[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123063-en":3,"doc-seo-123063-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123063,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Development of a DNI Forecast Tool Based on Machine Learning for the Smart Operation of a Parabolic Trough Collector System with Thermal Energy Storage - Theory and Results","In the Smart Solar System (S3) research project, Solar-Institut Jülich (SIJ) developed hourly direct normal irradiance (DNI) forecast tools for same-day prediction to support smart operation of a parabolic trough collector (PTC) system with concrete thermal energy storage (C-TES) at KEAN Soft Drinks Ltd in Limassol, Cyprus. The paper develops a DNI forecast tool using an LSTM long short-term memory recurrent neural network and compares it with a non-machine-learning analytical approach. Real-life testing since end of 2022 enables validation against DNI measurements, showing markedly improved accuracy for the LSTM model at larger errors.","SolarPACES 2023, 29th International Conference on Concentrating Solar Power, Thermal, and Chemical Energy Systems  \nOperations, Maintenance, and Component Reliability [https://doi.org/10.52825/solarpaces.v2i.802](https://doi.org/10.52825/solarpaces.v2i.802)  \n© Authors. This work is licensed under a Creative Commons Attribution 4.0 International License Published: 15 Oct. 2024  \nDevelopment of a DNI Forecast Tool Based on Machine Learning for the Smart Operation of a Parabolic Trough Collector System with Thermal  \nEnergy Storage  \nTheory and Results  \nJohannes Christoph Sattler1, Siddharth Dutta2 , Spiros Alexopoulos 1, Adnan Kawam 1 , Cristiano Teixeira Boura 1, Ulf Herrmann1 , and Ioannis Kioutsioukis3  \n1 Solar-Institut Jülich (SIJ) of the FH Aachen University of Applied Sciences, Germany  \n2 Protarget AG, Zeissstrasse 5, 50859 Cologne, Germany  \n3 University of Patras, Laboratory of Atmospheric Physics, 26504 Rio, Patras, Greece  \n*Correspondence: Johannes Christoph Sattler, [sattler@sij.fh-aachen.de](sattler@sij.fh-aachen.de)  \nAbstract. In the research project Smart Solar System (S3), the Solar-Institut Jülich (SIJ) developed forecast tools to predict the direct normal irradiance (DNI) in hourly resolution for the current day. The aim of the daily DNI forecast is to use it as input to enable a smart operation of a parabolic trough collector (PTC) system with a concrete thermal energy storage (C-TES) located at the company KEAN Soft Drinks Ltd in Limassol, Cyprus. The main focus in this work is on the development of a DNI forecast tool based on long short-term memory (LSTM) , which is a recurrent neural network (RNN) , and its comparison with a DNI forecast tool based on analytical algorithms ( non-machine learning) . Only the non-machine learning DNI forecast tool with hourly update was tested in real-life PTC plant operation since end of 2022. The comparisons between the three DNI forecast tools show that the potential of using machine learning is very high. Different comparisons were made including an evaluation of the accuracy of the tool (i.e. comparison of the DNI forecast data with DNI measurement data) . The DNI forecast based on the LSTM network proved to be more accurate than the nonmachine learning DNI forecasts when considering errors greater than ± 100 W/m2. The error of the LSTM network compared to DNI measurement data was as follows: 43.6 % of the data was within ± 100 W/m2 , 74.8 % was within ±200 W/m2 , 89.8 % was within ±300 W/m2 and 95.8 % was within ±400 W/m2.  \nKeywords: Direct Normal Irradiance ( DNI) Forecasting, Long Short-Term Memory ( LSTM), Recurrent Neural Network, RNN, Parabolic Trough Collector, PTC, Thermal Energy Storage, TES  \n1. Introduction  \nIn the research project Smart Solar System (S3), funded by national and regional funding organisations in the European network SOLAR-ERA. NET, the Solar-Institut Jülich (SIJ) developed forecast tools to predict the direct normal irradiance (DNI) in hourly resolution for  \nthe current day. The aim of the daily DNI forecast is to use it as input to enable a smart operation of a parabolic trough collector (PTC) system with a concrete thermal energy storage (C-TES) located at the company KEAN Soft Drinks Ltd in Limassol, Cyprus. More details on the PTC system and C-TES are described in [1], [2] and [3] . First results for a non-machine learning DNI forecasting tool developed by the SIJ were published by [4], hereafter referred to as method 1. In the present work, a DNI forecast tool based on a long short-term memory (LSTM) network, which is a recurrent neural network (RNN), was developed using the Keras library in Python (method 2) . An RNN is a type of artificial neural network (ANN) . An RNN network can process time series data or sequences [5], which is why it is suitable for DNI forecasting. Also, method 1 was developed further.  \nThe novelty of this paper is to present non-hardware based and low-cost options for DNI forecasting using ordinary weat","cbCaii5dm0Qnu3bd","https://ap.wps.com/l/cbCaii5dm0Qnu3bd","pdf",943414,1,10,"English","en",105,"# Introduction\n## Research background and objectives\n## Forecast tool methods (1–3)\n## Weather inputs and data handling\n## Validation concept and comparison approach","[{\"question\":\"What problem does the paper address and what is the application goal?\",\"answer\":\"The paper targets hourly forecasts of direct normal irradiance (DNI) for the current day, to enable smart operation of a parabolic trough collector system with concrete thermal energy storage located at KEAN Soft Drinks Ltd in Cyprus.\"},{\"question\":\"What forecasting methods are compared in the study?\",\"answer\":\"Three methods are evaluated: Method 1 uses an analytical algorithm with a once-nightly 24-hour update, Method 2 uses an LSTM-based recurrent neural network with hourly resolution, and Method 3 uses an analytical algorithm with hourly updates tested in real-life PTC operation.\"},{\"question\":\"How does the LSTM approach perform compared with analytical forecasting?\",\"answer\":\"The LSTM-based DNI forecast is more accurate than the non-machine-learning approaches for larger errors beyond ±100 W/m2, with 43.6% of data within ±100 W/m2 and 95.8% within ±400 W/m2 when compared to DNI measurements.\"}]","Development of a DNI Forecast Tool Based on Machine Learning for the Smart Operation of a Parabolic Trough Collector System with Thermal Energy Storage - Theory and Results | PDF",1785814465,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"development-of-a-dni-forecast-tool-based-on-machine-learning-for-the-smart-operation-of-a-parabolic-trough-collector-system-with-thermal-energy-storage-theory-and-results","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/development-of-a-dni-forecast-tool-based-on-machine-learning-for-the-smart-operation-of-a-parabolic-trough-collector-system-with-thermal-energy-storage-theory-and-results/123063/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does the paper address and what is the application goal?","Question",{"text":76,"@type":77},"The paper targets hourly forecasts of direct normal irradiance (DNI) for the current day, to enable smart operation of a parabolic trough collector system with concrete thermal energy storage located at KEAN Soft Drinks Ltd in Cyprus.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What forecasting methods are compared in the study?",{"text":81,"@type":77},"Three methods are evaluated: Method 1 uses an analytical algorithm with a once-nightly 24-hour update, Method 2 uses an LSTM-based recurrent neural network with hourly resolution, and Method 3 uses an analytical algorithm with hourly updates tested in real-life PTC operation.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the LSTM approach perform compared with analytical forecasting?",{"text":85,"@type":77},"The LSTM-based DNI forecast is more accurate than the non-machine-learning approaches for larger errors beyond ±100 W/m2, with 43.6% of data within ±100 W/m2 and 95.8% within ±400 W/m2 when compared to DNI measurements.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":21,"slug":134},"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]