DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Optimization of cleaning strategies based on ANN algorithms assessing the benefit of soiling rate forecasts

Terhag, Felix and Wolfertstetter, Fabian and Wilbert, Stefan and Schaudt, Oliver and Hirsch, Tobias (2019) Optimization of cleaning strategies based on ANN algorithms assessing the benefit of soiling rate forecasts. In: AIP Conference Proceedings, 2126 (220005), pp. 1-10. SolarPACES, 2.-5. October 2018, Casablanca, Morocco. DOI: 10.1063/1.5117764

[img] PDF
[img] PDF

Official URL: https://aip.scitation.org/doi/abs/10.1063/1.5117764


Soiling puts operators of solar power plants before the challenge of finding the right strategy for the cleaning of their solar fields. The trade-off between a low cleanliness and thus low revenues on the one hand and elevated cleaning costs and high field efficiency on the other hand has to be met. In this study we address this problem using a reinforced learning algorithm. Reinforced learning is a trial and error based learning process based on a scalar reward. The algorithms improve with an increasing number of training runs, each performed on a different one-year data set. The reward being the profit of the CSP project. In order to prevent overfitting to a special case, the training data has to be sufficiently large. To increase our 5 year soiling-rate and 25 year meteorological measurement data set from CIEMAT’s Plataforma Solar de Almeria (PSA). We first present a method to create artificial long term data sets based on These measurements that are representative of the sites’ weather conditions. With the extended datasets we are able to train the algorithm sufficiently before testing it on the validation dataset. The algorithm is given the daily choice to deploy up to two cleaning units in day and/or night shifts. In a second step, it is given soiling rate forecasts with different forecast horizons. At PSA our trained algorithm can increase a project’s profit by 1.28 % compared to a reference constant cleaning frequency (RPI) if only the current cleanliness of the solar field is known. If it is given a one day soiling-rate forecast the profit can be increased by 1.33 %. A three day soiling-rate-forecast can increase the profit by 1.37 %. An extended forecast horizon does not seem to increase the RPI further. For sites with higher dust loads than PSA the RPI is expected to be significantly higher than at PSA. Reinforced learning in combination with the data extension algorithm can be a useful method to increase a CSP project’s profit over its lifetime.

Item URL in elib:https://elib.dlr.de/125719/
Document Type:Conference or Workshop Item (Speech)
Title:Optimization of cleaning strategies based on ANN algorithms assessing the benefit of soiling rate forecasts
AuthorsInstitution or Email of AuthorsAuthor's ORCID iD
Wolfertstetter, Fabianfabian.wolfertstetter (at) dlr.dehttps://orcid.org/0000-0003-4323-8433
Wilbert, StefanStefan.Wilbert (at) dlr.dehttps://orcid.org/0000-0003-3573-3004
Hirsch, Tobiastobias.hirsch (at) dlr.dehttps://orcid.org/0000-0003-0063-0128
Date:25 July 2019
Journal or Publication Title:AIP Conference Proceedings
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In ISI Web of Science:No
DOI :10.1063/1.5117764
Page Range:pp. 1-10
Keywords:cleaning optimization, reinforced learning, ANN, soiling, CSP, parabolic trough
Event Title:SolarPACES
Event Location:Casablanca, Morocco
Event Type:international Conference
Event Dates:2.-5. October 2018
HGF - Research field:Energy
HGF - Program:Renewable Energies
HGF - Program Themes:Concentrating Solar Thermal Technology
DLR - Research area:Energy
DLR - Program:E SW - Solar and Wind Energy
DLR - Research theme (Project):E - Impact of Desert Environment
Location: Köln-Porz
Institutes and Institutions:Institute of Solar Research > Qualification
Deposited By: Kruschinski, Anja
Deposited On:08 Jan 2019 13:03
Last Modified:26 Jul 2020 03:00

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.