A. Energy, Vol. 147 https://doi.org/10.1016/j.energy.2018.01.030	journal	March 2018
Techno-economic study driven based on available efficiency index for optimal operation of a smart grid in the presence of energy storage system Afzali, Peyman; Anjom Shoa, Nadia; Rashidinejad, Masoud Journal of Energy Storage, Vol. 32 https://doi.org/10.1016/j.est.2020.101853	journal	December 2020
GEFCom2014: Probabilistic solar and wind power forecasting using a generalized additive tree ensemble approach Nagy, Gábor I.; Barta, Gergő; Kazi, Sándor International Journal of Forecasting, Vol. 32, Issue 3 https://doi.org/10.1016/j.ijforecast.2015.11.013	journal	July 2016
Impacts of a forecast-based operation strategy for grid-connected PV storage systems on profitability and the energy system Klingler, Anna-Lena; Teichtmann, Lukas Solar Energy, Vol. 158 https://doi.org/10.1016/j.solener.2017.10.052	journal	December 2017
Machine learning approaches to the unit commitment problem: Current trends, emerging challenges, and new strategies Yang, Yafei; Wu, Lei The Electricity Journal, Vol. 34, Issue 1 https://doi.org/10.1016/j.tej.2020.106889	journal	January 2021
Artificial neural networks: a tutorial Jain, A. K.; Mohiuddin, K. M. Computer, Vol. 29, Issue 3 https://doi.org/10.1109/2.485891	journal	March 1996
Innovative power management of hybrid energy storage systems coupled to RES plants: The Simultaneous Perturbation Stochastic Approximation approach Ciupageanu, Dana-Alexandra; Barelli, Linda; Ottaviano, Andrea 2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe) https://doi.org/10.1109/ISGTEurope.2019.8905775	conference	September 2019
A Novel Electricity Price Forecasting Approach Based on Dimension Reduction Strategy and Rough Artificial Neural Networks Jahangir, Hamidreza; Tayarani, Hanif; Baghali, Sina IEEE Transactions on Industrial Informatics, Vol. 16, Issue 4 https://doi.org/10.1109/TII.2019.2933009	journal	April 2020
Local Short and Middle Term Electricity Load Forecasting With Semi-Parametric Additive Models Goude, Yannig; Nedellec, Raphael; Kong, Nicolas IEEE Transactions on Smart Grid, Vol. 5, Issue 1 https://doi.org/10.1109/TSG.2013.2278425	journal	January 2014
Generalized additive models for large data sets Wood, Simon N.; Goude, Yannig; Shaw, Simon Journal of the Royal Statistical Society: Series C (Applied Statistics), Vol. 64, Issue 1 https://doi.org/10.1111/rssc.12068	journal	May 2014

Similar Records

RODeO (Revenue Operation and Device Optimization Model) [SWR 20-67]

Software · Mon Jun 22 20:00:00 EDT 2020 · OSTI ID:code-45155

A deep learning-based battery sizing optimization tool for hybridizing generation plants

Journal Article · Tue Jan 02 19:00:00 EST 2024 · Renewable Energy · OSTI ID:2373075

Hydro-battery Hybrids – A Case for Holistic Assessment of Hybrid Energy Systems

Conference · Thu Dec 29 23:00:00 EST 2022 · OSTI ID:1922438

Related Subjects

13 HYDRO ENERGY
25 ENERGY STORAGE
Decision making
Energy storage
Hydropower
Integrated energy system
Machine learning techniques
Renewable energy
Revenue optimization

Revenue prediction for integrated renewable energy and energy storage system using machine learning techniques

Citation Formats

References (16)

Similar Records

Related Subjects